{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SS4XUNYQF6KT2BNCKFOZA3JLVR","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":"27c74d880af043e76e7aa924ad0b96cd7d1dd90dcecc8a747b62275ca594d902","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-24T13:40:51Z","title_canon_sha256":"a3d8734244f07c76a433b3c236170e925afd14de53e2a5909ed7749a69883b3f"},"schema_version":"1.0","source":{"id":"2109.11955","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.11955","created_at":"2026-07-05T03:17:09Z"},{"alias_kind":"arxiv_version","alias_value":"2109.11955v1","created_at":"2026-07-05T03:17:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.11955","created_at":"2026-07-05T03:17:09Z"},{"alias_kind":"pith_short_12","alias_value":"SS4XUNYQF6KT","created_at":"2026-07-05T03:17:09Z"},{"alias_kind":"pith_short_16","alias_value":"SS4XUNYQF6KT2BNC","created_at":"2026-07-05T03:17:09Z"},{"alias_kind":"pith_short_8","alias_value":"SS4XUNYQ","created_at":"2026-07-05T03:17:09Z"}],"graph_snapshots":[{"event_id":"sha256:5193570b41271cd63339c30bd01415ab0ac55184be7dcbabbe58ff8b2d77ab13","target":"graph","created_at":"2026-07-05T03:17:09Z","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/2109.11955/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art approaches for visually-guided audio source separation typically assume sources that have characteristic sounds, such as musical instruments. These approaches often ignore the visual context of these sound sources or avoid modeling object interactions that may be useful to better characterize the sources, especially when the same object class may produce varied sounds from distinct interactions. To address this challenging problem, we propose Audio Visual Scene Graph Segmenter (AVSGS), a novel deep learning model that embeds the visual structure of the scene as a graph and seg","authors_text":"Anoop Cherian, Jonathan Le Roux, Moitreya Chatterjee, Narendra Ahuja","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-24T13:40:51Z","title":"Visual Scene Graphs for Audio Source Separation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.11955","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":"sha256:0162c84ed1cb742b618b18bc9b8d26bc93fc386b612565a8d2e3adced5c89549","target":"record","created_at":"2026-07-05T03:17:09Z","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":"27c74d880af043e76e7aa924ad0b96cd7d1dd90dcecc8a747b62275ca594d902","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-24T13:40:51Z","title_canon_sha256":"a3d8734244f07c76a433b3c236170e925afd14de53e2a5909ed7749a69883b3f"},"schema_version":"1.0","source":{"id":"2109.11955","kind":"arxiv","version":1}},"canonical_sha256":"94b97a37102f953d05a2515d906d2bac5285039457a9eba085d1a1c735e02736","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94b97a37102f953d05a2515d906d2bac5285039457a9eba085d1a1c735e02736","first_computed_at":"2026-07-05T03:17:09.266170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:17:09.266170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OKrxap/a0aNCNf9eLV0+tZtAKc5MutGAqo5dL0pK2kkGRdy9pVPtHGThIPSK8VDsxx9kkiYMUnJDM4YSldOJCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:17:09.266649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.11955","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0162c84ed1cb742b618b18bc9b8d26bc93fc386b612565a8d2e3adced5c89549","sha256:5193570b41271cd63339c30bd01415ab0ac55184be7dcbabbe58ff8b2d77ab13"],"state_sha256":"c0dd57a7711b7bc301b0f2a29001a34fa5eb778d95f0ab9fda6a42ab94413a60"}