{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AQ7MR45H6YSUTT3267ZV5C3ACA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"49de67978e75b871b655dec57a990ebdd81871c1eb2e485b06b817117cf1a982","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-05-07T20:54:07Z","title_canon_sha256":"f36a4404567304f7b87958e007d415975a53882b21b6292b6d03704e5c4120b1"},"schema_version":"1.0","source":{"id":"2605.06936","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.06936","created_at":"2026-05-25T02:01:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.06936v2","created_at":"2026-05-25T02:01:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.06936","created_at":"2026-05-25T02:01:22Z"},{"alias_kind":"pith_short_12","alias_value":"AQ7MR45H6YSU","created_at":"2026-05-25T02:01:22Z"},{"alias_kind":"pith_short_16","alias_value":"AQ7MR45H6YSUTT32","created_at":"2026-05-25T02:01:22Z"},{"alias_kind":"pith_short_8","alias_value":"AQ7MR45H","created_at":"2026-05-25T02:01:22Z"}],"graph_snapshots":[{"event_id":"sha256:2eb074065f51d031e935c7a2c5206c66bdd6603b250f5531901429dac53b93e1","target":"graph","created_at":"2026-05-25T02:01:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Across eight commercial and open-source LLMs under multiple agent scaffolds, we find that agents handle synthetic DRC-Essential and single-objective PPA-Mono reasonably well but degrade sharply on the more practical DRC-Reasoning, where the best success rate is 36.66%, and PPA-Multi, where the best success rate is 20.00%; vision augmentation consistently enhances DRC-Bench; and trade-off reasoning, rather than knob knowledge, is the dominant PPA-Multi bottleneck."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The 145 tasks across the four categories in PostEDA-Bench, supported by EDA toolchains with machine-checkable evaluation, are representative of real-world post-EDA challenges and provide a fair test of agent capabilities."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PostEDA-Bench shows LLM agents succeed reasonably on basic DRC and single-objective PPA tasks but struggle on practical DRC reasoning (best 36.66% success) and multi-objective PPA (best 20% success)."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"LLM agents succeed on simple post-EDA tasks but reach only 37% and 20% success on practical DRC reasoning and multi-objective PPA."}],"snapshot_sha256":"031218625567234a91d6c30074af8ca56e7be852b08704fd8a9149115488ea10"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"eb2cd9baa6597817a8e41f2eba9af508e09d57c54ee63a6d494b35294db17a8b"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T11:42:03.512658Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T06:39:35.896396Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T17:31:19.310570Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T12:14:10.140053Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.06936/integrity.json","findings":[],"snapshot_sha256":"c804961ceb7f651adb76397e7b89962bff64e1ac7ab6880cc33bb4b4c1e87c46","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM-based agents are increasingly applied to the \"last mile\" of Electronic Design Automation (EDA): repairing residual sign-off Design Rule Check (DRC) violations and converging Power-Performance-Area (PPA) targets after tool runs. Existing EDA-LLM benchmarks, however, omit DRC fixing entirely and rely on flat hierarchies tied to a single toolchain. We introduce PostEDA-Bench, a hierarchical benchmark with 145 tasks across DRC-Essential, DRC-Reasoning, PPA-Mono, and PPA-Multi, supported by EDA toolchains with machine-checkable evaluation. Across eight commercial and open-source LLMs under mult","authors_text":"Caiwen Ding, Jinwei Tang, Nuo Xu, Pengju Liu, Yu Cao","cross_cats":["cs.AI","cs.MA"],"headline":"LLM agents succeed on simple post-EDA tasks but reach only 37% and 20% success on practical DRC reasoning and multi-objective PPA.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-05-07T20:54:07Z","title":"Bridging the Last Mile of Circuit Design: PostEDA-Bench, a Hierarchical Benchmark for PPA Convergence and DRC Fixing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.06936","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-11T00:57:42.284462Z","id":"d9a1ffce-a062-430b-9190-50a9ca2f92ea","model_set":{"reader":"grok-4.3"},"one_line_summary":"PostEDA-Bench shows LLM agents succeed reasonably on basic DRC and single-objective PPA tasks but struggle on practical DRC reasoning (best 36.66% success) and multi-objective PPA (best 20% success).","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"LLM agents succeed on simple post-EDA tasks but reach only 37% and 20% success on practical DRC reasoning and multi-objective PPA.","strongest_claim":"Across eight commercial and open-source LLMs under multiple agent scaffolds, we find that agents handle synthetic DRC-Essential and single-objective PPA-Mono reasonably well but degrade sharply on the more practical DRC-Reasoning, where the best success rate is 36.66%, and PPA-Multi, where the best success rate is 20.00%; vision augmentation consistently enhances DRC-Bench; and trade-off reasoning, rather than knob knowledge, is the dominant PPA-Multi bottleneck.","weakest_assumption":"The 145 tasks across the four categories in PostEDA-Bench, supported by EDA toolchains with machine-checkable evaluation, are representative of real-world post-EDA challenges and provide a fair test of agent capabilities."}},"verdict_id":"d9a1ffce-a062-430b-9190-50a9ca2f92ea"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e62d5bb7c3980e48551c2d4fb8def4f49fb8fff33e9813610a2eb997aac9e183","target":"record","created_at":"2026-05-25T02:01:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"49de67978e75b871b655dec57a990ebdd81871c1eb2e485b06b817117cf1a982","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-05-07T20:54:07Z","title_canon_sha256":"f36a4404567304f7b87958e007d415975a53882b21b6292b6d03704e5c4120b1"},"schema_version":"1.0","source":{"id":"2605.06936","kind":"arxiv","version":2}},"canonical_sha256":"043ec8f3a7f62549cf7af7f35e8b60101391fc1f421c02053f15bcc52945bbf1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"043ec8f3a7f62549cf7af7f35e8b60101391fc1f421c02053f15bcc52945bbf1","first_computed_at":"2026-05-25T02:01:22.384645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:22.384645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IFxjopcmtdJvCI90f5F6o2Hd66FyvW/NOlsWLc94/xxuqPCpO09ebPT46vuUmdbqPmP0ZgTf8n6Ht5SKHjlIAQ==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:22.385401Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.06936","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e62d5bb7c3980e48551c2d4fb8def4f49fb8fff33e9813610a2eb997aac9e183","sha256:2eb074065f51d031e935c7a2c5206c66bdd6603b250f5531901429dac53b93e1"],"state_sha256":"74f749877426010724f9cf8f6bcfc01acdda9292f4f5725b00c5ca28bce1965f"}