mirror of
https://github.com/agentscope-ai/ReMe.git
synced 2026-10-24 05:47:32 +00:00
docs: compare compaction-only costs and omit Full from cost panel
This commit is contained in:
jinli.yl
parent
21f754b08a
commit
7686be7baa
8 changed files with 178 additions and 186 deletions
|
|
@ -73,5 +73,5 @@ For the recorded format amendment, native summaries used the pre-amendment sourc
|
|||
and permits only the held-out `exam` field to differ; the summary generator never receives that field.
|
||||
|
||||
`costs.json` reports standalone summary/ranking input and output overhead separately from answer usage, including
|
||||
recorded retries. The chart converts summary + Jev + one Qwen answer usage to estimated USD with the dated rates in
|
||||
[pricing.json](./pricing.json); cache discounts and trajectory collection are excluded. See [the formula](./SETTINGS.md#scoring-and-costs).
|
||||
recorded retries. Panel C converts summary + Jev compaction usage to estimated USD with the dated rates in
|
||||
[pricing.json](./pricing.json); cache discounts, downstream answering and trajectory collection are excluded. Full appears in A/B only. See [the formula](./SETTINGS.md#scoring-and-costs).
|
||||
|
|
|
|||
|
|
@ -8,46 +8,42 @@ each summary remains byte-identical across its six conditions.
|
|||
|
||||
## Four primary tasks
|
||||
|
||||
| Method | Fact score | Answer input | Summary in / out | Jev in / out | Total USD |
|
||||
| Method | Fact score | Answer input | Summary in / out | Jev in / out | Compaction USD |
|
||||
| --- | ---: | ---: | ---: | ---: | ---: |
|
||||
| Full context | 100.0% | 4,014 | 0 / 0 | 0 / 0 | $0.006992 |
|
||||
| S | 82.0% | 2,480 | 5,379 / 200 | 0 / 0 | $0.014293 |
|
||||
| S + Jev Top 1 | 83.0% | 2,753 | 5,379 / 200 | 4,162 / 344 | $0.014920 |
|
||||
| S + Jev Top 2 | 94.5% | 2,974 | 5,379 / 200 | 4,162 / 344 | $0.015289 |
|
||||
| S + Jev Top 3 | 99.5% | 3,241 | 5,379 / 200 | 4,162 / 344 | $0.015738 |
|
||||
| S + Jev Top 4 | 98.1% | 3,496 | 5,379 / 200 | 4,162 / 344 | $0.016166 |
|
||||
| S + Jev Top 5 | 97.4% | 3,660 | 5,379 / 200 | 4,162 / 344 | $0.016429 |
|
||||
| H (Hermes, small budget) | 79.4% | 2,432 | 3,120 / 152 | 0 / 0 | $0.010245 |
|
||||
| H + Jev Top 1 | 85.3% | 2,705 | 3,120 / 152 | 4,162 / 344 | $0.010877 |
|
||||
| H + Jev Top 2 | 92.9% | 2,927 | 3,120 / 152 | 4,162 / 344 | $0.011244 |
|
||||
| H + Jev Top 3 | 97.9% | 3,193 | 3,120 / 152 | 4,162 / 344 | $0.011697 |
|
||||
| H + Jev Top 4 | 96.9% | 3,448 | 3,120 / 152 | 4,162 / 344 | $0.012114 |
|
||||
| H + Jev Top 5 | 96.9% | 3,613 | 3,120 / 152 | 4,162 / 344 | $0.012388 |
|
||||
| Full context | 100.0% | 4,014 | 0 / 0 | 0 / 0 | — |
|
||||
| S | 82.0% | 2,480 | 5,379 / 200 | 0 / 0 | $0.009864 |
|
||||
| S + Jev Top 1 | 83.0% | 2,753 | 5,379 / 200 | 4,162 / 344 | $0.010039 |
|
||||
| S + Jev Top 2 | 94.5% | 2,974 | 5,379 / 200 | 4,162 / 344 | $0.010039 |
|
||||
| S + Jev Top 3 | 99.5% | 3,241 | 5,379 / 200 | 4,162 / 344 | $0.010039 |
|
||||
| S + Jev Top 4 | 98.1% | 3,496 | 5,379 / 200 | 4,162 / 344 | $0.010039 |
|
||||
| S + Jev Top 5 | 97.4% | 3,660 | 5,379 / 200 | 4,162 / 344 | $0.010039 |
|
||||
| H (Hermes, small budget) | 79.4% | 2,432 | 3,120 / 152 | 0 / 0 | $0.005902 |
|
||||
| H + Jev Top 1 | 85.3% | 2,705 | 3,120 / 152 | 4,162 / 344 | $0.006077 |
|
||||
| H + Jev Top 2 | 92.9% | 2,927 | 3,120 / 152 | 4,162 / 344 | $0.006077 |
|
||||
| H + Jev Top 3 | 97.9% | 3,193 | 3,120 / 152 | 4,162 / 344 | $0.006077 |
|
||||
| H + Jev Top 4 | 96.9% | 3,448 | 3,120 / 152 | 4,162 / 344 | $0.006077 |
|
||||
| H + Jev Top 5 | 96.9% | 3,613 | 3,120 / 152 | 4,162 / 344 | $0.006077 |
|
||||
|
||||
|
||||
|
||||
|
||||
Both summary mechanisms benefit on this panel: S rises from **82.0% to 99.5%** at Top 3; H rises from **79.4% to 97.9%**.
|
||||
Mean downstream inputs at Top 3 are **3,241 / 3,193**, versus Full's **4,014**: reductions of **19.3% / 20.4%**.
|
||||
Top 4–5 do not improve these point estimates. This is an exploratory result on four synthetic task templates,
|
||||
not a general optimal-N claim, equivalence test or proof that Jev beats other equal-budget selectors.
|
||||
|
||||
Panel C plots **one-compression + one-answer total fees** against Top N, separately for S and H.
|
||||
S increases from **$0.014293** at Top 0 to **$0.016429** at Top 5;
|
||||
H increases from **$0.010245** to **$0.012388**.
|
||||
Full's answering fee is **$0.006992**. More selected evidence increases downstream Qwen input cost;
|
||||
Jev's ranking fee itself stays **$0.000175** for every N > 0.
|
||||
Panel C compares **compaction fees only: summary generation + Jev ranking**, with Full omitted.
|
||||
Top 0 costs **$0.009864 for S / $0.005902 for H**. Top 1–5 each cost **$0.010039 / $0.006077**.
|
||||
Jev adds **$0.000175** once per compaction, about **1.8% / 3.0%** above S/H summary generation respectively.
|
||||
The plateau is expected: Jev scores all available evidence once, then different N values retain different score prefixes.
|
||||
|
||||
## Token and cost accounting
|
||||
|
||||
Token columns are mean actual provider usage. Answer input includes the original system/task, summary/evidence and
|
||||
held-out question. **Total USD** includes one summary generation, one complete Jev ranking for N > 0, and **one Qwen
|
||||
answer (input + output)**. Recorded summary/ranking retries are included; trajectory collection and calibration are
|
||||
excluded. Full pays its answering fee and has no compression preprocessing. The two scoring repeats estimate the
|
||||
mean cost of one answer; preprocessing is charged once, not amortized across them.
