{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DEV5SXLHHCXGH66LJROTG3W4XM","short_pith_number":"pith:DEV5SXLH","schema_version":"1.0","canonical_sha256":"192bd95d6738ae63fbcb4c5d336edcbb05c8644583ed33186b78831a1a504327","source":{"kind":"arxiv","id":"2412.01488","version":3},"attestation_state":"computed","paper":{"title":"TACO: Training-free Sound Prompted Segmentation via Semantically Constrained Audio-visual CO-factorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"eess.AS","authors_text":"Hugo Malard, Michel Olvera, Slim Essid, Stephane Lathuiliere","submitted_at":"2024-12-02T13:39:49Z","abstract_excerpt":"Large-scale pre-trained audio and image models demonstrate an unprecedented degree of generalization, making them suitable for a wide range of applications. Here, we tackle the specific task of sound-prompted segmentation, aiming to segment image regions corresponding to objects heard in an audio signal. Most existing approaches tackle this problem by fine-tuning pre-trained models or by training additional modules specifically for the task. We adopt a different strategy: we introduce a training-free approach that leverages Non-negative Matrix Factorization (NMF) to co-factorize audio and visu"},"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":"2412.01488","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-02T13:39:49Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"46258e06c969d5621c99aca71e253ef5962d5fcce939f14befad657ed4482278","abstract_canon_sha256":"96b18bf4d0d3eaf76adf66e3727435efd428e4e1e55cb2f371ce9a9bc3af6060"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:44.255895Z","signature_b64":"T9tuCJFepgWbIlc3dTYbsHxs6W1SUVKExxzb6++mgySkmakVnMoq6Ryc/bSS5Azs/eXOOCbkYwRxCtg/cYyoBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"192bd95d6738ae63fbcb4c5d336edcbb05c8644583ed33186b78831a1a504327","last_reissued_at":"2026-07-05T11:09:44.255398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:44.255398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TACO: Training-free Sound Prompted Segmentation via Semantically Constrained Audio-visual CO-factorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"eess.AS","authors_text":"Hugo Malard, Michel Olvera, Slim Essid, Stephane Lathuiliere","submitted_at":"2024-12-02T13:39:49Z","abstract_excerpt":"Large-scale pre-trained audio and image models demonstrate an unprecedented degree of generalization, making them suitable for a wide range of applications. Here, we tackle the specific task of sound-prompted segmentation, aiming to segment image regions corresponding to objects heard in an audio signal. Most existing approaches tackle this problem by fine-tuning pre-trained models or by training additional modules specifically for the task. We adopt a different strategy: we introduce a training-free approach that leverages Non-negative Matrix Factorization (NMF) to co-factorize audio and visu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01488","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/2412.01488/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":"2412.01488","created_at":"2026-07-05T11:09:44.255459+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01488v3","created_at":"2026-07-05T11:09:44.255459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01488","created_at":"2026-07-05T11:09:44.255459+00:00"},{"alias_kind":"pith_short_12","alias_value":"DEV5SXLHHCXG","created_at":"2026-07-05T11:09:44.255459+00:00"},{"alias_kind":"pith_short_16","alias_value":"DEV5SXLHHCXGH66L","created_at":"2026-07-05T11:09:44.255459+00:00"},{"alias_kind":"pith_short_8","alias_value":"DEV5SXLH","created_at":"2026-07-05T11:09:44.255459+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/DEV5SXLHHCXGH66LJROTG3W4XM","json":"https://pith.science/pith/DEV5SXLHHCXGH66LJROTG3W4XM.json","graph_json":"https://pith.science/api/pith-number/DEV5SXLHHCXGH66LJROTG3W4XM/graph.json","events_json":"https://pith.science/api/pith-number/DEV5SXLHHCXGH66LJROTG3W4XM/events.json","paper":"https://pith.science/paper/DEV5SXLH"},"agent_actions":{"view_html":"https://pith.science/pith/DEV5SXLHHCXGH66LJROTG3W4XM","download_json":"https://pith.science/pith/DEV5SXLHHCXGH66LJROTG3W4XM.json","view_paper":"https://pith.science/paper/DEV5SXLH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01488&json=true","fetch_graph":"https://pith.science/api/pith-number/DEV5SXLHHCXGH66LJROTG3W4XM/graph.json","fetch_events":"https://pith.science/api/pith-number/DEV5SXLHHCXGH66LJROTG3W4XM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DEV5SXLHHCXGH66LJROTG3W4XM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DEV5SXLHHCXGH66LJROTG3W4XM/action/storage_attestation","attest_author":"https://pith.science/pith/DEV5SXLHHCXGH66LJROTG3W4XM/action/author_attestation","sign_citation":"https://pith.science/pith/DEV5SXLHHCXGH66LJROTG3W4XM/action/citation_signature","submit_replication":"https://pith.science/pith/DEV5SXLHHCXGH66LJROTG3W4XM/action/replication_record"}},"created_at":"2026-07-05T11:09:44.255459+00:00","updated_at":"2026-07-05T11:09:44.255459+00:00"}