{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7W6NBBJ5LCS36PGE6HTJAI2D6P","short_pith_number":"pith:7W6NBBJ5","schema_version":"1.0","canonical_sha256":"fdbcd0853d58a5bf3cc4f1e6902343f3d91f5b69ed2085bd563d15bbf6cec455","source":{"kind":"arxiv","id":"2210.05197","version":1},"attestation_state":"computed","paper":{"title":"Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Daxin Jiang, Junjie Huang, Ming Gong, Nan Duan, Qian Liu, Wanjun Zhong","submitted_at":"2022-10-11T07:04:39Z","abstract_excerpt":"Retrieving evidences from tabular and textual resources is essential for open-domain question answering (OpenQA), which provides more comprehensive information. However, training an effective dense table-text retriever is difficult due to the challenges of table-text discrepancy and data sparsity problem. To address the above challenges, we introduce an optimized OpenQA Table-Text Retriever (OTTeR) to jointly retrieve tabular and textual evidences. Firstly, we propose to enhance mixed-modality representation learning via two mechanisms: modality-enhanced representation and mixed-modality negat"},"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":"2210.05197","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T07:04:39Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"c8897a9b44ee9161d5e2ab0e6a4186032bb16a977f9b3b5457f77da0dd181b85","abstract_canon_sha256":"3761225b4a13271d235509b3d574dee92c55775f9fb13df20cbf9ac632d398c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:15.520571Z","signature_b64":"VEOWYf/neBMuBFxgynM/WwZhChSVtTmHkFPMYL3lw4OLbjSlrQQrRi4YYVLpChmPtcQv8E5sgO2nXJJivkSPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdbcd0853d58a5bf3cc4f1e6902343f3d91f5b69ed2085bd563d15bbf6cec455","last_reissued_at":"2026-07-05T05:06:15.520094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:15.520094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Daxin Jiang, Junjie Huang, Ming Gong, Nan Duan, Qian Liu, Wanjun Zhong","submitted_at":"2022-10-11T07:04:39Z","abstract_excerpt":"Retrieving evidences from tabular and textual resources is essential for open-domain question answering (OpenQA), which provides more comprehensive information. However, training an effective dense table-text retriever is difficult due to the challenges of table-text discrepancy and data sparsity problem. To address the above challenges, we introduce an optimized OpenQA Table-Text Retriever (OTTeR) to jointly retrieve tabular and textual evidences. Firstly, we propose to enhance mixed-modality representation learning via two mechanisms: modality-enhanced representation and mixed-modality negat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05197","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/2210.05197/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":"2210.05197","created_at":"2026-07-05T05:06:15.520154+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.05197v1","created_at":"2026-07-05T05:06:15.520154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05197","created_at":"2026-07-05T05:06:15.520154+00:00"},{"alias_kind":"pith_short_12","alias_value":"7W6NBBJ5LCS3","created_at":"2026-07-05T05:06:15.520154+00:00"},{"alias_kind":"pith_short_16","alias_value":"7W6NBBJ5LCS36PGE","created_at":"2026-07-05T05:06:15.520154+00:00"},{"alias_kind":"pith_short_8","alias_value":"7W6NBBJ5","created_at":"2026-07-05T05:06:15.520154+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/7W6NBBJ5LCS36PGE6HTJAI2D6P","json":"https://pith.science/pith/7W6NBBJ5LCS36PGE6HTJAI2D6P.json","graph_json":"https://pith.science/api/pith-number/7W6NBBJ5LCS36PGE6HTJAI2D6P/graph.json","events_json":"https://pith.science/api/pith-number/7W6NBBJ5LCS36PGE6HTJAI2D6P/events.json","paper":"https://pith.science/paper/7W6NBBJ5"},"agent_actions":{"view_html":"https://pith.science/pith/7W6NBBJ5LCS36PGE6HTJAI2D6P","download_json":"https://pith.science/pith/7W6NBBJ5LCS36PGE6HTJAI2D6P.json","view_paper":"https://pith.science/paper/7W6NBBJ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.05197&json=true","fetch_graph":"https://pith.science/api/pith-number/7W6NBBJ5LCS36PGE6HTJAI2D6P/graph.json","fetch_events":"https://pith.science/api/pith-number/7W6NBBJ5LCS36PGE6HTJAI2D6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7W6NBBJ5LCS36PGE6HTJAI2D6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7W6NBBJ5LCS36PGE6HTJAI2D6P/action/storage_attestation","attest_author":"https://pith.science/pith/7W6NBBJ5LCS36PGE6HTJAI2D6P/action/author_attestation","sign_citation":"https://pith.science/pith/7W6NBBJ5LCS36PGE6HTJAI2D6P/action/citation_signature","submit_replication":"https://pith.science/pith/7W6NBBJ5LCS36PGE6HTJAI2D6P/action/replication_record"}},"created_at":"2026-07-05T05:06:15.520154+00:00","updated_at":"2026-07-05T05:06:15.520154+00:00"}