|
||||
|
||||
For reference, preprocessing alone costs S $0.009864 / H $0.005902 at Top 0,
|
||||
or S $0.010039 / H $0.006077 with Jev. Those preprocessing fees stay flat
|
||||
at Top 1–5; the **overall** curve rises because the selected evidence must be read by Qwen when answering.
|
||||
Token columns are mean actual provider usage. Answer input remains a separate context-length metric, including the
|
||||
original system/task, compressed evidence and held-out question. **Compaction USD** includes one summary generation
|
||||
and one complete Jev ranking for N > 0, including recorded retries. **Downstream answering, trajectory collection and
|
||||
calibration are excluded.** Full does not perform compaction and has no fee entry in this comparison (shown as “—”);
|
||||
it remains the reference for answer quality and input length in A/B. No zero-total-cost claim is made for Full.
|
||||
The two scoring repeats do not amortize compaction fees.
|
||||
|
||||
Prices checked **2026-10-16**, per million tokens:
|
||||
|
||||
|
|
@ -56,12 +52,11 @@ Prices checked **2026-10-16**, per million tokens:
|
|||
| Qwen `qwen3.8-max`, China (Beijing) | $1.65 | $4.951 | [Alibaba Cloud](https://www.alibabacloud.com/help/en/model-studio/qwen3-8-max) |
|
||||
| Jev `jev-1.13.0`, direct TypeSafe | $0.042 | $0 | [TypeSafe](https://docs.typesafe.ai/models) |
|
||||
|
||||
`total_usd = ((summary_input + answer_input) × 1.65 + (summary_output + answer_output) × 4.951
|
||||
+ jev_input × 0.042) / 1,000,000`.
|
||||
`compaction_usd = (summary_input × 1.65 + summary_output × 4.951 + jev_input × 0.042) / 1,000,000`.
|
||||
[pricing.json](./pricing.json) freezes the rates, sources and scope. These are **uncached public-list-price estimates**:
|
||||
all prompt tokens are priced at the regular input rate, even where API usage reports cache hits. Free quotas, discounts,
|
||||
credits, taxes and account billing differences are excluded. This is a one-answer list-price comparison, not invoice reconciliation. In this horizon every compressed method
|
||||
costs more than Full; future-turn amortization or total savings have not been established.
|
||||
all summary prompt tokens are priced at the regular input rate, even where API usage reports cache hits. Free quotas,
|
||||
discounts, credits, taxes and account billing differences are excluded. This measures the incremental cost of adding
|
||||
Jev to a summary, not end-to-end monetary savings or invoice reconciliation.
|
||||
One shared ranking serves Top 1–5 and both mechanisms in the experiment; each standalone fused method includes its full
|
||||
cost, neither multiplied by N nor divided across sweep conditions.
|
||||
|
||||
|
|
@ -90,21 +85,21 @@ the other 38 comprise 9 primary and 29 control contexts. All remain scored. Aver
|
|||
<details>
|
||||
<summary>Ten short/query-only controls</summary>
|
||||
|
||||
| Method | Fact score | Answer input | Summary in / out | Jev in / out | Total USD |
|
||||
| Method | Fact score | Answer input | Summary in / out | Jev in / out | Compaction USD |
|
||||
| --- | ---: | ---: | ---: | ---: | ---: |
|
||||
| Full context | 100.0% | 2,727 | 0 / 0 | 0 / 0 | $0.004692 |
|
||||
| S | 67.1% | 2,315 | 1,099 / 74 | 0 / 0 | $0.006175 |
|
||||
| S + Jev Top 1 | 84.7% | 2,493 | 1,099 / 74 | 929 / 50 | $0.006517 |
|
||||
| S + Jev Top 2 | 87.5% | 2,573 | 1,099 / 74 | 929 / 50 | $0.006654 |
|
||||
| S + Jev Top 3 | 92.9% | 2,687 | 1,099 / 74 | 929 / 50 | $0.006843 |
|
||||
| S + Jev Top 4 | 92.9% | 2,722 | 1,099 / 74 | 929 / 50 | $0.006901 |
|
||||
| S + Jev Top 5 | 92.5% | 2,722 | 1,099 / 74 | 929 / 50 | $0.006901 |
|
||||
| H (Hermes, small budget) | 73.2% | 2,308 | 1,944 / 69 | 0 / 0 | $0.007532 |
|
||||
| H + Jev Top 1 | 80.1% | 2,486 | 1,944 / 69 | 929 / 50 | $0.007871 |
|
||||
| H + Jev Top 2 | 92.5% | 2,566 | 1,944 / 69 | 929 / 50 | $0.008019 |
|
||||
| H + Jev Top 3 | 99.2% | 2,680 | 1,944 / 69 | 929 / 50 | $0.008204 |
|
||||
| H + Jev Top 4 | 99.2% | 2,715 | 1,944 / 69 | 929 / 50 | $0.008263 |
|
||||
| H + Jev Top 5 | 98.8% | 2,715 | 1,944 / 69 | 929 / 50 | $0.008264 |
|
||||
| Full context | 100.0% | 2,727 | 0 / 0 | 0 / 0 | — |
|
||||
| S | 67.1% | 2,315 | 1,099 / 74 | 0 / 0 | $0.002179 |
|
||||
| S + Jev Top 1 | 84.7% | 2,493 | 1,099 / 74 | 929 / 50 | $0.002218 |
|
||||
| S + Jev Top 2 | 87.5% | 2,573 | 1,099 / 74 | 929 / 50 | $0.002218 |
|
||||
| S + Jev Top 3 | 92.9% | 2,687 | 1,099 / 74 | 929 / 50 | $0.002218 |
|
||||
| S + Jev Top 4 | 92.9% | 2,722 | 1,099 / 74 | 929 / 50 | $0.002218 |
|
||||
| S + Jev Top 5 | 92.5% | 2,722 | 1,099 / 74 | 929 / 50 | $0.002218 |
|
||||
| H (Hermes, small budget) | 73.2% | 2,308 | 1,944 / 69 | 0 / 0 | $0.003550 |
|
||||
| H + Jev Top 1 | 80.1% | 2,486 | 1,944 / 69 | 929 / 50 | $0.003589 |
|
||||
| H + Jev Top 2 | 92.5% | 2,566 | 1,944 / 69 | 929 / 50 | $0.003589 |
|
||||
| H + Jev Top 3 | 99.2% | 2,680 | 1,944 / 69 | 929 / 50 | $0.003589 |
|
||||
| H + Jev Top 4 | 99.2% | 2,715 | 1,944 / 69 | 929 / 50 | $0.003589 |
|
||||
| H + Jev Top 5 | 98.8% | 2,715 | 1,944 / 69 | 929 / 50 | $0.003589 |
|
||||
|
||||
These controls are not ten additional long-context tasks. Their small source-unit counts can make Top N saturate.
