{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PCARYHQBKCYB7APDFLCAXG6XWD","merge_version":"pith-open-graph-merge-v1","event_count":5,"valid_event_count":5,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"62c5feec7a026f5c769ab545bd1ae5d977fb383f9b59a7d5570ecf99f3847ab3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-11T20:30:32Z","title_canon_sha256":"90cd41ab7ecd3c975f91affe91ef615ea708fb93aa1d775712155ab9d5ec7daf"},"schema_version":"1.0","source":{"id":"2608.11415","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11415","created_at":"2026-08-13T00:21:48Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11415v1","created_at":"2026-08-13T00:21:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11415","created_at":"2026-08-13T00:21:48Z"},{"alias_kind":"pith_short_12","alias_value":"PCARYHQBKCYB","created_at":"2026-08-13T00:21:48Z"},{"alias_kind":"pith_short_16","alias_value":"PCARYHQBKCYB7APD","created_at":"2026-08-13T00:21:48Z"},{"alias_kind":"pith_short_8","alias_value":"PCARYHQB","created_at":"2026-08-13T00:21:48Z"}],"graph_snapshots":[{"event_id":"sha256:f045f3eb4296a50fe4d9bde8eab4efac978b2c0d912e45b8b4819de4626b8e60","target":"graph","created_at":"2026-08-13T00:21:48Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.11415/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models are being proposed as agents in scientific workflows, in domains where no downstream verifier exists. Such deployment assumes the model can distinguish reliable scientific literature from unreliable literature, a capability that has not yet been directly measured. Existing benchmarks evaluate factuality on questions with known answers; the failure mode we target here is different. We introduce a probe corpus of 42 retracted, fraudulent, and pseudoscientific papers, paired with a methodology for eliciting and scoring single-shot model engagement with each paper's framing. ","authors_text":"Shamil Assylbekov, Valentin Rodionov","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-11T20:30:32Z","title":"TRACES: A Benchmark for Epistemic Reliability in Scientific Reasoning by LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11415","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6de7986ed71367c5cad4e6c43997e6ea2f156fac7e6804c8a7caf1f8d2ac08cd","target":"record","created_at":"2026-08-13T00:21:48Z","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":"62c5feec7a026f5c769ab545bd1ae5d977fb383f9b59a7d5570ecf99f3847ab3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-11T20:30:32Z","title_canon_sha256":"90cd41ab7ecd3c975f91affe91ef615ea708fb93aa1d775712155ab9d5ec7daf"},"schema_version":"1.0","source":{"id":"2608.11415","kind":"arxiv","version":1}},"canonical_sha256":"78811c1e0150b01f81e32ac40b9bd7b0c78941250f2a050fddb969d0468cca2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78811c1e0150b01f81e32ac40b9bd7b0c78941250f2a050fddb969d0468cca2d","first_computed_at":"2026-08-13T00:21:48.372821Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T00:21:48.372821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"abwG1UOKlzu8ZRQKEwMDzhl5h57O2L/hEcTMhutbMklS2yplQBarhu+4MC4pNq/f6Aj08cq1N69AYeV0M+dJAg==","signature_status":"signed_v1","signed_at":"2026-08-13T00:21:48.374272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.11415","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:180fed777566710cea34e2f520a5d2ecffa6135e5c0aedc6f0e65387ae63fd6b","sha256:5bc252f1a5c312b6357677f10349a88b3c7c87ed65cef9474f354723da9019d9","sha256:cf2c36d6e3f115bf8c39efa9516f779c9bfbcd31f19787a1a37f99dbb8441070"]}],"invalid_events":[],"applied_event_ids":["sha256:6de7986ed71367c5cad4e6c43997e6ea2f156fac7e6804c8a7caf1f8d2ac08cd","sha256:f045f3eb4296a50fe4d9bde8eab4efac978b2c0d912e45b8b4819de4626b8e60"],"state_sha256":"c667ebf7e2bd92ed03d1d6597b931cbb8554c6d0ce1e4897277ddc3802f62b7b"}