{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SSY4AXEDU7CC4WBADJSFTAOVY6","short_pith_number":"pith:SSY4AXED","schema_version":"1.0","canonical_sha256":"94b1c05c83a7c42e58201a645981d5c788eba2332a68e4f04a9a75d2ae6d18d5","source":{"kind":"arxiv","id":"2606.05382","version":1},"attestation_state":"computed","paper":{"title":"Synthetic Contrastive Reasoning for Multi-Table Q&A","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ankit Pratap Singh, Phillip Howard, Xin Su","submitted_at":"2026-06-03T19:35:54Z","abstract_excerpt":"Multi-table question answering requires models to retrieve relevant evidence, link schemas, and perform compositional reasoning across relational tables. Existing multi-table Q&A resources typically provide questions and final answers but lack reasoning supervision that explains how answers are derived. To address this gap, we construct a synthetic contrastive reasoning-trace dataset for MMQA by generating validated positive traces and plausible negative traces with heterogeneous LLMs. We then use the resulting preference pairs to fine-tune open-weight LLMs with Contrastive Preference Optimiza"},"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":"2606.05382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-03T19:35:54Z","cross_cats_sorted":[],"title_canon_sha256":"857a327a33eb2dffb3417970edcf534bf1e3e7641e05483a622e2311536a0feb","abstract_canon_sha256":"407e0d5e5b423e532025be1777bd636126323ace6b1e67762107c809b74732a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:55.972748Z","signature_b64":"7qB5+U+S0w1bsn1o2fxiiADVWEi0Bd/aqi5TxgU/jyBYnw9PEsgF+KckWAWvZ8vu4A9cSFUQWAGFB76n2ggCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94b1c05c83a7c42e58201a645981d5c788eba2332a68e4f04a9a75d2ae6d18d5","last_reissued_at":"2026-06-05T00:13:55.972241Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:55.972241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Contrastive Reasoning for Multi-Table Q&A","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ankit Pratap Singh, Phillip Howard, Xin Su","submitted_at":"2026-06-03T19:35:54Z","abstract_excerpt":"Multi-table question answering requires models to retrieve relevant evidence, link schemas, and perform compositional reasoning across relational tables. Existing multi-table Q&A resources typically provide questions and final answers but lack reasoning supervision that explains how answers are derived. To address this gap, we construct a synthetic contrastive reasoning-trace dataset for MMQA by generating validated positive traces and plausible negative traces with heterogeneous LLMs. We then use the resulting preference pairs to fine-tune open-weight LLMs with Contrastive Preference Optimiza"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05382","kind":"arxiv","version":1},"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/2606.05382/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":"2606.05382","created_at":"2026-06-05T00:13:55.972311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05382v1","created_at":"2026-06-05T00:13:55.972311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05382","created_at":"2026-06-05T00:13:55.972311+00:00"},{"alias_kind":"pith_short_12","alias_value":"SSY4AXEDU7CC","created_at":"2026-06-05T00:13:55.972311+00:00"},{"alias_kind":"pith_short_16","alias_value":"SSY4AXEDU7CC4WBA","created_at":"2026-06-05T00:13:55.972311+00:00"},{"alias_kind":"pith_short_8","alias_value":"SSY4AXED","created_at":"2026-06-05T00:13:55.972311+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/SSY4AXEDU7CC4WBADJSFTAOVY6","json":"https://pith.science/pith/SSY4AXEDU7CC4WBADJSFTAOVY6.json","graph_json":"https://pith.science/api/pith-number/SSY4AXEDU7CC4WBADJSFTAOVY6/graph.json","events_json":"https://pith.science/api/pith-number/SSY4AXEDU7CC4WBADJSFTAOVY6/events.json","paper":"https://pith.science/paper/SSY4AXED"},"agent_actions":{"view_html":"https://pith.science/pith/SSY4AXEDU7CC4WBADJSFTAOVY6","download_json":"https://pith.science/pith/SSY4AXEDU7CC4WBADJSFTAOVY6.json","view_paper":"https://pith.science/paper/SSY4AXED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05382&json=true","fetch_graph":"https://pith.science/api/pith-number/SSY4AXEDU7CC4WBADJSFTAOVY6/graph.json","fetch_events":"https://pith.science/api/pith-number/SSY4AXEDU7CC4WBADJSFTAOVY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SSY4AXEDU7CC4WBADJSFTAOVY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SSY4AXEDU7CC4WBADJSFTAOVY6/action/storage_attestation","attest_author":"https://pith.science/pith/SSY4AXEDU7CC4WBADJSFTAOVY6/action/author_attestation","sign_citation":"https://pith.science/pith/SSY4AXEDU7CC4WBADJSFTAOVY6/action/citation_signature","submit_replication":"https://pith.science/pith/SSY4AXEDU7CC4WBADJSFTAOVY6/action/replication_record"}},"created_at":"2026-06-05T00:13:55.972311+00:00","updated_at":"2026-06-05T00:13:55.972311+00:00"}