|
||||
|
||||
|
|
|
|||
|
|
@ -119,20 +119,18 @@ generations, generations within tasks, then tasks equally. Report primary/contro
|
|||
Answer input includes system/task, compressed history and exam. Standalone-method overhead includes one summary and,
|
||||
for N > 0, one whole Jev ranking, including recorded retries. Ranking cost is identical across N and both mechanisms;
|
||||
do not multiply by N or divide by sweep size. Evaluation repeats do not amortize overhead. Report input/output tokens
|
||||
by model. Total fees use [pricing.json](./pricing.json), checked 2026-10-16: Qwen `qwen3.8-max` China (Beijing)
|
||||
by model. Compaction fees use [pricing.json](./pricing.json), checked 2026-10-16: Qwen `qwen3.8-max` China (Beijing)
|
||||
input **$1.65/M**, output **$4.951/M** ([official rate](https://www.alibabacloud.com/help/en/model-studio/qwen3-8-max));
|
||||
Jev `jev-1.13.0` input **$0.042/M**, output free ([official rate](https://docs.typesafe.ai/models)).
|
||||
|
||||
`total_usd = ((summary_input + answer_input) * 1.65 + (summary_output + answer_output) * 4.951
|
||||
+ jev_input * 0.042) / 1e6`.
|
||||
At Top 0 charge summary generation plus one Qwen answer; Top 1–5 add one identical whole Jev ranking
|
||||
and charge the Qwen answer on the enlarged context. Mean usage is averaged across
|
||||
the same tasks/generations; fees are computed from unrounded usage. Recorded retries are included. The plotted amount
|
||||
includes one downstream answer and excludes collection/calibration. Full pays its actual mean answering fee and
|
||||
no compression preprocessing. Two scoring repeats estimate the cost of one answer; they do not amortize overhead.
|
||||
These are uncached list-price estimates: cache hits are deliberately charged at the regular input rate for comparison.
|
||||
No free quotas, promotions, taxes or account-specific adjustments are applied. Prices are a dated snapshot, not an invoice;
|
||||
no total monetary saving is claimed.
|
||||
`compaction_usd = (summary_input * 1.65 + summary_output * 4.951 + jev_input * 0.042) / 1e6`.
|
||||
At Top 0 charge only summary generation; Top 1–5 each add one identical complete Jev ranking. Mean usage is averaged
|
||||
across the same tasks/generations, and fees are computed from unrounded usage. Recorded summary/ranking retries are
|
||||
included. **Downstream answering, collection and calibration are excluded.** Full is excluded from panel C and has
|
||||
“—” in the cost table; it remains the quality/input reference in A/B. Scoring repeats do not amortize preprocessing.
|
||||
These are uncached list-price estimates: summary cache hits are charged at the regular input rate for comparison.
|
||||
No free quotas, promotions, taxes or account-specific adjustments are applied. Prices are a dated snapshot, not an
|
||||
invoice. This scope measures summary + Jev compaction overhead, not total execution cost or monetary savings.
|
||||
|
||||
## Reproduction levels and artifact availability
|
||||
|
||||
|
|
|
|||
|
|
@ -111,10 +111,10 @@ The extension keeps the existing per-task ceilings. Strict shrinkage versus Full
|
|||
filtering or removing conditions: Top 3–5 each shorten 9/12 primary contexts in both mechanisms. The H fusion arms
|
||||
shorten 172/210 contexts (51/60 primary, 121/150 controls). Summary-only H still shortens all 42/42.
|
||||
|
||||
For costs, each independent method includes one summary generation when applicable, one complete Jev ranking when
|
||||
N > 0, and one downstream answer. Recorded retry usage is included. One ranking is shared across the Top-N sweep and
|
||||
For compaction costs, each independent method includes one summary generation and one complete Jev ranking when
|
||||
N > 0. Downstream answering is excluded. Recorded retry usage is included. One ranking is shared across the Top-N sweep and
|
||||
mechanisms in the actual experiment; its standalone-method cost is neither multiplied by N nor divided by sweep size.
|
||||
The two answer repeats do not amortize compression overhead. Report provider input/output tokens separately.
|
||||
The current chart estimates summary + Jev + one downstream answer fees from the dated public USD rates in [pricing.json](./pricing.json),
|
||||
using uncached input pricing and excluding trajectory collection. [Settings](./SETTINGS.md#scoring-and-costs) define
|
||||
Panel C estimates summary + Jev compaction fees from the dated public USD rates in [pricing.json](./pricing.json),
|
||||
using uncached input pricing and excluding downstream answering and trajectory collection. Full appears in A/B only. [Settings](./SETTINGS.md#scoring-and-costs) define
|
||||
the formula and exclusions; this is not an account invoice or a claim of total pipeline savings.
|
||||
|
|
|
|||
|
|
@ -13,6 +13,6 @@
|
|||
"output": 0.0,
|
||||
"source": "https://docs.typesafe.ai/models"
|
||||
},
|
||||
"scope": "One summary generation plus one complete Jev ranking when N > 0, plus one downstream Qwen answer; recorded summary/ranking retries included; trajectory collection excluded",
|
||||
"scope": "Compaction only: one summary generation plus one complete Jev ranking when N > 0; recorded retries included; downstream answering and trajectory collection excluded; Full omitted from the cost comparison",
|
||||
"billing_basis": "Public list-price estimate; all input charged at uncached rate; no credits, promotions, taxes, exchange conversion or invoice reconciliation"
|
||||
}
|
||||
|
|
|
|||
|
|
@ -124,7 +124,7 @@ latency and total cost alongside token reduction. ReMe does not automatically su
|
|||
Summaries shorten history but can omit exact identifiers, configuration values or log details needed for a later answer.
|
||||
This experiment asks: **can a few Jev-selected original evidence blocks recover information missing from a fixed summary,
|
||||
and does that benefit occur with both a generic summary and a Hermes summary?** Answer input and total fees show the
|
||||
tradeoff between retained information, context length and cost.
|
||||
tradeoff between retained information, context length and compaction cost.
|
||||
|
||||
### Experimental setup
|
||||
|
||||
|
|
@ -143,7 +143,7 @@ This is a gold-answer **information-retention evaluation**, without resuming Her
|
|||
|
||||
### Reading the figure and conclusions
|
||||
|
||||
|
||||
|
||||
|
||||
- **A: selected originals help both summary mechanisms on this panel.** Full scores 100%; Top 3 improves S from
|
||||
**82.0% to 99.5%**, and H from **79.4% to 97.9%**. This supports supplementing these summaries with original evidence;
|
||||
|
|
@ -151,10 +151,12 @@ This is a gold-answer **information-retention evaluation**, without resuming Her
|
|||
- **B: higher retention consumes more context than summary alone.** Top 3 uses **3,241 / 3,193** mean answer-input tokens
|
||||
for S/H, versus Full's **4,014**, reductions of **19.3% / 20.4%**. Both exceed their summary-only input. Top 4–5 do not
|
||||
improve the scores: more original text does not guarantee better answers.
