{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:VJCHGT4BI4KCPAPXX4NDDQLOE4","short_pith_number":"pith:VJCHGT4B","canonical_record":{"source":{"id":"1603.09725","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-31T19:15:01Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"f2b98952e22cfeaedbe03984ec6f238fc6dfbb5f9df5d5e3dd0edefbe5bdaa06","abstract_canon_sha256":"4515f53cc8425ef5c9a40d50a8df83cb5558c1ecb0dd246513e73cd9131e9483"},"schema_version":"1.0"},"canonical_sha256":"aa44734f8147142781f7bf1a31c16e2714bd03b70b54143a144c57e2087658b7","source":{"kind":"arxiv","id":"1603.09725","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.09725","created_at":"2026-05-18T00:03:34Z"},{"alias_kind":"arxiv_version","alias_value":"1603.09725v2","created_at":"2026-05-18T00:03:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.09725","created_at":"2026-05-18T00:03:34Z"},{"alias_kind":"pith_short_12","alias_value":"VJCHGT4BI4KC","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"VJCHGT4BI4KCPAPX","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"VJCHGT4B","created_at":"2026-05-18T12:30:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:VJCHGT4BI4KCPAPXX4NDDQLOE4","target":"record","payload":{"canonical_record":{"source":{"id":"1603.09725","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-31T19:15:01Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"f2b98952e22cfeaedbe03984ec6f238fc6dfbb5f9df5d5e3dd0edefbe5bdaa06","abstract_canon_sha256":"4515f53cc8425ef5c9a40d50a8df83cb5558c1ecb0dd246513e73cd9131e9483"},"schema_version":"1.0"},"canonical_sha256":"aa44734f8147142781f7bf1a31c16e2714bd03b70b54143a144c57e2087658b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:34.573997Z","signature_b64":"ILKldOrSPVrKCFx0NWV2woU0ciyGlUYr71SNu4fb4Xc8LA/D28LldYbIBntvcSN5btrkEza4MJyEKKq1OJSmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa44734f8147142781f7bf1a31c16e2714bd03b70b54143a144c57e2087658b7","last_reissued_at":"2026-05-18T00:03:34.573586Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:34.573586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1603.09725","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":"2026-05-18T00:03:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2SwcSSJmSPbwcunfo0udycx6a/GL7XaZgIYoeA4SO1bDofn5OD8lk8Zi8gL15FOuTp/Ej46qElzIkhJZzCdjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T13:32:44.635096Z"},"content_sha256":"7ec06081e602a709bfc5850bdafe56e1516c5896f6a2cd9626a31a603687319d","schema_version":"1.0","event_id":"sha256:7ec06081e602a709bfc5850bdafe56e1516c5896f6a2cd9626a31a603687319d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:VJCHGT4BI4KCPAPXX4NDDQLOE4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Audio-Visual Speaker Diarization Based on Spatiotemporal Bayesian Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.CV","authors_text":"Israel D. Gebru, Radu Horaud, Sil\\`eye Ba, Xiaofei Li","submitted_at":"2016-03-31T19:15:01Z","abstract_excerpt":"Speaker diarization consists of assigning speech signals to people engaged in a dialogue. An audio-visual spatiotemporal diarization model is proposed. The model is well suited for challenging scenarios that consist of several participants engaged in multi-party interaction while they move around and turn their heads towards the other participants rather than facing the cameras and the microphones. Multiple-person visual tracking is combined with multiple speech-source localization in order to tackle the speech-to-person association problem. The latter is solved within a novel audio-visual fus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.09725","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":""},"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":"2026-05-18T00:03:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"27MjbT3GwV61ck4gsaIiGSLfgkFxhH2AjyJdQhNrIRCQrGnGHtTZisdshuCfDySpdNeE7yADS2HMsfVzHMcGDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T13:32:44.635470Z"},"content_sha256":"5e2fae0771777dcfa93a3145b5892717562a83a138a54932d8ff6a4e9abb0565","schema_version":"1.0","event_id":"sha256:5e2fae0771777dcfa93a3145b5892717562a83a138a54932d8ff6a4e9abb0565"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VJCHGT4BI4KCPAPXX4NDDQLOE4/bundle.json","state