{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UA2OXLNLMSJGYJBUJYRIG4D2QI","short_pith_number":"pith:UA2OXLNL","schema_version":"1.0","canonical_sha256":"a034ebadab64926c24344e2283707a82119a2cb6da71d6c64b8a823287543ae1","source":{"kind":"arxiv","id":"2606.05812","version":1},"attestation_state":"computed","paper":{"title":"FORTE: FOL-guided Optimal Refinement for Text-audio rEtrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.MM","authors_text":"Arghya Pal, Sailaja Rajanala","submitted_at":"2026-06-04T07:50:33Z","abstract_excerpt":"Text-to-audio retrieval has made significant progress with shared embedding models such as CLAP and Pengi, yet they often struggle with fine-grained semantic alignment due to the inherent modality gap between text and audio. In this work, we propose FORTE, a unified framework that integrates structured logical reasoning with parameter-efficient cross-modal alignment to improve retrieval precision. Our approach first transforms queries into first-order logic and refines them via a constrained search that preserves semantic invariance while introducing discriminative attributes. The refined repr"},"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":"2606.05812","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-06-04T07:50:33Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"dccd541648e9d9496f8f7b6e3a27f428ffc81b1c62d0ba1d22fb85473a238f5b","abstract_canon_sha256":"d96d9778471f302f39d443ece46bf1c295b1e18a7f91c9cd221046e5358cd59d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:04.131597Z","signature_b64":"+ri02AqE+QPGuSTCKP1MRmvZUaw8zw6kH+h1+QcF4FczqnCAQxLrVFIu7Fb0hgg8B9bJF1B8eBMBrAbVdUVyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a034ebadab64926c24344e2283707a82119a2cb6da71d6c64b8a823287543ae1","last_reissued_at":"2026-06-05T01:15:04.130979Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:04.130979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FORTE: FOL-guided Optimal Refinement for Text-audio rEtrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.MM","authors_text":"Arghya Pal, Sailaja Rajanala","submitted_at":"2026-06-04T07:50:33Z","abstract_excerpt":"Text-to-audio retrieval has made significant progress with shared embedding models such as CLAP and Pengi, yet they often struggle with fine-grained semantic alignment due to the inherent modality gap between text and audio. In this work, we propose FORTE, a unified framework that integrates structured logical reasoning with parameter-efficient cross-modal alignment to improve retrieval precision. Our approach first transforms queries into first-order logic and refines them via a constrained search that preserves semantic invariance while introducing discriminative attributes. The refined repr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05812","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/2606.05812/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":"2606.05812","created_at":"2026-06-05T01:15:04.131060+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05812v1","created_at":"2026-06-05T01:15:04.131060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05812","created_at":"2026-06-05T01:15:04.131060+00:00"},{"alias_kind":"pith_short_12","alias_value":"UA2OXLNLMSJG","created_at":"2026-06-05T01:15:04.131060+00:00"},{"alias_kind":"pith_short_16","alias_value":"UA2OXLNLMSJGYJBU","created_at":"2026-06-05T01:15:04.131060+00:00"},{"alias_kind":"pith_short_8","alias_value":"UA2OXLNL","created_at":"2026-06-05T01:15:04.131060+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/UA2OXLNLMSJGYJBUJYRIG4D2QI","json":"https://pith.science/pith/UA2OXLNLMSJGYJBUJYRIG4D2QI.json","graph_json":"https://pith.science/api/pith-number/UA2OXLNLMSJGYJBUJYRIG4D2QI/graph.json","events_json":"https://pith.science/api/pith-number/UA2OXLNLMSJGYJBUJYRIG4D2QI/events.json","paper":"https://pith.science/paper/UA2OXLNL"},"agent_actions":{"view_html":"https://pith.science/pith/UA2OXLNLMSJGYJBUJYRIG4D2QI","download_json":"https://pith.science/pith/UA2OXLNLMSJGYJBUJYRIG4D2QI.json","view_paper":"https://pith.science/paper/UA2OXLNL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05812&json=true","fetch_graph":"https://pith.science/api/pith-number/UA2OXLNLMSJGYJBUJYRIG4D2QI/graph.json","fetch_events":"https://pith.science/api/pith-number/UA2OXLNLMSJGYJBUJYRIG4D2QI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UA2OXLNLMSJGYJBUJYRIG4D2QI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UA2OXLNLMSJGYJBUJYRIG4D2QI/action/storage_attestation","attest_author":"https://pith.science/pith/UA2OXLNLMSJGYJBUJYRIG4D2QI/action/author_attestation","sign_citation":"https://pith.science/pith/UA2OXLNLMSJGYJBUJYRIG4D2QI/action/citation_signature","submit_replication":"https://pith.science/pith/UA2OXLNLMSJGYJBUJYRIG4D2QI/action/replication_record"}},"created_at":"2026-06-05T01:15:04.131060+00:00","updated_at":"2026-06-05T01:15:04.131060+00:00"}