|
||||
- **C: there is no total-cost saving over a single post-compression answer here.** Fees include **summary generation +
|
||||
one Jev ranking + one Qwen answer, input and output**. At Top 3, S/H cost about **$0.015738 / $0.011697**, versus Full's
|
||||
**$0.006992**. Ranking fees are identical at Top 1–5; reading additional evidence increases Qwen's fee. These are
|
||||
public USD list-price estimates dated 2026-10-16, excluding cache discounts, free quotas and account offers, not invoices.
|
||||
- **C: compare compaction fees only.** Top 0 pays for Qwen summary generation: **$0.009864 / $0.005902** for S/H.
|
||||
Top 1–5 each pay for summary generation plus one complete Jev ranking: **$0.010039 / $0.006077**.
|
||||
Jev adds **$0.000175**, about **1.8% / 3.0%** of S/H summary fees. The curve plateaus because Jev scores all evidence
|
||||
once before selecting Top N. **C excludes downstream answering and omits Full; Full remains the reference in A/B.**
|
||||
Fees use public USD list prices dated 2026-10-16, excluding cache discounts, free quotas and account offers.
|
||||
This is neither an invoice nor evidence of end-to-end savings.
|
||||
|
||||
**Scope:** the primary result covers four synthetic task templates; ten controls are separate. All 42 H-only contexts
|
||||
shorten Full, but Top 3–5 shorten only **9/12 primary contexts per method**, with every case still scored. Strict field scoring includes format compliance; semantically equivalent wording can still lose credit.
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
<rdf:RDF xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://creativecommons.org/ns#" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
|
||||
<cc:Work>
|
||||
<dc:type rdf:resource="http://purl.org/dc/dcmitype/StillImage"/>
|
||||
<dc:date>2026-10-16T17:47:05.316892</dc:date>
|
||||
<dc:date>2026-10-16T18:18:39.704996</dc:date>
|
||||
<dc:format>image/svg+xml</dc:format>
|
||||
<dc:creator>
|
||||
<cc:Agent>
|
||||
|
|
@ -40,7 +40,7 @@ z
|
|||
<g id="line2d_1">
|
||||
<path d="M 76.032 180.72
|
||||
L 420.832463 180.72
|
||||
" clip-path="url(#p766555bb3d)" style="fill: none; stroke-dasharray: 7.5,6; stroke-dashoffset: 0; stroke: #7b8798; stroke-width: 1.5"/>
|
||||
" clip-path="url(#peabac2b509)" style="fill: none; stroke-dasharray: 7.5,6; stroke-dashoffset: 0; stroke: #7b8798; stroke-width: 1.5"/>
|
||||
</g>
|
||||
<g id="matplotlib.axis_1">
|
||||
<g id="xtick_1">
|
||||
|
|
@ -88,7 +88,7 @@ L 420.832463 180.72
|
|||
<g id="line2d_8">
|
||||
<path d="M 76.032 434.52
|
||||
L 420.832463 434.52
|
||||
" clip-path="url(#p766555bb3d)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
" clip-path="url(#peabac2b509)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
</g>
|
||||
<g id="line2d_9"/>
|
||||
<g id="text_8">
|
||||
|
|
@ -99,7 +99,7 @@ L 420.832463 434.52
|
|||
<g id="line2d_10">
|
||||
<path d="M 76.032 392.22
|
||||
L 420.832463 392.22
|
||||
" clip-path="url(#p766555bb3d)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
" clip-path="url(#peabac2b509)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
</g>
|
||||
<g id="line2d_11"/>
|
||||
<g id="text_9">
|
||||
|
|
@ -110,7 +110,7 @@ L 420.832463 392.22
|
|||
<g id="line2d_12">
|
||||
<path d="M 76.032 349.92
|
||||
L 420.832463 349.92
|
||||
" clip-path="url(#p766555bb3d)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
" clip-path="url(#peabac2b509)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
</g>
|
||||
<g id="line2d_13"/>
|
||||
<g id="text_10">
|
||||
|
|
@ -121,7 +121,7 @@ L 420.832463 349.92
|
|||
<g id="line2d_14">
|
||||
<path d="M 76.032 307.62
|
||||
L 420.832463 307.62
|
||||
" clip-path="url(#p766555bb3d)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
" clip-path="url(#peabac2b509)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
</g>
|
||||
<g id="line2d_15"/>
|
||||
<g id="text_11">
|
||||
|
|
@ -132,7 +132,7 @@ L 420.832463 307.62
|
|||
<g id="line2d_16">
|
||||
<path d="M 76.032 265.32
|
||||
L 420.832463 265.32
|
||||
" clip-path="url(#p766555bb3d)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
" clip-path="url(#peabac2b509)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
</g>
|
||||
<g id="line2d_17"/>
|
||||
<g id="text_12">
|
||||
|
|
@ -143,7 +143,7 @@ L 420.832463 265.32
|
|||
<g id="line2d_18">
|
||||
<path d="M 76.032 223.02
|
||||
L 420.832463 223.02
|
||||
" clip-path="url(#p766555bb3d)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
" clip-path="url(#peabac2b509)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
</g>
|
||||
<g id="line2d_19"/>
|
||||
<g id="text_13">
|
||||
|
|
@ -154,7 +154,7 @@ L 420.832463 223.02
|
|||
<g id="line2d_20">
|
||||
<path d="M 76.032 180.72
|
||||
L 420.832463 180.72
|
||||
" clip-path="url(#p766555bb3d)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
" clip-path="url(#peabac2b509)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
</g>
|
||||
<g id="line2d_21"/>
|
||||
<g id="text_14">
|
||||
|
|
@ -177,9 +177,9 @@ L 217.646476 227.42625
|
|||
L 279.217987 185.12625
|
||||
L 340.789498 196.87625
|
||||
L 402.361009 202.75125
|
||||
" clip-path="url(#p766555bb3d)" style="fill: none; stroke: #dc8f20; stroke-width: 2.6; stroke-linecap: square"/>
|
||||
" clip-path="url(#peabac2b509)" style="fill: none; stroke: #dc8f20; stroke-width: 2.6; stroke-linecap: square"/>
|
||||
<defs>
|
||||
<path id="m4bfcf8ab74" d="M 0 3
|
||||
<path id="m07951b0c58" d="M 0 3
|
||||
C 0.795609 3 1.55874 2.683901 2.12132 2.12132
|
||||
C 2.683901 1.55874 3 0.795609 3 0
|
||||
C 3 -0.795609 2.683901 -1.55874 2.12132 -2.12132
|
||||
|
|
@ -191,13 +191,13 @@ C -1.55874 2.683901 -0.795609 3 0 3
|
|||
z
|
||||
" style="stroke: #dc8f20"/>
|
||||
</defs>
|
||||
<g clip-path="url(#p766555bb3d)">
|
||||
<use xlink:href="#m4bfcf8ab74" x="94.503453" y="332.8825" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m4bfcf8ab74" x="156.074965" y="324.95125" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m4bfcf8ab74" x="217.646476" y="227.42625" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m4bfcf8ab74" x="279.217987" y="185.12625" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m4bfcf8ab74" x="340.789498" y="196.87625" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m4bfcf8ab74" x="402.361009" y="202.75125" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<g clip-path="url(#peabac2b509)">
