{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MNTTDIYM6RO4YLQNZKKAV3AHQ2","short_pith_number":"pith:MNTTDIYM","schema_version":"1.0","canonical_sha256":"636731a30cf45dcc2e0dca940aec0786b5f9d66c5af800644127e4e9d407acdf","source":{"kind":"arxiv","id":"2303.16342","version":2},"attestation_state":"computed","paper":{"title":"Language-Guided Audio-Visual Source Separation via Trimodal Consistency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Andrea Burns, Arijit Ray, Bryan A. Plummer, Bryan Russell, Justin Salamon, Kate Saenko, Oriol Nieto, Reuben Tan","submitted_at":"2023-03-28T22:45:40Z","abstract_excerpt":"We propose a self-supervised approach for learning to perform audio source separation in videos based on natural language queries, using only unlabeled video and audio pairs as training data. A key challenge in this task is learning to associate the linguistic description of a sound-emitting object to its visual features and the corresponding components of the audio waveform, all without access to annotations during training. To overcome this challenge, we adapt off-the-shelf vision-language foundation models to provide pseudo-target supervision via two novel loss functions and encourage a str"},"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":"2303.16342","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-28T22:45:40Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e8582a7c7b083547543d2fcf9125c0ef2ae8b7afa84395997afb084130f289cc","abstract_canon_sha256":"e33f0789c7d9065f9e1ca18b71f56a195fa8eedf09a57e50a83f0cabd6890c96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:36.018498Z","signature_b64":"IjEKYwJh325Vm+mrTVmoxJRePViVNJHeFLqj4Yld4/oQJ5cn+PhzYLzLjb+mfVQkF2ANGT8HHzrIf6+ya2bKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"636731a30cf45dcc2e0dca940aec0786b5f9d66c5af800644127e4e9d407acdf","last_reissued_at":"2026-07-05T06:53:36.017941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:36.017941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language-Guided Audio-Visual Source Separation via Trimodal Consistency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Andrea Burns, Arijit Ray, Bryan A. Plummer, Bryan Russell, Justin Salamon, Kate Saenko, Oriol Nieto, Reuben Tan","submitted_at":"2023-03-28T22:45:40Z","abstract_excerpt":"We propose a self-supervised approach for learning to perform audio source separation in videos based on natural language queries, using only unlabeled video and audio pairs as training data. A key challenge in this task is learning to associate the linguistic description of a sound-emitting object to its visual features and the corresponding components of the audio waveform, all without access to annotations during training. To overcome this challenge, we adapt off-the-shelf vision-language foundation models to provide pseudo-target supervision via two novel loss functions and encourage a str"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16342","kind":"arxiv","version":2},"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/2303.16342/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":"2303.16342","created_at":"2026-07-05T06:53:36.018002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.16342v2","created_at":"2026-07-05T06:53:36.018002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16342","created_at":"2026-07-05T06:53:36.018002+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNTTDIYM6RO4","created_at":"2026-07-05T06:53:36.018002+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNTTDIYM6RO4YLQN","created_at":"2026-07-05T06:53:36.018002+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNTTDIYM","created_at":"2026-07-05T06:53:36.018002+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/MNTTDIYM6RO4YLQNZKKAV3AHQ2","json":"https://pith.science/pith/MNTTDIYM6RO4YLQNZKKAV3AHQ2.json","graph_json":"https://pith.science/api/pith-number/MNTTDIYM6RO4YLQNZKKAV3AHQ2/graph.json","events_json":"https://pith.science/api/pith-number/MNTTDIYM6RO4YLQNZKKAV3AHQ2/events.json","paper":"https://pith.science/paper/MNTTDIYM"},"agent_actions":{"view_html":"https://pith.science/pith/MNTTDIYM6RO4YLQNZKKAV3AHQ2","download_json":"https://pith.science/pith/MNTTDIYM6RO4YLQNZKKAV3AHQ2.json","view_paper":"https://pith.science/paper/MNTTDIYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.16342&json=true","fetch_graph":"https://pith.science/api/pith-number/MNTTDIYM6RO4YLQNZKKAV3AHQ2/graph.json","fetch_events":"https://pith.science/api/pith-number/MNTTDIYM6RO4YLQNZKKAV3AHQ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNTTDIYM6RO4YLQNZKKAV3AHQ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNTTDIYM6RO4YLQNZKKAV3AHQ2/action/storage_attestation","attest_author":"https://pith.science/pith/MNTTDIYM6RO4YLQNZKKAV3AHQ2/action/author_attestation","sign_citation":"https://pith.science/pith/MNTTDIYM6RO4YLQNZKKAV3AHQ2/action/citation_signature","submit_replication":"https://pith.science/pith/MNTTDIYM6RO4YLQNZKKAV3AHQ2/action/replication_record"}},"created_at":"2026-07-05T06:53:36.018002+00:00","updated_at":"2026-07-05T06:53:36.018002+00:00"}