{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ID2LEUVHPZCXHOBKGQEDRZRGO5","short_pith_number":"pith:ID2LEUVH","schema_version":"1.0","canonical_sha256":"40f4b252a77e4573b82a340838e62677541c3109e8db002c46ae2128e74198c4","source":{"kind":"arxiv","id":"2310.11713","version":1},"attestation_state":"computed","paper":{"title":"Separating Invisible Sounds Toward Universal Audiovisual Scene-Aware Sound Separation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Ali Vosoughi, Chenliang Xu, Shijian Deng, Yapeng Tian, Yiyang Su","submitted_at":"2023-10-18T05:03:57Z","abstract_excerpt":"The audio-visual sound separation field assumes visible sources in videos, but this excludes invisible sounds beyond the camera's view. Current methods struggle with such sounds lacking visible cues. This paper introduces a novel \"Audio-Visual Scene-Aware Separation\" (AVSA-Sep) framework. It includes a semantic parser for visible and invisible sounds and a separator for scene-informed separation. AVSA-Sep successfully separates both sound types, with joint training and cross-modal alignment enhancing effectiveness."},"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":"2310.11713","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-18T05:03:57Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"fc98139977e21fdf5c95b9a96b6deca5f2045f75f31830ae9167a0639e39dac6","abstract_canon_sha256":"36810adec713e2ca94664a447f5918742da8a626866b274cec7dd734b69aa275"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:11.273136Z","signature_b64":"W9SbpN0vjkiWBkHLLruiSJyN5eHNxLtD9c2PT9ruYXEoruKBI95gbyR5IkSmVmjAHqmb2Ad+zq3nEyqrK3C8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40f4b252a77e4573b82a340838e62677541c3109e8db002c46ae2128e74198c4","last_reissued_at":"2026-07-05T07:02:11.272683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:11.272683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Separating Invisible Sounds Toward Universal Audiovisual Scene-Aware Sound Separation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Ali Vosoughi, Chenliang Xu, Shijian Deng, Yapeng Tian, Yiyang Su","submitted_at":"2023-10-18T05:03:57Z","abstract_excerpt":"The audio-visual sound separation field assumes visible sources in videos, but this excludes invisible sounds beyond the camera's view. Current methods struggle with such sounds lacking visible cues. This paper introduces a novel \"Audio-Visual Scene-Aware Separation\" (AVSA-Sep) framework. It includes a semantic parser for visible and invisible sounds and a separator for scene-informed separation. AVSA-Sep successfully separates both sound types, with joint training and cross-modal alignment enhancing effectiveness."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11713","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/2310.11713/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":"2310.11713","created_at":"2026-07-05T07:02:11.272740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.11713v1","created_at":"2026-07-05T07:02:11.272740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11713","created_at":"2026-07-05T07:02:11.272740+00:00"},{"alias_kind":"pith_short_12","alias_value":"ID2LEUVHPZCX","created_at":"2026-07-05T07:02:11.272740+00:00"},{"alias_kind":"pith_short_16","alias_value":"ID2LEUVHPZCXHOBK","created_at":"2026-07-05T07:02:11.272740+00:00"},{"alias_kind":"pith_short_8","alias_value":"ID2LEUVH","created_at":"2026-07-05T07:02:11.272740+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/ID2LEUVHPZCXHOBKGQEDRZRGO5","json":"https://pith.science/pith/ID2LEUVHPZCXHOBKGQEDRZRGO5.json","graph_json":"https://pith.science/api/pith-number/ID2LEUVHPZCXHOBKGQEDRZRGO5/graph.json","events_json":"https://pith.science/api/pith-number/ID2LEUVHPZCXHOBKGQEDRZRGO5/events.json","paper":"https://pith.science/paper/ID2LEUVH"},"agent_actions":{"view_html":"https://pith.science/pith/ID2LEUVHPZCXHOBKGQEDRZRGO5","download_json":"https://pith.science/pith/ID2LEUVHPZCXHOBKGQEDRZRGO5.json","view_paper":"https://pith.science/paper/ID2LEUVH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.11713&json=true","fetch_graph":"https://pith.science/api/pith-number/ID2LEUVHPZCXHOBKGQEDRZRGO5/graph.json","fetch_events":"https://pith.science/api/pith-number/ID2LEUVHPZCXHOBKGQEDRZRGO5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ID2LEUVHPZCXHOBKGQEDRZRGO5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ID2LEUVHPZCXHOBKGQEDRZRGO5/action/storage_attestation","attest_author":"https://pith.science/pith/ID2LEUVHPZCXHOBKGQEDRZRGO5/action/author_attestation","sign_citation":"https://pith.science/pith/ID2LEUVHPZCXHOBKGQEDRZRGO5/action/citation_signature","submit_replication":"https://pith.science/pith/ID2LEUVHPZCXHOBKGQEDRZRGO5/action/replication_record"}},"created_at":"2026-07-05T07:02:11.272740+00:00","updated_at":"2026-07-05T07:02:11.272740+00:00"}