|
||||
<use xlink:href="#m07951b0c58" x="94.503453" y="332.8825" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m07951b0c58" x="156.074965" y="324.95125" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m07951b0c58" x="217.646476" y="227.42625" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m07951b0c58" x="279.217987" y="185.12625" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m07951b0c58" x="340.789498" y="196.87625" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m07951b0c58" x="402.361009" y="202.75125" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
</g>
|
||||
</g>
|
||||
<g id="text_16">
|
||||
|
|
@ -216,9 +216,9 @@ L 217.646476 240.645
|
|||
L 279.217987 198.345
|
||||
L 340.789498 207.1575
|
||||
L 402.361009 207.1575
|
||||
" clip-path="url(#p766555bb3d)" style="fill: none; stroke: #596fc4; stroke-width: 2.6; stroke-linecap: square"/>
|
||||
" clip-path="url(#peabac2b509)" style="fill: none; stroke: #596fc4; stroke-width: 2.6; stroke-linecap: square"/>
|
||||
<defs>
|
||||
<path id="m59085ef62d" d="M 0 3
|
||||
<path id="maab8e31a6c" d="M 0 3
|
||||
C 0.795609 3 1.55874 2.683901 2.12132 2.12132
|
||||
C 2.683901 1.55874 3 0.795609 3 0
|
||||
C 3 -0.795609 2.683901 -1.55874 2.12132 -2.12132
|
||||
|
|
@ -230,13 +230,13 @@ C -1.55874 2.683901 -0.795609 3 0 3
|
|||
z
|
||||
" style="stroke: #596fc4"/>
|
||||
</defs>
|
||||
<g clip-path="url(#p766555bb3d)">
|
||||
<use xlink:href="#m59085ef62d" x="94.503453" y="355.2075" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#m59085ef62d" x="156.074965" y="304.97625" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#m59085ef62d" x="217.646476" y="240.645" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#m59085ef62d" x="279.217987" y="198.345" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#m59085ef62d" x="340.789498" y="207.1575" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#m59085ef62d" x="402.361009" y="207.1575" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<g clip-path="url(#peabac2b509)">
|
||||
<use xlink:href="#maab8e31a6c" x="94.503453" y="355.2075" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#maab8e31a6c" x="156.074965" y="304.97625" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#maab8e31a6c" x="217.646476" y="240.645" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#maab8e31a6c" x="279.217987" y="198.345" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#maab8e31a6c" x="340.789498" y="207.1575" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#maab8e31a6c" x="402.361009" y="207.1575" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
</g>
|
||||
</g>
|
||||
<g id="text_19">
|
||||
|
|
@ -267,7 +267,7 @@ z
|
|||
<g id="line2d_24">
|
||||
<path d="M 532.639759 195.184761
|
||||
L 877.440222 195.184761
|
||||
" clip-path="url(#pbc4e44716b)" style="fill: none; stroke-dasharray: 7.5,6; stroke-dashoffset: 0; stroke: #7b8798; stroke-width: 1.5"/>
|
||||
" clip-path="url(#p5ed38ffaf2)" style="fill: none; stroke-dasharray: 7.5,6; stroke-dashoffset: 0; stroke: #7b8798; stroke-width: 1.5"/>
|
||||
</g>
|
||||
<g id="matplotlib.axis_3">
|
||||
<g id="xtick_7">
|
||||
|
|
@ -315,7 +315,7 @@ L 877.440222 195.184761
|
|||
<g id="line2d_31">
|
||||
<path d="M 532.639759 384.495652
|
||||
L 877.440222 384.495652
|
||||
" clip-path="url(#pbc4e44716b)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
" clip-path="url(#p5ed38ffaf2)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
</g>
|
||||
<g id="line2d_32"/>
|
||||
<g id="text_31">
|
||||
|
|
@ -326,7 +326,7 @@ L 877.440222 384.495652
|
|||
<g id="line2d_33">
|
||||
<path d="M 532.639759 321.965217
|
||||
L 877.440222 321.965217
|
||||
" clip-path="url(#pbc4e44716b)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
" clip-path="url(#p5ed38ffaf2)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
</g>
|
||||
<g id="line2d_34"/>
|
||||
<g id="text_32">
|
||||
|
|
@ -337,7 +337,7 @@ L 877.440222 321.965217
|
|||
<g id="line2d_35">
|
||||
<path d="M 532.639759 259.434783
|
||||
L 877.440222 259.434783
|
||||
" clip-path="url(#pbc4e44716b)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
" clip-path="url(#p5ed38ffaf2)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
</g>
|
||||
<g id="line2d_36"/>
|
||||
<g id="text_33">
|
||||
|
|
@ -348,7 +348,7 @@ L 877.440222 259.434783
|
|||
<g id="line2d_37">
|
||||
<path d="M 532.639759 196.904348
|
||||
L 877.440222 196.904348
|
||||
" clip-path="url(#pbc4e44716b)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
" clip-path="url(#p5ed38ffaf2)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
</g>
|
||||
<g id="line2d_38"/>
|
||||
<g id="text_34">
|
||||
|
|
@ -371,14 +371,14 @@ L 674.254235 325.195957
|
|||
L 735.825746 291.856813
|
||||
L 797.397258 259.935026
|
||||
L 858.968769 239.393778
|
||||
" clip-path="url(#pbc4e44716b)" style="fill: none; stroke: #dc8f20; stroke-width: 2.6; stroke-linecap: square"/>
|
||||
<g clip-path="url(#pbc4e44716b)">
|
||||
<use xlink:href="#m4bfcf8ab74" x="551.111213" y="387.007291" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m4bfcf8ab74" x="612.682724" y="352.896939" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m4bfcf8ab74" x="674.254235" y="325.195957" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m4bfcf8ab74" x="735.825746" y="291.856813" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m4bfcf8ab74" x="797.397258" y="259.935026" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m4bfcf8ab74" x="858.968769" y="239.393778" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
" clip-path="url(#p5ed38ffaf2)" style="fill: none; stroke: #dc8f20; stroke-width: 2.6; stroke-linecap: square"/>
|
||||
<g clip-path="url(#p5ed38ffaf2)">
|
||||
<use xlink:href="#m07951b0c58" x="551.111213" y="387.007291" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m07951b0c58" x="612.682724" y="352.896939" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m07951b0c58" x="674.254235" y="325.195957" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m07951b0c58" x="735.825746" y="291.856813" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m07951b0c58" x="797.397258" y="259.935026" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m07951b0c58" x="858.968769" y="239.393778" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
