{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DEV5SXLHHCXGH66LJROTG3W4XM","short_pith_number":"pith:DEV5SXLH","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"},"canonical_sha256":"192bd95d6738ae63fbcb4c5d336edcbb05c8644583ed33186b78831a1a504327","source":{"kind":"arxiv","id":"2412.01488","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01488","created_at":"2026-07-05T11:09:44Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01488v3","created_at":"2026-07-05T11:09:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01488","created_at":"2026-07-05T11:09:44Z"},{"alias_kind":"pith_short_12","alias_value":"DEV5SXLHHCXG","created_at":"2026-07-05T11:09:44Z"},{"alias_kind":"pith_short_16","alias_value":"DEV5SXLHHCXGH66L","created_at":"2026-07-05T11:09:44Z"},{"alias_kind":"pith_short_8","alias_value":"DEV5SXLH","created_at":"2026-07-05T11:09:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DEV5SXLHHCXGH66LJROTG3W4XM","target":"record","payload":{"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"},"canonical_sha256":"192bd95d6738ae63fbcb4c5d336edcbb05c8644583ed33186b78831a1a504327","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"},"source_kind":"arxiv","source_id":"2412.01488","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gipH7uHP5Vr1dq5VOLf7OtD98B73FKaceRRHPCO3FVl2ZLFUQOr0q3fdsm2SrWIH6UX1Vrbl6dIFFkmWoPnaAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:58:36.860601Z"},"content_sha256":"6034fb1679df9b6cf7199a64c34c628e0b358f8d81e09e17693a0ef76725d118","schema_version":"1.0","event_id":"sha256:6034fb1679df9b6cf7199a64c34c628e0b358f8d81e09e17693a0ef76725d118"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DEV5SXLHHCXGH66LJROTG3W4XM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"80bc9Xet1gL+YSf0dyVpZGuiH+U5brAU90UaGKFqhF23pUKi/z1HdybvIbgdAbmeHL9jDD3ty/VKHd6YEd6/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:58:36.861618Z"},"content_sha256":"b6d95a650f2ae0700c9524c9863b4f0ab7a736f795c7b43f1da253b23b96ff69","schema_version":"1.0","event_id":"sha256:b6d95a650f2ae0700c9524c9863b4f0ab7a736f795c7b43f1da253b23b96ff69"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DEV5SXLHHCXGH66LJROTG3W4XM/bundle.json","state_url":"https://pith.science/pith/DEV5SXLHHCXGH66LJROTG3W4XM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DEV5SXLHHCXGH66LJROTG3W4XM/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":"2026-08-19T12:58:36Z","links":{"resolver":"https://pith.science/pith/DEV5SXLHHCXGH66LJROTG3W4XM","bundle":"https://pith.science/pith/DEV5SXLHHCXGH66LJROTG3W4XM/bundle.json","state":"https://pith.science/pith/DEV5SXLHHCXGH66LJROTG3W4XM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DEV5SXLHHCXGH66LJROTG3W4XM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DEV5SXLHHCXGH66LJROTG3W4XM","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":"96b18bf4d0d3eaf76adf66e3727435efd428e4e1e55cb2f371ce9a9bc3af6060","cross_cats_sorted":["cs.LG","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-02T13:39:49Z","title_canon_sha256":"46258e06c969d5621c99aca71e253ef5962d5fcce939f14befad657ed4482278"},"schema_version":"1.0","source":{"id":"2412.01488","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01488","created_at":"2026-07-05T11:09:44Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01488v3","created_at":"2026-07-05T11:09:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01488","created_at":"2026-07-05T11:09:44Z"},{"alias_kind":"pith_short_12","alias_value":"DEV5SXLHHCXG","created_at":"2026-07-05T11:09:44Z"},{"alias_kind":"pith_short_16","alias_value":"DEV5SXLHHCXGH66L","created_at":"2026-07-05T11:09:44Z"},{"alias_kind":"pith_short_8","alias_value":"DEV5SXLH","created_at":"2026-07-05T11:09:44Z"}],"graph_snapshots":[{"event_id":"sha256:b6d95a650f2ae0700c9524c9863b4f0ab7a736f795c7b43f1da253b23b96ff69","target":"graph","created_at":"2026-07-05T11:09:44Z","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/2412.01488/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hugo Malard, Michel Olvera, Slim Essid, Stephane Lathuiliere","cross_cats":["cs.LG","eess.IV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-02T13:39:49Z","title":"TACO: Training-free Sound Prompted Segmentation via Semantically Constrained Audio-visual CO-factorization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01488","kind":"arxiv","version":3},"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":"sha256:6034fb1679df9b6cf7199a64c34c628e0b358f8d81e09e17693a0ef76725d118","target":"record","created_at":"2026-07-05T11:09:44Z","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":"96b18bf4d0d3eaf76adf66e3727435efd428e4e1e55cb2f371ce9a9bc3af6060","cross_cats_sorted":["cs.LG","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-02T13:39:49Z","title_canon_sha256":"46258e06c969d5621c99aca71e253ef5962d5fcce939f14befad657ed4482278"},"schema_version":"1.0","source":{"id":"2412.01488","kind":"arxiv","version":3}},"canonical_sha256":"192bd95d6738ae63fbcb4c5d336edcbb05c8644583ed33186b78831a1a504327","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"192bd95d6738ae63fbcb4c5d336edcbb05c8644583ed33186b78831a1a504327","first_computed_at":"2026-07-05T11:09:44.255398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:44.255398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T9tuCJFepgWbIlc3dTYbsHxs6W1SUVKExxzb6++mgySkmakVnMoq6Ryc/bSS5Azs/eXOOCbkYwRxCtg/cYyoBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:44.255895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01488","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6034fb1679df9b6cf7199a64c34c628e0b358f8d81e09e17693a0ef76725d118","sha256:b6d95a650f2ae0700c9524c9863b4f0ab7a736f795c7b43f1da253b23b96ff69"],"state_sha256":"9b11298c42f4748166fae2fffe63e06f668a23ea8eddd874a745a49c81cbbf05"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bgmBsUYlc/oGSDCnKP7R8rvCYuiieRXWYvqi2lvPO/YNT5aEprumKCl9AS1QF9f6K1RXfJOqXSkfRU2rBTtBBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T12:58:36.870271Z","bundle_sha256":"dfc8fc6895c8f678d118c3255467ed46ba305352448056ba83306766a4593965"}}