{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:WF7ODPVMP65VNCE6VZ6GQQP6QD","short_pith_number":"pith:WF7ODPVM","canonical_record":{"source":{"id":"2211.01299","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-02T17:20:42Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"7bc40cdec83ea3e798481ef8647ba954662f86af24610d83dcb0a16b176e7741","abstract_canon_sha256":"5347009ab430e4d3fb057c2ef68a47d7ba4927fe2697d1e91026078c8137bc83"},"schema_version":"1.0"},"canonical_sha256":"b17ee1beac7fbb56889eae7c6841fe80c6574837b74a219783f40828d4366e28","source":{"kind":"arxiv","id":"2211.01299","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.01299","created_at":"2026-07-05T06:54:53Z"},{"alias_kind":"arxiv_version","alias_value":"2211.01299v2","created_at":"2026-07-05T06:54:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01299","created_at":"2026-07-05T06:54:53Z"},{"alias_kind":"pith_short_12","alias_value":"WF7ODPVMP65V","created_at":"2026-07-05T06:54:53Z"},{"alias_kind":"pith_short_16","alias_value":"WF7ODPVMP65VNCE6","created_at":"2026-07-05T06:54:53Z"},{"alias_kind":"pith_short_8","alias_value":"WF7ODPVM","created_at":"2026-07-05T06:54:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:WF7ODPVMP65VNCE6VZ6GQQP6QD","target":"record","payload":{"canonical_record":{"source":{"id":"2211.01299","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-02T17:20:42Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"7bc40cdec83ea3e798481ef8647ba954662f86af24610d83dcb0a16b176e7741","abstract_canon_sha256":"5347009ab430e4d3fb057c2ef68a47d7ba4927fe2697d1e91026078c8137bc83"},"schema_version":"1.0"},"canonical_sha256":"b17ee1beac7fbb56889eae7c6841fe80c6574837b74a219783f40828d4366e28","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:53.477399Z","signature_b64":"r6AFc0IvQaH3kRutW8nnTutIEejsW4tbHEFCl7NMZcE8akwvcVcTkUb1kYehAsfacb0pwjDEbZu0ynER62mPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b17ee1beac7fbb56889eae7c6841fe80c6574837b74a219783f40828d4366e28","last_reissued_at":"2026-07-05T06:54:53.476896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:53.476896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.01299","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":"2026-07-05T06:54:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FOW7Z+IMLdrbfIOqq9mO1600vHGpHvjs9roMRe43RF1nYg7qMz16DGaMryoUUuLV4aL1lOCNCpYll6SMdJLWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T03:27:42.314389Z"},"content_sha256":"e6699131d339037b819d799fcd433addb92138dae2aa44bc19b9161e05dd509c","schema_version":"1.0","event_id":"sha256:e6699131d339037b819d799fcd433addb92138dae2aa44bc19b9161e05dd509c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:WF7ODPVMP65VNCE6VZ6GQQP6QD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Late Audio-Visual Fusion for In-The-Wild Speaker Diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Aswin Subramanian, Fran\\c{c}ois G. Germain, Gordon Wichern, Jonathan Le Roux, Zexu Pan","submitted_at":"2022-11-02T17:20:42Z","abstract_excerpt":"Speaker diarization is well studied for constrained audios but little explored for challenging in-the-wild videos, which have more speakers, shorter utterances, and inconsistent on-screen speakers. We address this gap by proposing an audio-visual diarization model which combines audio-only and visual-centric sub-systems via late fusion. For audio, we show that an attractor-based end-to-end system (EEND-EDA) performs remarkably well when trained with our proposed recipe of a simulated proxy dataset, and propose an improved version, EEND-EDA++, that uses attention in decoding and a speaker recog"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01299","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/2211.01299/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":"2026-07-05T06:54:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SVWs5hxQWPnbp/tswje6SZ7V6jDWnYhLIFYjbpFIveIbCHXcU2e1gcjCWvFAv1676NUGrP1lR1dYFWiv9if+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T03:27:42.315166Z"},"content_sha256":"865b0a02c7af7726cc2415064649dd88793ba58126f11595482d7f208d36a283","schema_version":"1.0","event_id":"sha256:865b0a02c7af7726cc2415064649dd88793ba58126f11595482d7f208d36a283"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WF7ODPVMP65VNCE6VZ6GQQP6QD/bundle.json","state_url":"https://