</g>
|
||||
</g>
|
||||
<g id="text_36">
|
||||
|
|
@ -397,14 +397,14 @@ L 674.254235 331.136348
|
|||
L 735.825746 297.797204
|
||||
L 797.397258 265.875417
|
||||
L 858.968769 245.33417
|
||||
" clip-path="url(#pbc4e44716b)" style="fill: none; stroke: #596fc4; stroke-width: 2.6; stroke-linecap: square"/>
|
||||
<g clip-path="url(#pbc4e44716b)">
|
||||
<use xlink:href="#m59085ef62d" x="551.111213" y="392.947683" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#m59085ef62d" x="612.682724" y="358.83733" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#m59085ef62d" x="674.254235" y="331.136348" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#m59085ef62d" x="735.825746" y="297.797204" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#m59085ef62d" x="797.397258" y="265.875417" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#m59085ef62d" x="858.968769" y="245.33417" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
" clip-path="url(#p5ed38ffaf2)" style="fill: none; stroke: #596fc4; stroke-width: 2.6; stroke-linecap: square"/>
|
||||
<g clip-path="url(#p5ed38ffaf2)">
|
||||
<use xlink:href="#maab8e31a6c" x="551.111213" y="392.947683" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#maab8e31a6c" x="612.682724" y="358.83733" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#maab8e31a6c" x="674.254235" y="331.136348" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#maab8e31a6c" x="735.825746" y="297.797204" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#maab8e31a6c" x="797.397258" y="265.875417" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#maab8e31a6c" x="858.968769" y="245.33417" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
</g>
|
||||
</g>
|
||||
<g id="text_39">
|
||||
|
|
@ -478,7 +478,7 @@ z
|
|||
<g id="line2d_47">
|
||||
<path d="M 989.247519 434.52
|
||||
L 1347.84 434.52
|
||||
" clip-path="url(#pc18ffa5c03)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
" clip-path="url(#p76a1f9e546)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
</g>
|
||||
<g id="line2d_48"/>
|
||||
<g id="text_51">
|
||||
|
|
@ -489,114 +489,109 @@ L 1347.84 434.52
|
|||
<g id="line2d_49">
|
||||
<path d="M 989.247519 362.61
|
||||
L 1347.84 362.61
|
||||
" clip-path="url(#pc18ffa5c03)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
" clip-path="url(#p76a1f9e546)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
</g>
|
||||
<g id="line2d_50"/>
|
||||
<g id="text_52">
|
||||
<text style="font-size: 12px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: end; fill: #58677b" x="982.247519" y="367.169062" transform="rotate(-0 982.247519 367.169062)">$0.005</text>
|
||||
<text style="font-size: 12px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: end; fill: #58677b" x="982.247519" y="367.169062" transform="rotate(-0 982.247519 367.169062)">$0.003</text>
|
||||
</g>
|
||||
</g>
|
||||
<g id="ytick_14">
|
||||
<g id="line2d_51">
|
||||
<path d="M 989.247519 290.7
|
||||
L 1347.84 290.7
|
||||
" clip-path="url(#pc18ffa5c03)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
" clip-path="url(#p76a1f9e546)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
</g>
|
||||
<g id="line2d_52"/>
|
||||
<g id="text_53">
|
||||
<text style="font-size: 12px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: end; fill: #58677b" x="982.247519" y="295.259063" transform="rotate(-0 982.247519 295.259063)">$0.010</text>
|
||||
<text style="font-size: 12px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: end; fill: #58677b" x="982.247519" y="295.259063" transform="rotate(-0 982.247519 295.259063)">$0.006</text>
|
||||
</g>
|
||||
</g>
|
||||
<g id="ytick_15">
|
||||
<g id="line2d_53">
|
||||
<path d="M 989.247519 218.79
|
||||
L 1347.84 218.79
|
||||
" clip-path="url(#pc18ffa5c03)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
" clip-path="url(#p76a1f9e546)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
</g>
|
||||
<g id="line2d_54"/>
|
||||
<g id="text_54">
|
||||
<text style="font-size: 12px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: end; fill: #58677b" x="982.247519" y="223.349063" transform="rotate(-0 982.247519 223.349063)">$0.015</text>
|
||||
<text style="font-size: 12px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: end; fill: #58677b" x="982.247519" y="223.349063" transform="rotate(-0 982.247519 223.349063)">$0.009</text>
|
||||
</g>
|
||||
</g>
|
||||
<g id="ytick_16">
|
||||
<g id="line2d_55">
|
||||
<path d="M 989.247519 146.88
|
||||
L 1347.84 146.88
|
||||
" clip-path="url(#pc18ffa5c03)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
" clip-path="url(#p76a1f9e546)" style="fill: none; stroke: #e8edf3; stroke-width: 0.9; stroke-linecap: square"/>
|
||||
</g>
|
||||
<g id="line2d_56"/>
|
||||
<g id="text_55">
|
||||
<text style="font-size: 12px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: end; fill: #58677b" x="982.247519" y="151.439062" transform="rotate(-0 982.247519 151.439062)">$0.020</text>
|
||||
<text style="font-size: 12px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: end; fill: #58677b" x="982.247519" y="151.439062" transform="rotate(-0 982.247519 151.439062)">$0.012</text>
|
||||
</g>
|
||||
</g>
|
||||
<g id="text_56">
|
||||
<text style="font-size: 12px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: middle; fill: #43536b" x="927.375956" y="290.7" transform="rotate(-90 927.375956 290.7)">Estimated USD: compress + answer</text>
|
||||
<text style="font-size: 12px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: middle; fill: #43536b" x="927.375956" y="290.7" transform="rotate(-90 927.375956 290.7)">Estimated USD per compaction</text>
|
||||
</g>
|
||||
</g>
|
||||
<g id="line2d_57">
|
||||
<path d="M 989.247519 333.961781
|
||||
L 1347.84 333.961781
|
||||
" clip-path="url(#pc18ffa5c03)" style="fill: none; stroke-dasharray: 7.5,6; stroke-dashoffset: 0; stroke: #7b8798; stroke-width: 1.5"/>
|
||||
</g>
|
||||
<g id="patch_7">
|
||||
<path d="M 989.247519 434.52
|
||||
L 1347.84 434.52
|
||||
" style="fill: none; stroke: #dbe2ea; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square"/>
|
||||
</g>
|
||||
<g id="line2d_58">
|
||||
<path d="M 1016.597793 228.957369
|
||||
L 1077.376179 219.944347
