{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UA2OXLNLMSJGYJBUJYRIG4D2QI","short_pith_number":"pith:UA2OXLNL","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"},"canonical_sha256":"a034ebadab64926c24344e2283707a82119a2cb6da71d6c64b8a823287543ae1","source":{"kind":"arxiv","id":"2606.05812","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05812","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05812v1","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05812","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"UA2OXLNLMSJG","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"pith_short_16","alias_value":"UA2OXLNLMSJGYJBU","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"pith_short_8","alias_value":"UA2OXLNL","created_at":"2026-06-05T01:15:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UA2OXLNLMSJGYJBUJYRIG4D2QI","target":"record","payload":{"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"},"canonical_sha256":"a034ebadab64926c24344e2283707a82119a2cb6da71d6c64b8a823287543ae1","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"},"source_kind":"arxiv","source_id":"2606.05812","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T01:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6lQEOT+7pevGcxGR5xKO4hKYxMx1mem+8nW1W7VmBsbAhbq2ICVXIC+UIVh0xagEFiH4JBkOnqE6mGmFPFcbAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T15:45:37.301495Z"},"content_sha256":"a863b1a57ec8c3b7639aedd72f1bbc91db2a6cf03daed39dc4785b614e2827a6","schema_version":"1.0","event_id":"sha256:a863b1a57ec8c3b7639aedd72f1bbc91db2a6cf03daed39dc4785b614e2827a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UA2OXLNLMSJGYJBUJYRIG4D2QI","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T01:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"24GHoW5WB8nWYaxPCw4ttj98UgGxFgIvnF1FiyZ4AZljaNX9wFYkcZIFU6z4cYLCzwVTBrvq3HLjjvOsaDhVCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T15:45:37.301884Z"},"content_sha256":"a8bfa224ce98682d83f2545b668fc8898d351ceb37f6fc40128e8f357ff2506f","schema_version":"1.0","event_id":"sha256:a8bfa224ce98682d83f2545b668fc8898d351ceb37f6fc40128e8f357ff2506f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UA2OXLNLMSJGYJBUJYRIG4D2QI/bundle.json","state_url":"https://pith.science/pith/UA2OXLNLMSJGYJBUJYRIG4D2QI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UA2OXLNLMSJGYJBUJYRIG4D2QI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-03T15:45:37Z","links":{"resolver":"https://pith.science/pith/UA2OXLNLMSJGYJBUJYRIG4D2QI","bundle":"https://pith.science/pith/UA2OXLNLMSJGYJBUJYRIG4D2QI/bundle.json","state":"https://pith.science/pith/UA2OXLNLMSJGYJBUJYRIG4D2QI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UA2OXLNLMSJGYJBUJYRIG4D2QI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UA2OXLNLMSJGYJBUJYRIG4D2QI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d96d9778471f302f39d443ece46bf1c295b1e18a7f91c9cd221046e5358cd59d","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-06-04T07:50:33Z","title_canon_sha256":"dccd541648e9d9496f8f7b6e3a27f428ffc81b1c62d0ba1d22fb85473a238f5b"},"schema_version":"1.0","source":{"id":"2606.05812","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05812","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05812v1","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05812","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"UA2OXLNLMSJG","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"pith_short_16","alias_value":"UA2OXLNLMSJGYJBU","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"pith_short_8","alias_value":"UA2OXLNL","created_at":"2026-06-05T01:15:04Z"}],"graph_snapshots":[{"event_id":"sha256:a8bfa224ce98682d83f2545b668fc8898d351ceb37f6fc40128e8f357ff2506f","target":"graph","created_at":"2026-06-05T01:15:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.05812/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Arghya Pal, Sailaja Rajanala","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-06-04T07:50:33Z","title":"FORTE: FOL-guided Optimal Refinement for Text-audio rEtrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05812","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a863b1a57ec8c3b7639aedd72f1bbc91db2a6cf03daed39dc4785b614e2827a6","target":"record","created_at":"2026-06-05T01:15:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d96d9778471f302f39d443ece46bf1c295b1e18a7f91c9cd221046e5358cd59d","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-06-04T07:50:33Z","title_canon_sha256":"dccd541648e9d9496f8f7b6e3a27f428ffc81b1c62d0ba1d22fb85473a238f5b"},"schema_version":"1.0","source":{"id":"2606.05812","kind":"arxiv","version":1}},"canonical_sha256":"a034ebadab64926c24344e2283707a82119a2cb6da71d6c64b8a823287543ae1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a034ebadab64926c24344e2283707a82119a2cb6da71d6c64b8a823287543ae1","first_computed_at":"2026-06-05T01:15:04.130979Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:04.130979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+ri02AqE+QPGuSTCKP1MRmvZUaw8zw6kH+h1+QcF4FczqnCAQxLrVFIu7Fb0hgg8B9bJF1B8eBMBrAbVdUVyCA==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:04.131597Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05812","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a863b1a57ec8c3b7639aedd72f1bbc91db2a6cf03daed39dc4785b614e2827a6","sha256:a8bfa224ce98682d83f2545b668fc8898d351ceb37f6fc40128e8f357ff2506f"],"state_sha256":"966c447d258556f6ba66c1d383442c07043387dc122bd5736df4475a6ae1613c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b6sDFMvHPCEHUozD7NsIDsxS/1D+/ATD9R3btind+4ftyfkNnJvpRcR3IHoPXTpGuNbXK7r05faYOkm08f2YBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T15:45:37.304026Z","bundle_sha256":"6254e7c409311cdb82d50c21fccbc45f5991dbb219e5d0239aa7ba3cf74cc30e"}}