_url":"https://pith.science/pith/VJCHGT4BI4KCPAPXX4NDDQLOE4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VJCHGT4BI4KCPAPXX4NDDQLOE4/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":"2026-06-22T13:32:44Z","links":{"resolver":"https://pith.science/pith/VJCHGT4BI4KCPAPXX4NDDQLOE4","bundle":"https://pith.science/pith/VJCHGT4BI4KCPAPXX4NDDQLOE4/bundle.json","state":"https://pith.science/pith/VJCHGT4BI4KCPAPXX4NDDQLOE4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VJCHGT4BI4KCPAPXX4NDDQLOE4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:VJCHGT4BI4KCPAPXX4NDDQLOE4","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":"4515f53cc8425ef5c9a40d50a8df83cb5558c1ecb0dd246513e73cd9131e9483","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-31T19:15:01Z","title_canon_sha256":"f2b98952e22cfeaedbe03984ec6f238fc6dfbb5f9df5d5e3dd0edefbe5bdaa06"},"schema_version":"1.0","source":{"id":"1603.09725","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.09725","created_at":"2026-05-18T00:03:34Z"},{"alias_kind":"arxiv_version","alias_value":"1603.09725v2","created_at":"2026-05-18T00:03:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.09725","created_at":"2026-05-18T00:03:34Z"},{"alias_kind":"pith_short_12","alias_value":"VJCHGT4BI4KC","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"VJCHGT4BI4KCPAPX","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"VJCHGT4B","created_at":"2026-05-18T12:30:48Z"}],"graph_snapshots":[{"event_id":"sha256:5e2fae0771777dcfa93a3145b5892717562a83a138a54932d8ff6a4e9abb0565","target":"graph","created_at":"2026-05-18T00:03:34Z","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"},"paper":{"abstract_excerpt":"Speaker diarization consists of assigning speech signals to people engaged in a dialogue. An audio-visual spatiotemporal diarization model is proposed. The model is well suited for challenging scenarios that consist of several participants engaged in multi-party interaction while they move around and turn their heads towards the other participants rather than facing the cameras and the microphones. Multiple-person visual tracking is combined with multiple speech-source localization in order to tackle the speech-to-person association problem. The latter is solved within a novel audio-visual fus","authors_text":"Israel D. Gebru, Radu Horaud, Sil\\`eye Ba, Xiaofei Li","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-31T19:15:01Z","title":"Audio-Visual Speaker Diarization Based on Spatiotemporal Bayesian Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.09725","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":"sha256:7ec06081e602a709bfc5850bdafe56e1516c5896f6a2cd9626a31a603687319d","target":"record","created_at":"2026-05-18T00:03:34Z","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":"4515f53cc8425ef5c9a40d50a8df83cb5558c1ecb0dd246513e73cd9131e9483","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-31T19:15:01Z","title_canon_sha256":"f2b98952e22cfeaedbe03984ec6f238fc6dfbb5f9df5d5e3dd0edefbe5bdaa06"},"schema_version":"1.0","source":{"id":"1603.09725","kind":"arxiv","version":2}},"canonical_sha256":"aa44734f8147142781f7bf1a31c16e2714bd03b70b54143a144c57e2087658b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa44734f8147142781f7bf1a31c16e2714bd03b70b54143a144c57e2087658b7","first_computed_at":"2026-05-18T00:03:34.573586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:34.573586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ILKldOrSPVrKCFx0NWV2woU0ciyGlUYr71SNu4fb4Xc8LA/D28LldYbIBntvcSN5btrkEza4MJyEKKq1OJSmBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:34.573997Z","signed_message":"canonical_sha256_bytes"},"source_id":"1603.09725","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ec06081e602a709bfc5850bdafe56e1516c5896f6a2cd9626a31a603687319d","sha256:5e2fae0771777dcfa93a3145b5892717562a83a138a54932d8ff6a4e9abb0565"],"state_sha256":"c19dd7705e1d20585cc87a43afeb1d30a3eeb214c24b177617f482a4d1405468"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"08sHig4FuIzu/QM1AuSnCXsr/JQ4AKnsd/e6G6O0tyPAU3u+NZuotf6nNF1Qxqx4NFVWZSgYRdHsLglQ3sMADQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-22T13:32:44.637415Z","bundle_sha256":"4ecaee998406651aea5b56fcd5fc63e9719f0c809e6db3294164f99f1899b8e7"}}