{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OYGVDNRUDEBNEJH5V6MMI7AFYE","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":"b570ae014ba43b9ce39da0b06bae0096c954254b6f75f5956f527567da6668b1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-09T20:28:14Z","title_canon_sha256":"823727278d2b107ddf193d01942432ab8649d3adb3cc89bfd2a48ce785104182"},"schema_version":"1.0","source":{"id":"2603.08910","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.08910","created_at":"2026-08-11T00:14:51Z"},{"alias_kind":"arxiv_version","alias_value":"2603.08910v2","created_at":"2026-08-11T00:14:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.08910","created_at":"2026-08-11T00:14:51Z"},{"alias_kind":"pith_short_12","alias_value":"OYGVDNRUDEBN","created_at":"2026-08-11T00:14:51Z"},{"alias_kind":"pith_short_16","alias_value":"OYGVDNRUDEBNEJH5","created_at":"2026-08-11T00:14:51Z"},{"alias_kind":"pith_short_8","alias_value":"OYGVDNRU","created_at":"2026-08-11T00:14:51Z"}],"graph_snapshots":[{"event_id":"sha256:f3b14f4ae3b9fa46a860fddef817db1c8219da82975e35932db23f9f343137eb","target":"graph","created_at":"2026-08-11T00:14:51Z","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/2603.08910/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce SciTaRC, an expert-authored benchmark for question answering over scientific tables that targets composite, multi-step reasoning. To enable fine-grained diagnostic analysis beyond end-task accuracy, SciTaRC pairs each question with a manually constructed reasoning plan and explicit complexity metrics. State-of-the-art models fail on at least 23% of these questions, while highly capable open-weight models like Llama-3.3-70B collapse on 65.5% of the benchmark. Error analysis shows that, in zero-shot settings, failures are driven primarily by question comprehension, where models misi","authors_text":"Adarsh Prabhudesai, Elina Baral, Hexuan Wang, Philipp Koehn, Rongkun Zhou, Shuxian Chen, Srikar Bommireddypalli, Yaxuan Ren","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-09T20:28:14Z","title":"SciTaRC: A Plan-Annotated Scientific Tabular QA Benchmark for Language Reasoning and Complex Computation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.08910","kind":"arxiv","version":2},"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:af2ad48bd376b6442361529a481d96ee8e39ddd0950ed538771438b1f62f46b4","target":"record","created_at":"2026-08-11T00:14:51Z","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":"b570ae014ba43b9ce39da0b06bae0096c954254b6f75f5956f527567da6668b1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-09T20:28:14Z","title_canon_sha256":"823727278d2b107ddf193d01942432ab8649d3adb3cc89bfd2a48ce785104182"},"schema_version":"1.0","source":{"id":"2603.08910","kind":"arxiv","version":2}},"canonical_sha256":"760d51b6341902d224fdaf98c47c05c10ee3d0fb6e9e31b3f82aeeacf682399c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"760d51b6341902d224fdaf98c47c05c10ee3d0fb6e9e31b3f82aeeacf682399c","first_computed_at":"2026-08-11T00:14:51.784889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T00:14:51.784889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ANx3gB9to0owa7HvU4yvH8dtAMB0FRYi+b85RdYWNXj617bY2DeIHbGQVGmVWOkXL+hFAdy1ysiW87uTKBVfCg==","signature_status":"signed_v1","signed_at":"2026-08-11T00:14:51.787731Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.08910","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af2ad48bd376b6442361529a481d96ee8e39ddd0950ed538771438b1f62f46b4","sha256:f3b14f4ae3b9fa46a860fddef817db1c8219da82975e35932db23f9f343137eb"],"state_sha256":"22974bc2797d49626fdb535bb7841cddd78392b61a35deb2741eef5fb943cd52"}