|
||||
L 1138.154566 214.634682
|
||||
L 1198.932953 208.178036
|
||||
L 1259.711339 202.02297
|
||||
L 1320.489726 198.23801
|
||||
" clip-path="url(#pc18ffa5c03)" style="fill: none; stroke: #dc8f20; stroke-width: 2.6; stroke-linecap: square"/>
|
||||
<g clip-path="url(#pc18ffa5c03)">
|
||||
<use xlink:href="#m4bfcf8ab74" x="1016.597793" y="228.957369" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m4bfcf8ab74" x="1077.376179" y="219.944347" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m4bfcf8ab74" x="1138.154566" y="214.634682" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m4bfcf8ab74" x="1198.932953" y="208.178036" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m4bfcf8ab74" x="1259.711339" y="202.02297" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m4bfcf8ab74" x="1320.489726" y="198.23801" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<g id="line2d_57">
|
||||
<path d="M 1016.597793 198.082325
|
||||
L 1077.376179 193.892525
|
||||
L 1138.154566 193.892525
|
||||
L 1198.932953 193.892525
|
||||
L 1259.711339 193.892525
|
||||
L 1320.489726 193.892525
|
||||
" clip-path="url(#p76a1f9e546)" style="fill: none; stroke: #dc8f20; stroke-width: 2.6; stroke-linecap: square"/>
|
||||
<g clip-path="url(#p76a1f9e546)">
|
||||
<use xlink:href="#m07951b0c58" x="1016.597793" y="198.082325" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m07951b0c58" x="1077.376179" y="193.892525" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m07951b0c58" x="1138.154566" y="193.892525" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m07951b0c58" x="1198.932953" y="193.892525" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m07951b0c58" x="1259.711339" y="193.892525" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m07951b0c58" x="1320.489726" y="193.892525" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
</g>
|
||||
</g>
|
||||
<g id="text_57">
|
||||
<text style="font-weight: 700; font-size: 10.5px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: middle; fill: #dc8f20" x="1019.597793" y="216.957369" transform="rotate(-0 1019.597793 216.957369)">$0.01429</text>
|
||||
<text style="font-weight: 700; font-size: 10.5px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: middle; fill: #dc8f20" x="1024.597793" y="186.082325" transform="rotate(-0 1024.597793 186.082325)">$0.009864</text>
|
||||
</g>
|
||||
<g id="text_58">
|
||||
<text style="font-weight: 700; font-size: 10.5px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: middle; fill: #dc8f20" x="1323.489726" y="186.23801" transform="rotate(-0 1323.489726 186.23801)">$0.01643</text>
|
||||
<text style="font-weight: 700; font-size: 10.5px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: middle; fill: #dc8f20" x="1312.489726" y="181.892525" transform="rotate(-0 1312.489726 181.892525)">$0.010039</text>
|
||||
</g>
|
||||
<g id="line2d_59">
|
||||
<path d="M 1016.597793 287.171465
|
||||
L 1077.376179 278.087238
|
||||
L 1138.154566 272.804275
|
||||
L 1198.932953 266.300159
|
||||
L 1259.711339 260.29047
|
||||
L 1320.489726 256.357166
|
||||
" clip-path="url(#pc18ffa5c03)" style="fill: none; stroke: #596fc4; stroke-width: 2.6; stroke-linecap: square"/>
|
||||
<g clip-path="url(#pc18ffa5c03)">
|
||||
<use xlink:href="#m59085ef62d" x="1016.597793" y="287.171465" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#m59085ef62d" x="1077.376179" y="278.087238" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#m59085ef62d" x="1138.154566" y="272.804275" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#m59085ef62d" x="1198.932953" y="266.300159" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#m59085ef62d" x="1259.711339" y="260.29047" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#m59085ef62d" x="1320.489726" y="256.357166" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<g id="line2d_58">
|
||||
<path d="M 1016.597793 293.054102
|
||||
L 1077.376179 288.864301
|
||||
L 1138.154566 288.864301
|
||||
L 1198.932953 288.864301
|
||||
L 1259.711339 288.864301
|
||||
L 1320.489726 288.864301
|
||||
" clip-path="url(#p76a1f9e546)" style="fill: none; stroke: #596fc4; stroke-width: 2.6; stroke-linecap: square"/>
|
||||
<g clip-path="url(#p76a1f9e546)">
|
||||
<use xlink:href="#maab8e31a6c" x="1016.597793" y="293.054102" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#maab8e31a6c" x="1077.376179" y="288.864301" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#maab8e31a6c" x="1138.154566" y="288.864301" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#maab8e31a6c" x="1198.932953" y="288.864301" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#maab8e31a6c" x="1259.711339" y="288.864301" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#maab8e31a6c" x="1320.489726" y="288.864301" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
</g>
|
||||
</g>
|
||||
<g id="text_59">
|
||||
<text style="font-weight: 700; font-size: 10.5px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: middle; fill: #596fc4" x="1019.597793" y="308.171465" transform="rotate(-0 1019.597793 308.171465)">$0.01025</text>
|
||||
<text style="font-weight: 700; font-size: 10.5px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: middle; fill: #596fc4" x="1024.597793" y="314.054102" transform="rotate(-0 1024.597793 314.054102)">$0.005902</text>
|
||||
</g>
|
||||
<g id="text_60">
|
||||
<text style="font-weight: 700; font-size: 10.5px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: middle; fill: #596fc4" x="1323.489726" y="277.357166" transform="rotate(-0 1323.489726 277.357166)">$0.01239</text>
|
||||
<text style="font-weight: 700; font-size: 10.5px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: middle; fill: #596fc4" x="1312.489726" y="309.864301" transform="rotate(-0 1312.489726 309.864301)">$0.006077</text>
|
||||
</g>
|
||||
<g id="text_61">
|
||||
<text style="font-size: 10.8px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: start; fill: #58677b" x="996.419368" y="163.714669" transform="rotate(-0 996.419368 163.714669)">Summary + Jev + one Qwen answer</text>
|
||||
<text style="font-size: 10.8px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: start; fill: #58677b" x="996.419368" y="163.715513" transform="rotate(-0 996.419368 163.715513)">Summary generation + Jev ranking</text>
