{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OYGVDNRUDEBNEJH5V6MMI7AFYE","short_pith_number":"pith:OYGVDNRU","schema_version":"1.0","canonical_sha256":"760d51b6341902d224fdaf98c47c05c10ee3d0fb6e9e31b3f82aeeacf682399c","source":{"kind":"arxiv","id":"2603.08910","version":2},"attestation_state":"computed","paper":{"title":"SciTaRC: A Plan-Annotated Scientific Tabular QA Benchmark for Language Reasoning and Complex Computation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adarsh Prabhudesai, Elina Baral, Hexuan Wang, Philipp Koehn, Rongkun Zhou, Shuxian Chen, Srikar Bommireddypalli, Yaxuan Ren","submitted_at":"2026-03-09T20:28:14Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2603.08910","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-09T20:28:14Z","cross_cats_sorted":[],"title_canon_sha256":"823727278d2b107ddf193d01942432ab8649d3adb3cc89bfd2a48ce785104182","abstract_canon_sha256":"b570ae014ba43b9ce39da0b06bae0096c954254b6f75f5956f527567da6668b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T00:14:51.787731Z","signature_b64":"ANx3gB9to0owa7HvU4yvH8dtAMB0FRYi+b85RdYWNXj617bY2DeIHbGQVGmVWOkXL+hFAdy1ysiW87uTKBVfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"760d51b6341902d224fdaf98c47c05c10ee3d0fb6e9e31b3f82aeeacf682399c","last_reissued_at":"2026-08-11T00:14:51.784889Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T00:14:51.784889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SciTaRC: A Plan-Annotated Scientific Tabular QA Benchmark for Language Reasoning and Complex Computation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adarsh Prabhudesai, Elina Baral, Hexuan Wang, Philipp Koehn, Rongkun Zhou, Shuxian Chen, Srikar Bommireddypalli, Yaxuan Ren","submitted_at":"2026-03-09T20:28:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.08910","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.08910/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2603.08910","created_at":"2026-08-11T00:14:51.785283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.08910v2","created_at":"2026-08-11T00:14:51.785283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.08910","created_at":"2026-08-11T00:14:51.785283+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYGVDNRUDEBN","created_at":"2026-08-11T00:14:51.785283+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYGVDNRUDEBNEJH5","created_at":"2026-08-11T00:14:51.785283+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYGVDNRU","created_at":"2026-08-11T00:14:51.785283+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OYGVDNRUDEBNEJH5V6MMI7AFYE","json":"https://pith.science/pith/OYGVDNRUDEBNEJH5V6MMI7AFYE.json","graph_json":"https://pith.science/api/pith-number/OYGVDNRUDEBNEJH5V6MMI7AFYE/graph.json","events_json":"https://pith.science/api/pith-number/OYGVDNRUDEBNEJH5V6MMI7AFYE/events.json","paper":"https://pith.science/paper/OYGVDNRU"},"agent_actions":{"view_html":"https://pith.science/pith/OYGVDNRUDEBNEJH5V6MMI7AFYE","download_json":"https://pith.science/pith/OYGVDNRUDEBNEJH5V6MMI7AFYE.json","view_paper":"https://pith.science/paper/OYGVDNRU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.08910&json=true","fetch_graph":"https://pith.science/api/pith-number/OYGVDNRUDEBNEJH5V6MMI7AFYE/graph.json","fetch_events":"https://pith.science/api/pith-number/OYGVDNRUDEBNEJH5V6MMI7AFYE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYGVDNRUDEBNEJH5V6MMI7AFYE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYGVDNRUDEBNEJH5V6MMI7AFYE/action/storage_attestation","attest_author":"https://pith.science/pith/OYGVDNRUDEBNEJH5V6MMI7AFYE/action/author_attestation","sign_citation":"https://pith.science/pith/OYGVDNRUDEBNEJH5V6MMI7AFYE/action/citation_signature","submit_replication":"https://pith.science/pith/OYGVDNRUDEBNEJH5V6MMI7AFYE/action/replication_record"}},"created_at":"2026-08-11T00:14:51.785283+00:00","updated_at":"2026-08-11T00:14:51.785283+00:00"}