{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:NIWJHI77DI2WZO5R3JYCIYIH57","short_pith_number":"pith:NIWJHI77","canonical_record":{"source":{"id":"1906.10042","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-06-24T16:06:13Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"4a4d362ce3f768983dcb35cc3e6ac2f5c9c6fa0928b6ba7af91f841f9e72198c","abstract_canon_sha256":"b022a3c6b5b4b7d2dbbe296259ca4103f36a26e72d9dac1a1dd5b891f1124438"},"schema_version":"1.0"},"canonical_sha256":"6a2c93a3ff1a356cbbb1da70246107effd1b915f9aff78533c03129d88317dff","source":{"kind":"arxiv","id":"1906.10042","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.10042","created_at":"2026-05-17T23:42:35Z"},{"alias_kind":"arxiv_version","alias_value":"1906.10042v1","created_at":"2026-05-17T23:42:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10042","created_at":"2026-05-17T23:42:35Z"},{"alias_kind":"pith_short_12","alias_value":"NIWJHI77DI2W","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NIWJHI77DI2WZO5R","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NIWJHI77","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:NIWJHI77DI2WZO5R3JYCIYIH57","target":"record","payload":{"canonical_record":{"source":{"id":"1906.10042","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-06-24T16:06:13Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"4a4d362ce3f768983dcb35cc3e6ac2f5c9c6fa0928b6ba7af91f841f9e72198c","abstract_canon_sha256":"b022a3c6b5b4b7d2dbbe296259ca4103f36a26e72d9dac1a1dd5b891f1124438"},"schema_version":"1.0"},"canonical_sha256":"6a2c93a3ff1a356cbbb1da70246107effd1b915f9aff78533c03129d88317dff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:35.642085Z","signature_b64":"BgRB2MIkFE7490FaXvoZaKl7dR3Q3RWnzuzlY0nORPfYs6+oZ+ZBzEC4MNUtB1Ndcye5hT+3l8duGx3YmmL7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a2c93a3ff1a356cbbb1da70246107effd1b915f9aff78533c03129d88317dff","last_reissued_at":"2026-05-17T23:42:35.641424Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:35.641424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.10042","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cni016Okzv/raR2Xax5uIgIJLPtB1DtsdLIMwJPAiajV0nSoUC2ib9z5F8YhPjav/cbcNIiPELPkqFtl6U1cAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T10:43:02.021110Z"},"content_sha256":"a3960a0e0344473232e0e7308043a00d22bfdd47562820f53401dca42e49b180","schema_version":"1.0","event_id":"sha256:a3960a0e0344473232e0e7308043a00d22bfdd47562820f53401dca42e49b180"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:NIWJHI77DI2WZO5R3JYCIYIH57","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Who said that?: Audio-visual speaker diarisation of real-world meetings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bong-Jin Lee, Icksang Han, Joon Son Chung","submitted_at":"2019-06-24T16:06:13Z","abstract_excerpt":"The goal of this work is to determine 'who spoke when' in real-world meetings. The method takes surround-view video and single or multi-channel audio as inputs, and generates robust diarisation outputs. To achieve this, we propose a novel iterative approach that first enrolls speaker models using audio-visual correspondence, then uses the enrolled models together with the visual information to determine the active speaker. We show strong quantitative and qualitative performance on a dataset of real-world meetings. The method is also evaluated on the public AMI meeting corpus, on which we demon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10042","kind":"arxiv","version":1},"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":"2026-05-17T23:42:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r8bC0DfpoWmXJ2wpmG1pBkRKKbZbzvBYWGYPd0iPvNu/hgRIu8xOVuR9oLpl8hOEj1GAtTi6bxEVBqaOxw64Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T10:43:02.021791Z"},"content_sha256":"90ae197856a75a53b3e096c5f1a5f7c56b093052cfcfcd03b240f04d86290b44","schema_version":"1.0","event_id":"sha256:90ae197856a75a53b3e096c5f1a5f7c56b093052cfcfcd03b240f04d86290b44"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NIWJHI77DI2WZO5R3JYCIYIH57/bundle.json","state_url":"https://pith.science/pith/NIWJHI77DI2WZO5R3JYCIYIH57/