|
||||
</g>
|
||||
<g id="text_62">
|
||||
<text style="font-size: 11px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: end; fill: #7b8798" x="1340.66815" y="326.770781" transform="rotate(-0 1340.66815 326.770781)">Full: $0.00699</text>
|
||||
<text style="font-size: 10.5px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: middle; fill: #43536b" x="1168.543759" y="250.4304" transform="rotate(-0 1168.543759 250.4304)">Jev adds $0.000175 once at N > 0</text>
|
||||
</g>
|
||||
<g id="text_63">
|
||||
<text style="font-weight: 700; font-size: 15px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: start; fill: #172d45" x="989.247519" y="123.88" transform="rotate(-0 989.247519 123.88)">C Total cost: one answer</text>
|
||||
<text style="font-weight: 700; font-size: 15px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: start; fill: #172d45" x="989.247519" y="123.88" transform="rotate(-0 989.247519 123.88)">C Compaction cost</text>
|
||||
</g>
|
||||
</g>
|
||||
<g id="text_64">
|
||||
|
|
@ -615,37 +610,37 @@ L 1320.489726 256.357166
|
|||
<text style="font-size: 11px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: start; fill: #58677b" x="76.032" y="547.74" transform="rotate(-0 76.032 547.74)">Primary cohort: 4 task templates, 24 answers per method; 10 separate controls. Top 3–5 shorten 9/12 primary contexts per method.</text>
|
||||
</g>
|
||||
<g id="text_69">
|
||||
<text style="font-size: 11px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: start; fill: #58677b" x="76.032" y="568.548" transform="rotate(-0 76.032 568.548)">C includes one summary, one Jev ranking at N > 0, and one Qwen answer (input + output). Full includes its Qwen answer fee.</text>
|
||||
<text style="font-size: 11px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: start; fill: #58677b" x="76.032" y="568.548" transform="rotate(-0 76.032 568.548)">C: Top 0 pays for summary generation; Top 1–5 add one complete Jev ranking. Answering is excluded. Full is shown in A/B only.</text>
|
||||
</g>
|
||||
<g id="text_70">
|
||||
<text style="font-size: 11px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: start; fill: #58677b" x="76.032" y="589.356" transform="rotate(-0 76.032 589.356)">Uncached list-price estimate (2026-10-16): Qwen $1.65 input / $4.951 output per M tokens; Jev $0.042 input / $0 output. Not an invoice.</text>
|
||||
</g>
|
||||
<g id="legend_1">
|
||||
<g id="line2d_60">
|
||||
<g id="line2d_59">
|
||||
<path d="M 78.5376 97.114125
|
||||
L 90.5376 97.114125
|
||||
L 102.5376 97.114125
|
||||
" style="fill: none; stroke: #dc8f20; stroke-width: 2.5; stroke-linecap: square"/>
|
||||
<g>
|
||||
<use xlink:href="#m4bfcf8ab74" x="90.5376" y="97.114125" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
<use xlink:href="#m07951b0c58" x="90.5376" y="97.114125" style="fill: #dc8f20; stroke: #dc8f20"/>
|
||||
</g>
|
||||
</g>
|
||||
<g id="text_71">
|
||||
<text style="font-size: 12px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: start; fill: #172d45" x="112.1376" y="101.314125" transform="rotate(-0 112.1376 101.314125)">Generic summary S</text>
|
||||
</g>
|
||||
<g id="line2d_61">
|
||||
<g id="line2d_60">
|
||||
<path d="M 254.541975 97.114125
|
||||
L 266.541975 97.114125
|
||||
L 278.541975 97.114125
|
||||
" style="fill: none; stroke: #596fc4; stroke-width: 2.5; stroke-linecap: square"/>
|
||||
<g>
|
||||
<use xlink:href="#m59085ef62d" x="266.541975" y="97.114125" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
<use xlink:href="#maab8e31a6c" x="266.541975" y="97.114125" style="fill: #596fc4; stroke: #596fc4"/>
|
||||
</g>
|
||||
</g>
|
||||
<g id="text_72">
|
||||
<text style="font-size: 12px; font-family: 'DejaVu Sans', Arial, sans-serif; text-anchor: start; fill: #172d45" x="288.141975" y="101.314125" transform="rotate(-0 288.141975 101.314125)">Hermes small-budget H</text>
|
||||
</g>
|
||||
<g id="line2d_62">
|
||||
<g id="line2d_61">
|
||||
<path d="M 454.086975 97.114125
|
||||
L 466.086975 97.114125
|
||||
L 478.086975 97.114125
|
||||
|
|
@ -657,13 +652,13 @@ L 478.086975 97.114125
|
|||
</g>
|
||||
</g>
|
||||
<defs>
|
||||
<clipPath id="p766555bb3d">
|
||||
<clipPath id="peabac2b509">
|
||||
<rect x="76.032" y="146.88" width="344.800463" height="287.64"/>
|
||||
</clipPath>
|
||||
<clipPath id="pbc4e44716b">
|
||||
<clipPath id="p5ed38ffaf2">
|
||||
<rect x="532.639759" y="146.88" width="344.800463" height="287.64"/>
|
||||
</clipPath>
|
||||
<clipPath id="pc18ffa5c03">
|
||||
<clipPath id="p76a1f9e546">
|
||||
<rect x="989.247519" y="146.88" width="358.592481" height="287.64"/>
|
||||
</clipPath>
|
||||
</defs>
|
||||
|
|
|
|||
|
Before Width: | Height: | Size: 33 KiB After Width: | Height: | Size: 33 KiB |
|
|
@ -114,7 +114,7 @@ ReMe 不会自动生成摘要或写入长期记忆。
|
|||
|
||||
摘要可以缩短历史，但可能丢失后续回答需要的精确标识符、配置值或日志细节。本实验考察：**在摘要保持不变的基础上，
|
||||
追加 Jev 选出的少量原文，能否补回这些信息？这一增益能否同时出现在普通摘要和 Hermes 摘要中？**
|
||||
同时报告回答输入量和总费用，观察信息保留、上下文长度与开销之间的取舍。
|
||||
同时报告回答输入量和压缩费用，观察信息保留、上下文长度与开销之间的取舍。
|
||||
|
||||
### 实验设置
|
||||
|
||||
|
|
@ -133,15 +133,17 @@ Jev 先依据原任务给全部证据块打分，再选择 Top N；N 只影响
|
|||
|
||||
### 读图与结论
|
||||
|
||||
|
||||
|
||||
|
||||
- **A：两种摘要都能从追加原文中获益。** Full 的字段正确率为 100%；Top 3 将 S 从 **82.0% 提升至 99.5%**，
|
||||
将 H 从 **79.4% 提升至 97.9%**。这支持“摘要 + 关键原文”在本组任务中补充摘要遗漏的信息，尚不能证明通用优势或与 Full 统计等价。
|
||||
- **B：以更多上下文换取更高的信息保留率。** Top 3 的平均回答输入为 S **3241**、H **3193 tokens**，
|
||||
相比 Full 的 **4014 tokens** 分别减少 **19.3%／20.4%**，但都高于各自纯摘要。Top 4～5 未继续提分，更多原文不保证效果更好。
|
||||
- **C：按一次压缩后回答计算，当前没有总费用节省。** 总费用包含**摘要生成 + 一次 Jev 排名 + 一次 Qwen 回答的输入／输出**。
|
||||
Top 3 的 S／H 费用约 **$0.015738／$0.011697**，Full 为 **$0.006992**。Jev 排名费在 Top 1～5 相同，
|
||||
曲线的增长来自 Qwen 读取更多原文。费用按 2026-10-16 的公开 USD 标价估算，未计缓存折扣、免费额度或账户优惠；不是实际账单。
|
||||
- **C：只比较压缩本身的费用。** Top 0 只计 Qwen 生成摘要的费用：S／H 约 **$0.009864／$0.005902**；
|
||||
Top 1～5 均为“摘要 + 一次完整 Jev 排名”，约 **$0.010039／$0.006077**。Jev 额外增加约 **$0.000175**，
|
||||
即摘要费的 **1.8%／3.0%**。Jev 先给全部证据打分，再取 Top N，因此 Top 1～5 的压缩费用相同，曲线呈平台。
|
||||
**C 不计压缩后的回答费用，也不展示 Full；Full 仅在 A/B 作为效果和输入量参考。**
|
||||
费用按 2026-10-16 的公开 USD 标价估算，未计缓存折扣、免费额度或账户优惠；不代表实际账单或端到端费用节省。
|
||||
|
||||
**结果边界：** 主结论来自 4 个合成任务模板；10 个短任务对照不混入主图。纯 H 的 42 个上下文均短于 Full，
|
||||
但 Top 3～5 每种方法仅有 **9/12 个主任务上下文**实际缩短，全部样例均保留评分。严格字段评分包含格式要求，语义相同但格式不同也可能失分。
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue