{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SNWUXK5XLHWKECHTP6XQ7RCCE7","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":"c9d6d8e7d866c0884e17b18808aaac4ba6367dadc6f3e6da904104a9e3f316c1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-05-04T14:34:36Z","title_canon_sha256":"1530913cd0ae2ca7c7b7034cd6d1daeb1e2835f61cbfff88c2190e62d7dafae0"},"schema_version":"1.0","source":{"id":"2605.02651","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.02651","created_at":"2026-05-20T00:00:40Z"},{"alias_kind":"arxiv_version","alias_value":"2605.02651v2","created_at":"2026-05-20T00:00:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.02651","created_at":"2026-05-20T00:00:40Z"},{"alias_kind":"pith_short_12","alias_value":"SNWUXK5XLHWK","created_at":"2026-05-20T00:00:40Z"},{"alias_kind":"pith_short_16","alias_value":"SNWUXK5XLHWKECHT","created_at":"2026-05-20T00:00:40Z"},{"alias_kind":"pith_short_8","alias_value":"SNWUXK5X","created_at":"2026-05-20T00:00:40Z"}],"graph_snapshots":[{"event_id":"sha256:6f9334772cce0e167c3375a65b5372515632d1de5bff4c4f84d4dcdbb7a53b77","target":"graph","created_at":"2026-05-20T00:00:40Z","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":"Experiments on 213 ReScience C articles demonstrate ARA's generalizability and consistent workflow reconstruction and assessment across LLMs, model temperatures, and scientific domains. ARA achieves ~61% accuracy on three benchmarks, and the highest accuracy reported on ReproBench (60.71% vs. 36.84%) and GoldStandardDB (61.68% vs. 43.56%)."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the directed workflow graphs extracted by the agentic system accurately capture the paper's experimental dependencies, data flows, and result-generating procedures in a way that correlates with actual human-validated reproducibility."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ARA uses LLMs to build workflow graphs linking sources, methods, and outputs in papers, then scores reproducibility, reaching ~61% accuracy on 213 ReScience C articles and outperforming priors on ReproBench and GoldStandardDB."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"ARA extracts directed workflow graphs from papers to evaluate reproducibility at scale."}],"snapshot_sha256":"657616c77ba0652cac99718b67f6cd776546ed7adf91ad6a1318108d8d87801b"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"6f0255288638567005bb0bf2ff23e9bf4033195601cd38394da5a273cdcd2bae"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T16:08:58.816968Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.02651/integrity.json","findings":[],"snapshot_sha256":"228d0ce0dc09f8d7a3660bfbaf74045a1a554c2c33c4cafe722f0501b913590a","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scientific peer review increasingly struggles to assess reproducibility at the scale and complexity of modern research output. Evaluating reproducibility requires reconstructing experimental dependencies, methodological choices, data flows, and result-generating procedures, which often exceeds what human reviewers can provide. Agentic Reproducibility Assessment (ARA) formalizes reproducibility assessment as a structured reasoning task over scientific documents. Given a paper, ARA extracts a directed workflow graph linking sources, methods, experiments, and outputs, then evaluates its reconstru","authors_text":"Anastasios Kouvelas, Andres L. Marin, Fan Wu, Georgios Fontaras, Kevin Riehl, Michail A. Makridis, Nikofors Zacharof, Patrick Langer, Robert Jakob","cross_cats":["cs.LG"],"headline":"ARA extracts directed workflow graphs from papers to evaluate reproducibility at scale.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-05-04T14:34:36Z","title":"ARA: Agentic Reproducibility Assessment For Scalable Support Of Scientific Peer-Review"},"references":{"count":62,"internal_anchors":2,"resolved_work":62,"sample":[{"cited_arxiv_id":"","doi":"10.2307/1290335","is_internal_anchor":false,"ref_index":1,"title":"Publish or perish","work_id":"645bdc08-04c9-4c7c-978f-b9503dffe8e1","year":2000},{"cited_arxiv_id":"","doi":"10.1038/440413a","is_internal_anchor":false,"ref_index":2,"title":"Science in an exponential world","work_id":"6d117d26-eaeb-4fa7-bb39-cdd415b36894","year":2006},{"cited_arxiv_id":"","doi":"10.18653/v1/2023.trustnlp-1.17","is_internal_anchor":false,"ref_index":3,"title":"Distinguishing fact from fiction: A benchmark dataset for identifying machine-generated scientific papers in the llm era","work_id":"3d37b1b4-088e-49ae-a71c-4b42f8f881fb","year":2023},{"cited_arxiv_id":"","doi":"10.1101/2024.03.25.586710","is_internal_anchor":false,"ref_index":4,"title":"Have ai-generated texts from llm infiltrated the realm of sci- entific writing? a large-scale analysis of preprint platforms","work_id":"6c2fddeb-b9f4-4665-875e-34f6bff5eae1","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Is LLM a reliable reviewer? a comprehensive evaluation of LLM on automatic paper reviewing tasks,","work_id":"30ca2493-b3c7-4a16-8bf5-08d8ad266893","year":2024}],"snapshot_sha256":"ee36ecdb7b1d422225e4aa365477b64e7034046724de4128e645bf3dff4434c9"},"source":{"id":"2605.02651","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-19T17:09:47.577891Z","id":"adf26f68-68b2-4515-b4f2-49b5c7183e57","model_set":{"reader":"grok-4.3"},"one_line_summary":"ARA uses LLMs to build workflow graphs linking sources, methods, and outputs in papers, then scores reproducibility, reaching ~61% accuracy on 213 ReScience C articles and outperforming priors on ReproBench and GoldStandardDB.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"ARA extracts directed workflow graphs from papers to evaluate reproducibility at scale.","strongest_claim":"Experiments on 213 ReScience C articles demonstrate ARA's generalizability and consistent workflow reconstruction and assessment across LLMs, model temperatures, and scientific domains. ARA achieves ~61% accuracy on three benchmarks, and the highest accuracy reported on ReproBench (60.71% vs. 36.84%) and GoldStandardDB (61.68% vs. 43.56%).","weakest_assumption":"That the directed workflow graphs extracted by the agentic system accurately capture the paper's experimental dependencies, data flows, and result-generating procedures in a way that correlates with actual human-validated reproducibility."}},"verdict_id":"adf26f68-68b2-4515-b4f2-49b5c7183e57"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:86c85585f6ac51dcc8f59117076f9c1e64625b082fa77c061e4bbcb99bc07b9c","target":"record","created_at":"2026-05-20T00:00:40Z","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":"c9d6d8e7d866c0884e17b18808aaac4ba6367dadc6f3e6da904104a9e3f316c1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-05-04T14:34:36Z","title_canon_sha256":"1530913cd0ae2ca7c7b7034cd6d1daeb1e2835f61cbfff88c2190e62d7dafae0"},"schema_version":"1.0","source":{"id":"2605.02651","kind":"arxiv","version":2}},"canonical_sha256":"936d4babb759eca208f37faf0fc44227c8fe885a1b37182d1779789c266bff9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"936d4babb759eca208f37faf0fc44227c8fe885a1b37182d1779789c266bff9b","first_computed_at":"2026-05-20T00:00:40.405373Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:40.405373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"683t02mLRxEvfsStcqGwrWtXpeO0spPtVqH+riG67HuSoN7DVm6fiKPT+jS0Kbt3i2Q6fs4TcQyfMVw/b68rBQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:40.406215Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.02651","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86c85585f6ac51dcc8f59117076f9c1e64625b082fa77c061e4bbcb99bc07b9c","sha256:6f9334772cce0e167c3375a65b5372515632d1de5bff4c4f84d4dcdbb7a53b77"],"state_sha256":"a5d7058762ca4752bb67f6822c95814e952385d7a76fd02ee5609049a408d8b5"}