{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZMBT7GWMHPOKCXRCO6FA3U3CPS","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":"5f7f6763bbb3c7065a1d34e25102d5a0acc0db92e95507ac504b414408cf9a1e","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-07-20T18:44:01Z","title_canon_sha256":"50f77fbf8cd77c58264e9aecceb41765a25c51e369e2f7607c8e250894a49f33"},"schema_version":"1.0","source":{"id":"2207.10141","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.10141","created_at":"2026-07-05T04:42:21Z"},{"alias_kind":"arxiv_version","alias_value":"2207.10141v1","created_at":"2026-07-05T04:42:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.10141","created_at":"2026-07-05T04:42:21Z"},{"alias_kind":"pith_short_12","alias_value":"ZMBT7GWMHPOK","created_at":"2026-07-05T04:42:21Z"},{"alias_kind":"pith_short_16","alias_value":"ZMBT7GWMHPOKCXRC","created_at":"2026-07-05T04:42:21Z"},{"alias_kind":"pith_short_8","alias_value":"ZMBT7GWM","created_at":"2026-07-05T04:42:21Z"}],"graph_snapshots":[{"event_id":"sha256:0e4887ebf91dd956449e0d86aae05862b84aa992eb0181b616b2c22221fad1f8","target":"graph","created_at":"2026-07-05T04:42:21Z","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/2207.10141/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce AudioScopeV2, a state-of-the-art universal 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 several limitations of previous work on audio-visual on-screen sound separation, including the coarse resolution of spatio-temporal attention, poor convergence of the audio separation model, limited variety in training and evaluation data, and failure to account for the trade off between preservation of on-screen sounds and suppression of off-screen sounds. W","authors_text":"Efthymios Tzinis, John R. Hershey, Scott Wisdom, Tal Remez","cross_cats":["cs.CV","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-07-20T18:44:01Z","title":"AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.10141","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":"sha256:8ce147b2958092b4da3594d9450b790977c7540d6d5731c7cc4fe83c54a721d9","target":"record","created_at":"2026-07-05T04:42:21Z","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":"5f7f6763bbb3c7065a1d34e25102d5a0acc0db92e95507ac504b414408cf9a1e","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-07-20T18:44:01Z","title_canon_sha256":"50f77fbf8cd77c58264e9aecceb41765a25c51e369e2f7607c8e250894a49f33"},"schema_version":"1.0","source":{"id":"2207.10141","kind":"arxiv","version":1}},"canonical_sha256":"cb033f9acc3bdca15e22778a0dd3627c892675687eeedc15caacf0eb6d019bf2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb033f9acc3bdca15e22778a0dd3627c892675687eeedc15caacf0eb6d019bf2","first_computed_at":"2026-07-05T04:42:21.497240Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:42:21.497240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2rTZ/tqJUH32qsRG35rT69Vpj1P3Smm/WeD1tKTjdQBO5Uj0nkgt2VDorniFYFxCGKNs/jJHcrsNcrGmKtbVCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:42:21.497733Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.10141","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ce147b2958092b4da3594d9450b790977c7540d6d5731c7cc4fe83c54a721d9","sha256:0e4887ebf91dd956449e0d86aae05862b84aa992eb0181b616b2c22221fad1f8"],"state_sha256":"318a8a95ab10cd3236bf9f4ec0e21410b3ca3336c55e0c57742e4a217381ce53"}