{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UAC3AIVMV37IIM7EYPQT6PIT6V","short_pith_number":"pith:UAC3AIVM","schema_version":"1.0","canonical_sha256":"a005b022acaefe8433e4c3e13f3d13f54a5504383587e7a1b6357463fdc7fb22","source":{"kind":"arxiv","id":"2104.08303","version":2},"attestation_state":"computed","paper":{"title":"Capturing Row and Column Semantics in Transformer Based Question Answering over Tables","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Alfio Gliozzo, Avi Sil, Feifei Pan, Michael Glass, Mustafa Canim, Nicolas Rodolfo Fauceglia, Rishav Chakravarti, Samarth Bharadwaj, Saneem Chemmengath, Vishwajeet Kumar","submitted_at":"2021-04-16T18:22:30Z","abstract_excerpt":"Transformer based architectures are recently used for the task of answering questions over tables. In order to improve the accuracy on this task, specialized pre-training techniques have been developed and applied on millions of open-domain web tables. In this paper, we propose two novel approaches demonstrating that one can achieve superior performance on table QA task without even using any of these specialized pre-training techniques. The first model, called RCI interaction, leverages a transformer based architecture that independently classifies rows and columns to identify relevant cells."},"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":"2104.08303","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2021-04-16T18:22:30Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"21e7734a3e9d2263e1c747d323ddb6a6bd3e5cda9226decc4329c2149a3f58de","abstract_canon_sha256":"2711998103d1396c8783b990f8614f4232f13b5c338da05dcafb4d86b04540e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:35:02.827344Z","signature_b64":"69wA+ASmy4NZSCtg2T6VAp1OxVj9e0Z2BGPOJ6/kNGIczqAuGMMvyNKZgRjBnUHd5x0e0PmbSeYa0Gm74XOYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a005b022acaefe8433e4c3e13f3d13f54a5504383587e7a1b6357463fdc7fb22","last_reissued_at":"2026-07-05T02:35:02.826927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:35:02.826927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Capturing Row and Column Semantics in Transformer Based Question Answering over Tables","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Alfio Gliozzo, Avi Sil, Feifei Pan, Michael Glass, Mustafa Canim, Nicolas Rodolfo Fauceglia, Rishav Chakravarti, Samarth Bharadwaj, Saneem Chemmengath, Vishwajeet Kumar","submitted_at":"2021-04-16T18:22:30Z","abstract_excerpt":"Transformer based architectures are recently used for the task of answering questions over tables. In order to improve the accuracy on this task, specialized pre-training techniques have been developed and applied on millions of open-domain web tables. In this paper, we propose two novel approaches demonstrating that one can achieve superior performance on table QA task without even using any of these specialized pre-training techniques. The first model, called RCI interaction, leverages a transformer based architecture that independently classifies rows and columns to identify relevant cells."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08303","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/2104.08303/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":"2104.08303","created_at":"2026-07-05T02:35:02.826989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.08303v2","created_at":"2026-07-05T02:35:02.826989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08303","created_at":"2026-07-05T02:35:02.826989+00:00"},{"alias_kind":"pith_short_12","alias_value":"UAC3AIVMV37I","created_at":"2026-07-05T02:35:02.826989+00:00"},{"alias_kind":"pith_short_16","alias_value":"UAC3AIVMV37IIM7E","created_at":"2026-07-05T02:35:02.826989+00:00"},{"alias_kind":"pith_short_8","alias_value":"UAC3AIVM","created_at":"2026-07-05T02:35:02.826989+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/UAC3AIVMV37IIM7EYPQT6PIT6V","json":"https://pith.science/pith/UAC3AIVMV37IIM7EYPQT6PIT6V.json","graph_json":"https://pith.science/api/pith-number/UAC3AIVMV37IIM7EYPQT6PIT6V/graph.json","events_json":"https://pith.science/api/pith-number/UAC3AIVMV37IIM7EYPQT6PIT6V/events.json","paper":"https://pith.science/paper/UAC3AIVM"},"agent_actions":{"view_html":"https://pith.science/pith/UAC3AIVMV37IIM7EYPQT6PIT6V","download_json":"https://pith.science/pith/UAC3AIVMV37IIM7EYPQT6PIT6V.json","view_paper":"https://pith.science/paper/UAC3AIVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.08303&json=true","fetch_graph":"https://pith.science/api/pith-number/UAC3AIVMV37IIM7EYPQT6PIT6V/graph.json","fetch_events":"https://pith.science/api/pith-number/UAC3AIVMV37IIM7EYPQT6PIT6V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UAC3AIVMV37IIM7EYPQT6PIT6V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UAC3AIVMV37IIM7EYPQT6PIT6V/action/storage_attestation","attest_author":"https://pith.science/pith/UAC3AIVMV37IIM7EYPQT6PIT6V/action/author_attestation","sign_citation":"https://pith.science/pith/UAC3AIVMV37IIM7EYPQT6PIT6V/action/citation_signature","submit_replication":"https://pith.science/pith/UAC3AIVMV37IIM7EYPQT6PIT6V/action/replication_record"}},"created_at":"2026-07-05T02:35:02.826989+00:00","updated_at":"2026-07-05T02:35:02.826989+00:00"}