{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NZH3IASXMCBG6YXCSYZNJ3F7FV","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":"95ab772a6692831f5ac5eeeadd222b8730cbf6956140d5fc904e24c7e116e5a4","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-06-17T17:23:44Z","title_canon_sha256":"97d1b2b4f32a95a0118dcd54b795245a643447f572708e70c78b0913959416b5"},"schema_version":"1.0","source":{"id":"2106.09669","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.09669","created_at":"2026-07-05T03:22:35Z"},{"alias_kind":"arxiv_version","alias_value":"2106.09669v2","created_at":"2026-07-05T03:22:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09669","created_at":"2026-07-05T03:22:35Z"},{"alias_kind":"pith_short_12","alias_value":"NZH3IASXMCBG","created_at":"2026-07-05T03:22:35Z"},{"alias_kind":"pith_short_16","alias_value":"NZH3IASXMCBG6YXC","created_at":"2026-07-05T03:22:35Z"},{"alias_kind":"pith_short_8","alias_value":"NZH3IASX","created_at":"2026-07-05T03:22:35Z"}],"graph_snapshots":[{"event_id":"sha256:d5439b37486c7215ca2e2f6cbdca85d7468f8b8624c447f32cd9fe61c281cd3d","target":"graph","created_at":"2026-07-05T03:22:35Z","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/2106.09669/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a state-of-the-art audio-visual on-screen sound separation system which is capable of learning to separate sounds and associate them with on-screen objects by looking at in-the-wild videos. We identify limitations of previous work on audio-visual on-screen sound separation, including the simplicity and coarse resolution of spatio-temporal attention, and poor convergence of the audio separation model. Our proposed model addresses these issues using cross-modal and self-attention modules that capture audio-visual dependencies at a finer resolution over time, and by unsupervised pre-","authors_text":"Efthymios Tzinis, John R. Hershey, Scott Wisdom, Tal Remez","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-06-17T17:23:44Z","title":"Improving On-Screen Sound Separation for Open-Domain Videos with Audio-Visual Self-Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09669","kind":"arxiv","version":2},"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":"sha256:0323a055dcefdeb8f10f89e4731f792c4b96b9f7189117cb459b0064c252b198","target":"record","created_at":"2026-07-05T03:22:35Z","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":"95ab772a6692831f5ac5eeeadd222b8730cbf6956140d5fc904e24c7e116e5a4","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-06-17T17:23:44Z","title_canon_sha256":"97d1b2b4f32a95a0118dcd54b795245a643447f572708e70c78b0913959416b5"},"schema_version":"1.0","source":{"id":"2106.09669","kind":"arxiv","version":2}},"canonical_sha256":"6e4fb4025760826f62e29632d4ecbf2d7dc82c0a1a9f8659b50756e0c925b315","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e4fb4025760826f62e29632d4ecbf2d7dc82c0a1a9f8659b50756e0c925b315","first_computed_at":"2026-07-05T03:22:35.487727Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:35.487727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6dZHyJzspXED/ZNjzJtkq0DnJz+lMO1/OTwGTP3mcFyBLeGolasmfSJvMZxbMlp7uORUJJYzJDqt1WwV74HdAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:35.488184Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.09669","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0323a055dcefdeb8f10f89e4731f792c4b96b9f7189117cb459b0064c252b198","sha256:d5439b37486c7215ca2e2f6cbdca85d7468f8b8624c447f32cd9fe61c281cd3d"],"state_sha256":"fe95d8c54746909aba9886b40e7e9a8fdc155384619a2ad6f434298eb934ba90"}