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NIWJHI77DI2WZO5R3JYCIYIH57/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":"2026-05-27T10:43:02Z","links":{"resolver":"https://pith.science/pith/NIWJHI77DI2WZO5R3JYCIYIH57","bundle":"https://pith.science/pith/NIWJHI77DI2WZO5R3JYCIYIH57/bundle.json","state":"https://pith.science/pith/NIWJHI77DI2WZO5R3JYCIYIH57/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NIWJHI77DI2WZO5R3JYCIYIH57/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NIWJHI77DI2WZO5R3JYCIYIH57","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":"b022a3c6b5b4b7d2dbbe296259ca4103f36a26e72d9dac1a1dd5b891f1124438","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-06-24T16:06:13Z","title_canon_sha256":"4a4d362ce3f768983dcb35cc3e6ac2f5c9c6fa0928b6ba7af91f841f9e72198c"},"schema_version":"1.0","source":{"id":"1906.10042","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.10042","created_at":"2026-05-17T23:42:35Z"},{"alias_kind":"arxiv_version","alias_value":"1906.10042v1","created_at":"2026-05-17T23:42:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10042","created_at":"2026-05-17T23:42:35Z"},{"alias_kind":"pith_short_12","alias_value":"NIWJHI77DI2W","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NIWJHI77DI2WZO5R","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NIWJHI77","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:90ae197856a75a53b3e096c5f1a5f7c56b093052cfcfcd03b240f04d86290b44","target":"graph","created_at":"2026-05-17T23:42:35Z","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"},"paper":{"abstract_excerpt":"The goal of this work is to determine 'who spoke when' in real-world meetings. The method takes surround-view video and single or multi-channel audio as inputs, and generates robust diarisation outputs. To achieve this, we propose a novel iterative approach that first enrolls speaker models using audio-visual correspondence, then uses the enrolled models together with the visual information to determine the active speaker. We show strong quantitative and qualitative performance on a dataset of real-world meetings. The method is also evaluated on the public AMI meeting corpus, on which we demon","authors_text":"Bong-Jin Lee, Icksang Han, Joon Son Chung","cross_cats":["cs.CV","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-06-24T16:06:13Z","title":"Who said that?: Audio-visual speaker diarisation of real-world meetings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10042","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:a3960a0e0344473232e0e7308043a00d22bfdd47562820f53401dca42e49b180","target":"record","created_at":"2026-05-17T23:42:35Z","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":"b022a3c6b5b4b7d2dbbe296259ca4103f36a26e72d9dac1a1dd5b891f1124438","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-06-24T16:06:13Z","title_canon_sha256":"4a4d362ce3f768983dcb35cc3e6ac2f5c9c6fa0928b6ba7af91f841f9e72198c"},"schema_version":"1.0","source":{"id":"1906.10042","kind":"arxiv","version":1}},"canonical_sha256":"6a2c93a3ff1a356cbbb1da70246107effd1b915f9aff78533c03129d88317dff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a2c93a3ff1a356cbbb1da70246107effd1b915f9aff78533c03129d88317dff","first_computed_at":"2026-05-17T23:42:35.641424Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:35.641424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BgRB2MIkFE7490FaXvoZaKl7dR3Q3RWnzuzlY0nORPfYs6+oZ+ZBzEC4MNUtB1Ndcye5hT+3l8duGx3YmmL7Dg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:35.642085Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.10042","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3960a0e0344473232e0e7308043a00d22bfdd47562820f53401dca42e49b180","sha256:90ae197856a75a53b3e096c5f1a5f7c56b093052cfcfcd03b240f04d86290b44"],"state_sha256":"c038ac4b4e1c695b4be5d96ce4e569ef1c259b9f4817c2a618c179b93db0f0f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WM1VxZzmuA5RWj6OMTTQWBA9IF04133nyraazP3BDCFR495uWZPlvJtLrOFODbt8sgTRE4nFVQpcDz3U4I3EAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T10:43:02.025256Z","bundle_sha256":"4c995140000593f255a1b0576e9aba557b1546709a0aa223fca84e18cd8ca69b"}}