{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:YCR37XI7SNNTWFP2NLGKLN3EOM","short_pith_number":"pith:YCR37XI7","canonical_record":{"source":{"id":"2011.01143","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-11-02T17:36:13Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"380ee062b36c5a50fb1684cbc0f7e3fc0b0ee779c17068e1b91f2d1a61ceeefe","abstract_canon_sha256":"abcf62ea0d9263f16f787b57e3456e896fe2201c463f9574b8321c8f0a474591"},"schema_version":"1.0"},"canonical_sha256":"c0a3bfdd1f935b3b15fa6acca5b7647300f8ddfac785a8f0fb6c887cbabc0ab3","source":{"kind":"arxiv","id":"2011.01143","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.01143","created_at":"2026-07-05T02:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2011.01143v2","created_at":"2026-07-05T02:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01143","created_at":"2026-07-05T02:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"YCR37XI7SNNT","created_at":"2026-07-05T02:44:16Z"},{"alias_kind":"pith_short_16","alias_value":"YCR37XI7SNNTWFP2","created_at":"2026-07-05T02:44:16Z"},{"alias_kind":"pith_short_8","alias_value":"YCR37XI7","created_at":"2026-07-05T02:44:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:YCR37XI7SNNTWFP2NLGKLN3EOM","target":"record","payload":{"canonical_record":{"source":{"id":"2011.01143","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-11-02T17:36:13Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"380ee062b36c5a50fb1684cbc0f7e3fc0b0ee779c17068e1b91f2d1a61ceeefe","abstract_canon_sha256":"abcf62ea0d9263f16f787b57e3456e896fe2201c463f9574b8321c8f0a474591"},"schema_version":"1.0"},"canonical_sha256":"c0a3bfdd1f935b3b15fa6acca5b7647300f8ddfac785a8f0fb6c887cbabc0ab3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:16.404086Z","signature_b64":"UkaoD7BnDo/TlzpXWkDb/JxVMfcyR3Q9WNVLbo8EdoLQFwxHrIvQL5y+1HsxqZBgr8chCKMWfHQrj0EZNn2wDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0a3bfdd1f935b3b15fa6acca5b7647300f8ddfac785a8f0fb6c887cbabc0ab3","last_reissued_at":"2026-07-05T02:44:16.403617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:16.403617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.01143","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AVoYkafG5j9QITDVy3VeOaa1dPykhKW5RBnWKlDj8q1C1f655SrkbLDAJNUIELzwOHJ5Zkc3WlgIdPvQ9uIlBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:11:29.183606Z"},"content_sha256":"fbc8263cf02906de03d2ab904e71352e0061732e3f15e74f2d3887132745794f","schema_version":"1.0","event_id":"sha256:fbc8263cf02906de03d2ab904e71352e0061732e3f15e74f2d3887132745794f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:YCR37XI7SNNTWFP2NLGKLN3EOM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aren Jansen, Daniel P. W. Ellis, Efthymios Tzinis, John R. Hershey, Scott Wisdom, Shawn Hershey, Tal Remez","submitted_at":"2020-11-02T17:36:13Z","abstract_excerpt":"Recent progress in deep learning has enabled many advances in sound separation and visual scene understanding. However, extracting sound sources which are apparent in natural videos remains an open problem. In this work, we present AudioScope, a novel audio-visual sound separation framework that can be trained without supervision to isolate on-screen sound sources from real in-the-wild videos. Prior audio-visual separation work assumed artificial limitations on the domain of sound classes (e.g., to speech or music), constrained the number of sources, and required strong sound separation or vis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01143","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/2011.01143/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oWvb6/V0TXCzQmEiWNztK779S2XLFDsevlcKQ//Y2nGECFql76hKiNZnkMXkCCrBuEqLVR6mBCxy35gqsAkHCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:11:29.185229Z"},"content_sha256":"b143d2a9c45e051d36daefd7cafa5b71b4cdbb96102846ceb12343e4b143ce72","schema_version":"1.0","event_id":"sha256:b143d2a9c45e051d36daefd7cafa5b71b4cdbb96102846ceb12343e4b143ce72"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YCR37XI7SNNTWFP2NLGKLN3EOM/bundle.json","state_url":"https://pith.science/pith/YCR37XI7SNNTWFP2NLGKLN3EOM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YCR37XI7SNNTWFP2NLGKLN3EOM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T23:11:29Z","links":{"resolver":"https://pith.science/pith/YCR37XI7SNNTWFP2NLGKLN3EOM","bundle":"https://pith.science/pith/YCR37XI7SNNTWFP2NLGKLN3EOM/bundle.json","state":"https://pith.science/pith/YCR37XI7SNNTWFP2NLGKLN3EOM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YCR37XI7SNNTWFP2NLGKLN3EOM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:YCR37XI7SNNTWFP2NLGKLN3EOM","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":"abcf62ea0d9263f16f787b57e3456e896fe2201c463f9574b8321c8f0a474591","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-11-02T17:36:13Z","title_canon_sha256":"380ee062b36c5a50fb1684cbc0f7e3fc0b0ee779c17068e1b91f2d1a61ceeefe"},"schema_version":"1.0","source":{"id":"2011.01143","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.01143","created_at":"2026-07-05T02:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2011.01143v2","created_at":"2026-07-05T02:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01143","created_at":"2026-07-05T02:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"YCR37XI7SNNT","created_at":"2026-07-05T02:44:16Z"},{"alias_kind":"pith_short_16","alias_value":"YCR37XI7SNNTWFP2","created_at":"2026-07-05T02:44:16Z"},{"alias_kind":"pith_short_8","alias_value":"YCR37XI7","created_at":"2026-07-05T02:44:16Z"}],"graph_snapshots":[{"event_id":"sha256:b143d2a9c45e051d36daefd7cafa5b71b4cdbb96102846ceb12343e4b143ce72","target":"graph","created_at":"2026-07-05T02:44:16Z","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/2011.01143/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent progress in deep learning has enabled many advances in sound separation and visual scene understanding. However, extracting sound sources which are apparent in natural videos remains an open problem. In this work, we present AudioScope, a novel audio-visual sound separation framework that can be trained without supervision to isolate on-screen sound sources from real in-the-wild videos. Prior audio-visual separation work assumed artificial limitations on the domain of sound classes (e.g., to speech or music), constrained the number of sources, and required strong sound separation or vis","authors_text":"Aren Jansen, Daniel P. W. Ellis, Efthymios Tzinis, John R. Hershey, Scott Wisdom, Shawn Hershey, Tal Remez","cross_cats":["cs.CV","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-11-02T17:36:13Z","title":"Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01143","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:fbc8263cf02906de03d2ab904e71352e0061732e3f15e74f2d3887132745794f","target":"record","created_at":"2026-07-05T02:44:16Z","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":"abcf62ea0d9263f16f787b57e3456e896fe2201c463f9574b8321c8f0a474591","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-11-02T17:36:13Z","title_canon_sha256":"380ee062b36c5a50fb1684cbc0f7e3fc0b0ee779c17068e1b91f2d1a61ceeefe"},"schema_version":"1.0","source":{"id":"2011.01143","kind":"arxiv","version":2}},"canonical_sha256":"c0a3bfdd1f935b3b15fa6acca5b7647300f8ddfac785a8f0fb6c887cbabc0ab3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0a3bfdd1f935b3b15fa6acca5b7647300f8ddfac785a8f0fb6c887cbabc0ab3","first_computed_at":"2026-07-05T02:44:16.403617Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:44:16.403617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UkaoD7BnDo/TlzpXWkDb/JxVMfcyR3Q9WNVLbo8EdoLQFwxHrIvQL5y+1HsxqZBgr8chCKMWfHQrj0EZNn2wDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:44:16.404086Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.01143","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fbc8263cf02906de03d2ab904e71352e0061732e3f15e74f2d3887132745794f","sha256:b143d2a9c45e051d36daefd7cafa5b71b4cdbb96102846ceb12343e4b143ce72"],"state_sha256":"41cfb45922a69eacbd251bfe05ed63d1fcd17e21f58ad342b3f001e4197cbd42"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fe5GakSof3kcG26CsaWXy+eCne6V/dO80dchn3IXNLoNKbDZOUnOXyY+9ZYRgEIohOcuB5tAdOiARwMR+yLUAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T23:11:29.194575Z","bundle_sha256":"9e4c6abd2b0c7b31f33b34529bfa9e917178938b28f819cbbbdee87957bf5f00"}}