ATTORNEY REVIEW PACKET · CONTESTED-REASONING TASK

IPR2022-01531: SynAffix B.V. v. Hangzhou DAC Biotech

U.S. Patent 10,131,682 C1 · antibody-drug-conjugate linker chemistry (TC1600) · Final Written Decision Paper 58 (Aug. 26, 2025)

This packet contains everything needed to review one contested-reasoning evaluation task built from the above proceeding: the task the model is given, the record it may see, the answer key derived from the FWD, the 15 graded rubric propositions with their source excerpts, and one fully scored model run. The ask is in the box below.

What we would like you to confirm


1. The Board's actual holding (the answer key)

Derived from FWD Paper 58 (CONCLUSION, summary table, and ORDER). This is the ground truth the rubric and scoring are built against. Each cell is one challenged claim.

Claim constructions adopted

Five instituted grounds

G1 Morales-Sanfrutos as ev. by Straus · G2 Harris · G3 Singh in view of Harris · G4 Singh/Harris/Bhakta · G5 Singh/Harris/Snow


2. What the model is asked to do

The complete task instruction handed to the model. It is told to predict the Board's ground-by-ground resolution from the pre-decision record, and explicitly told not to assume either side wins and not to use external sources.

Show full task instruction

3. What the model can see (and what it cannot)

The model works only from the bundled local record below, reached through file/search tools and a PDF reader. The Final Written Decision (Paper 58) is withheld, so the model must reconstruct the holding, not read it. The Patent Owner's briefing and the asserted references are present, so the survivors are reconstructable from the record. Click any document to open it. Two cited references are copyrighted journal articles and are not redistributed here.


4. The 15 graded rubric propositions

This is the core review surface. Each proposition is graded for/against the model's answer. For each, the green excerpt is the supporting FWD text; the acceptance criterion is the grading rule. Polarity: positive = the Board affirmatively held it; not_shown = the Board found it not proven; role_limit = a scope/not-reached limit.


5. One scored model run (worked example)

A fresh run of GPT-5.5 (xhigh reasoning) on this task, graded by the authoritative rubric scorer. Reward = 0.70·coverage + 0.15·ground + 0.15·motivation − 0.15·(over-kill contradictions), floored at 0. This example is included so you can see the grader applied to a real answer and check whether each row's verdict is sound.

Where the model's verdicts differ from the Board

Per-proposition grading (with the grader's reasoning)

Verdict per rubric row, with the judge's justification. This is what produced the score above.

The model's full trajectory

The agent's actual run: every reasoning step, shell command, and PDF-tool call (tool outputs truncated).

Show full agent trajectory

6. The model's full answer

The complete structured output the model produced (download raw JSON): its overall outcome, claim constructions, the rationale to combine, the contested disputes as it resolved them, and its per-claim reasoning with the record quotes it cited. This is what the rubric scorer graded.