pith.science/pith/WF7ODPVMP65VNCE6VZ6GQQP6QD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WF7ODPVMP65VNCE6VZ6GQQP6QD/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":"2026-08-21T03:27:42Z","links":{"resolver":"https://pith.science/pith/WF7ODPVMP65VNCE6VZ6GQQP6QD","bundle":"https://pith.science/pith/WF7ODPVMP65VNCE6VZ6GQQP6QD/bundle.json","state":"https://pith.science/pith/WF7ODPVMP65VNCE6VZ6GQQP6QD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WF7ODPVMP65VNCE6VZ6GQQP6QD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WF7ODPVMP65VNCE6VZ6GQQP6QD","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":"5347009ab430e4d3fb057c2ef68a47d7ba4927fe2697d1e91026078c8137bc83","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-02T17:20:42Z","title_canon_sha256":"7bc40cdec83ea3e798481ef8647ba954662f86af24610d83dcb0a16b176e7741"},"schema_version":"1.0","source":{"id":"2211.01299","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.01299","created_at":"2026-07-05T06:54:53Z"},{"alias_kind":"arxiv_version","alias_value":"2211.01299v2","created_at":"2026-07-05T06:54:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01299","created_at":"2026-07-05T06:54:53Z"},{"alias_kind":"pith_short_12","alias_value":"WF7ODPVMP65V","created_at":"2026-07-05T06:54:53Z"},{"alias_kind":"pith_short_16","alias_value":"WF7ODPVMP65VNCE6","created_at":"2026-07-05T06:54:53Z"},{"alias_kind":"pith_short_8","alias_value":"WF7ODPVM","created_at":"2026-07-05T06:54:53Z"}],"graph_snapshots":[{"event_id":"sha256:865b0a02c7af7726cc2415064649dd88793ba58126f11595482d7f208d36a283","target":"graph","created_at":"2026-07-05T06:54:53Z","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/2211.01299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speaker diarization is well studied for constrained audios but little explored for challenging in-the-wild videos, which have more speakers, shorter utterances, and inconsistent on-screen speakers. We address this gap by proposing an audio-visual diarization model which combines audio-only and visual-centric sub-systems via late fusion. For audio, we show that an attractor-based end-to-end system (EEND-EDA) performs remarkably well when trained with our proposed recipe of a simulated proxy dataset, and propose an improved version, EEND-EDA++, that uses attention in decoding and a speaker recog","authors_text":"Aswin Subramanian, Fran\\c{c}ois G. Germain, Gordon Wichern, Jonathan Le Roux, Zexu Pan","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-02T17:20:42Z","title":"Late Audio-Visual Fusion for In-The-Wild Speaker Diarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01299","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:e6699131d339037b819d799fcd433addb92138dae2aa44bc19b9161e05dd509c","target":"record","created_at":"2026-07-05T06:54:53Z","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":"5347009ab430e4d3fb057c2ef68a47d7ba4927fe2697d1e91026078c8137bc83","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-02T17:20:42Z","title_canon_sha256":"7bc40cdec83ea3e798481ef8647ba954662f86af24610d83dcb0a16b176e7741"},"schema_version":"1.0","source":{"id":"2211.01299","kind":"arxiv","version":2}},"canonical_sha256":"b17ee1beac7fbb56889eae7c6841fe80c6574837b74a219783f40828d4366e28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b17ee1beac7fbb56889eae7c6841fe80c6574837b74a219783f40828d4366e28","first_computed_at":"2026-07-05T06:54:53.476896Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:54:53.476896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r6AFc0IvQaH3kRutW8nnTutIEejsW4tbHEFCl7NMZcE8akwvcVcTkUb1kYehAsfacb0pwjDEbZu0ynER62mPDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:54:53.477399Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.01299","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6699131d339037b819d799fcd433addb92138dae2aa44bc19b9161e05dd509c","sha256:865b0a02c7af7726cc2415064649dd88793ba58126f11595482d7f208d36a283"],"state_sha256":"1081922842bb57e3c942bbcb68745e1a70a8cc76c54231fea66d3f3a4e39f8a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J+xKSeYgS+5hkoSEh9JOmQLQonbxUqVJCP0YNjpYy8me2p3F04YQ81c10JETtvdLFCDsccqzQ6uASCa91oQnBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T03:27:42.321024Z","bundle_sha256":"516f12e9538069b664748438e47aa995a628cfa8401ff7a28ed4fd6a04775a41"}}