{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3NAICPASB3LOFPP6JR5DUFZL27","short_pith_number":"pith:3NAICPAS","schema_version":"1.0","canonical_sha256":"db40813c120ed6e2bdfe4c7a3a172bd7c137787afe584e1711ca9767c87fcbc3","source":{"kind":"arxiv","id":"2505.19588","version":1},"attestation_state":"computed","paper":{"title":"LogiCoL: Logically-Informed Contrastive Learning for Set-based Dense Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chaitanya Malaviya, Dan Roth, Sihao Chen, Xueqiang Xu, Yanzhen Shen, Yunyi Zhang","submitted_at":"2025-05-26T07:00:32Z","abstract_excerpt":"While significant progress has been made with dual- and bi-encoder dense retrievers, they often struggle on queries with logical connectives, a use case that is often overlooked yet important in downstream applications. Current dense retrievers struggle with such queries, such that the retrieved results do not respect the logical constraints implied in the queries. To address this challenge, we introduce LogiCoL, a logically-informed contrastive learning objective for dense retrievers. LogiCoL builds upon in-batch supervised contrastive learning, and learns dense retrievers to respect the subs"},"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":"2505.19588","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-26T07:00:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"506d0ddd978ca26bfab400a9e453ca139c6eddb79a6ddd8a9495bbde39993fd2","abstract_canon_sha256":"26b2ec9a165d7a89e86e4d79b276af7f0d03e93e0a80f68a17defc1b9dd816b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:33.094492Z","signature_b64":"J7qaqZlEsK70rhXneSnCxZAsVs/N4VOWFxL56BY2nZrf+BjuBxpzRnc372U0zCaMo6GsxllE3heYEyBX0qL6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db40813c120ed6e2bdfe4c7a3a172bd7c137787afe584e1711ca9767c87fcbc3","last_reissued_at":"2026-07-05T11:09:33.093974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:33.093974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LogiCoL: Logically-Informed Contrastive Learning for Set-based Dense Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chaitanya Malaviya, Dan Roth, Sihao Chen, Xueqiang Xu, Yanzhen Shen, Yunyi Zhang","submitted_at":"2025-05-26T07:00:32Z","abstract_excerpt":"While significant progress has been made with dual- and bi-encoder dense retrievers, they often struggle on queries with logical connectives, a use case that is often overlooked yet important in downstream applications. Current dense retrievers struggle with such queries, such that the retrieved results do not respect the logical constraints implied in the queries. To address this challenge, we introduce LogiCoL, a logically-informed contrastive learning objective for dense retrievers. LogiCoL builds upon in-batch supervised contrastive learning, and learns dense retrievers to respect the subs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19588","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/2505.19588/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":"2505.19588","created_at":"2026-07-05T11:09:33.094026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19588v1","created_at":"2026-07-05T11:09:33.094026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19588","created_at":"2026-07-05T11:09:33.094026+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NAICPASB3LO","created_at":"2026-07-05T11:09:33.094026+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NAICPASB3LOFPP6","created_at":"2026-07-05T11:09:33.094026+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NAICPAS","created_at":"2026-07-05T11:09:33.094026+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/3NAICPASB3LOFPP6JR5DUFZL27","json":"https://pith.science/pith/3NAICPASB3LOFPP6JR5DUFZL27.json","graph_json":"https://pith.science/api/pith-number/3NAICPASB3LOFPP6JR5DUFZL27/graph.json","events_json":"https://pith.science/api/pith-number/3NAICPASB3LOFPP6JR5DUFZL27/events.json","paper":"https://pith.science/paper/3NAICPAS"},"agent_actions":{"view_html":"https://pith.science/pith/3NAICPASB3LOFPP6JR5DUFZL27","download_json":"https://pith.science/pith/3NAICPASB3LOFPP6JR5DUFZL27.json","view_paper":"https://pith.science/paper/3NAICPAS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19588&json=true","fetch_graph":"https://pith.science/api/pith-number/3NAICPASB3LOFPP6JR5DUFZL27/graph.json","fetch_events":"https://pith.science/api/pith-number/3NAICPASB3LOFPP6JR5DUFZL27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NAICPASB3LOFPP6JR5DUFZL27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NAICPASB3LOFPP6JR5DUFZL27/action/storage_attestation","attest_author":"https://pith.science/pith/3NAICPASB3LOFPP6JR5DUFZL27/action/author_attestation","sign_citation":"https://pith.science/pith/3NAICPASB3LOFPP6JR5DUFZL27/action/citation_signature","submit_replication":"https://pith.science/pith/3NAICPASB3LOFPP6JR5DUFZL27/action/replication_record"}},"created_at":"2026-07-05T11:09:33.094026+00:00","updated_at":"2026-07-05T11:09:33.094026+00:00"}