{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3FLBGI6R33KKELBFI3X2IVL4FG","short_pith_number":"pith:3FLBGI6R","schema_version":"1.0","canonical_sha256":"d9561323d1ded4a22c2546efa4557c29a9f3868a17f6936d9cf8809434c635c7","source":{"kind":"arxiv","id":"2506.23463","version":3},"attestation_state":"computed","paper":{"title":"What to Keep and What to Drop: Adaptive Table Filtering Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Wonjune Jang","submitted_at":"2025-06-30T02:03:23Z","abstract_excerpt":"Large language models (LLMs) for table-based reasoning often struggle with large tables due to input length limits. We propose ATF (Adaptive Table Filtering Framework), a modular and question-aware filtering pipeline that prunes uninformative columns and rows using LLM-generated column descriptions, clustering, and sparse-dense alignment scores. ATF integrates seamlessly with existing models (e.g., TAPAS, TAPEX) without retraining. Experiments show that ATF reduces table cells by 70%, boosting performance on out-of-domain TableQA tasks while causing slight performance drops on Table Fact Verif"},"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":"2506.23463","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-30T02:03:23Z","cross_cats_sorted":[],"title_canon_sha256":"22c5a20136ffe332199e7f11e649326ef140496be93fe281eb9298b3aba9b1c9","abstract_canon_sha256":"254f2a1bcf2388b8ff890b221b972ee630987ad247cb7d620a6149dd841c7a17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:25.324306Z","signature_b64":"5kEye0+L6ap4zJBXXf733fLJTmkQRnD7I5qsXyUqnV90YYFsoArnjnviP4kJ8GSoaMue/rLZtfTKjBBCTgWgBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9561323d1ded4a22c2546efa4557c29a9f3868a17f6936d9cf8809434c635c7","last_reissued_at":"2026-07-05T11:47:25.323764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:25.323764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What to Keep and What to Drop: Adaptive Table Filtering Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Wonjune Jang","submitted_at":"2025-06-30T02:03:23Z","abstract_excerpt":"Large language models (LLMs) for table-based reasoning often struggle with large tables due to input length limits. We propose ATF (Adaptive Table Filtering Framework), a modular and question-aware filtering pipeline that prunes uninformative columns and rows using LLM-generated column descriptions, clustering, and sparse-dense alignment scores. ATF integrates seamlessly with existing models (e.g., TAPAS, TAPEX) without retraining. Experiments show that ATF reduces table cells by 70%, boosting performance on out-of-domain TableQA tasks while causing slight performance drops on Table Fact Verif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23463","kind":"arxiv","version":3},"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/2506.23463/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":"2506.23463","created_at":"2026-07-05T11:47:25.323825+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23463v3","created_at":"2026-07-05T11:47:25.323825+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23463","created_at":"2026-07-05T11:47:25.323825+00:00"},{"alias_kind":"pith_short_12","alias_value":"3FLBGI6R33KK","created_at":"2026-07-05T11:47:25.323825+00:00"},{"alias_kind":"pith_short_16","alias_value":"3FLBGI6R33KKELBF","created_at":"2026-07-05T11:47:25.323825+00:00"},{"alias_kind":"pith_short_8","alias_value":"3FLBGI6R","created_at":"2026-07-05T11:47:25.323825+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/3FLBGI6R33KKELBFI3X2IVL4FG","json":"https://pith.science/pith/3FLBGI6R33KKELBFI3X2IVL4FG.json","graph_json":"https://pith.science/api/pith-number/3FLBGI6R33KKELBFI3X2IVL4FG/graph.json","events_json":"https://pith.science/api/pith-number/3FLBGI6R33KKELBFI3X2IVL4FG/events.json","paper":"https://pith.science/paper/3FLBGI6R"},"agent_actions":{"view_html":"https://pith.science/pith/3FLBGI6R33KKELBFI3X2IVL4FG","download_json":"https://pith.science/pith/3FLBGI6R33KKELBFI3X2IVL4FG.json","view_paper":"https://pith.science/paper/3FLBGI6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23463&json=true","fetch_graph":"https://pith.science/api/pith-number/3FLBGI6R33KKELBFI3X2IVL4FG/graph.json","fetch_events":"https://pith.science/api/pith-number/3FLBGI6R33KKELBFI3X2IVL4FG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3FLBGI6R33KKELBFI3X2IVL4FG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3FLBGI6R33KKELBFI3X2IVL4FG/action/storage_attestation","attest_author":"https://pith.science/pith/3FLBGI6R33KKELBFI3X2IVL4FG/action/author_attestation","sign_citation":"https://pith.science/pith/3FLBGI6R33KKELBFI3X2IVL4FG/action/citation_signature","submit_replication":"https://pith.science/pith/3FLBGI6R33KKELBFI3X2IVL4FG/action/replication_record"}},"created_at":"2026-07-05T11:47:25.323825+00:00","updated_at":"2026-07-05T11:47:25.323825+00:00"}