{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZPBEVIY53E3EUEJODJDDFVXPAW","short_pith_number":"pith:ZPBEVIY5","canonical_record":{"source":{"id":"2505.13971","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-20T06:11:51Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"45bbb25573482080c3dca95c3d22b38667d042ae1b03ca5918d26b89aa774a0b","abstract_canon_sha256":"23ba2d0dd61746b4e9d80690a2f945e1507d8222cb5dea3bc0aa3fcc828bc169"},"schema_version":"1.0"},"canonical_sha256":"cbc24aa31dd9364a112e1a4632d6ef058110a1370f9a58203b6546012a84eb36","source":{"kind":"arxiv","id":"2505.13971","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13971","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13971v2","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13971","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"pith_short_12","alias_value":"ZPBEVIY53E3E","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"pith_short_16","alias_value":"ZPBEVIY53E3EUEJO","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"pith_short_8","alias_value":"ZPBEVIY5","created_at":"2026-07-05T11:10:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZPBEVIY53E3EUEJODJDDFVXPAW","target":"record","payload":{"canonical_record":{"source":{"id":"2505.13971","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-20T06:11:51Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"45bbb25573482080c3dca95c3d22b38667d042ae1b03ca5918d26b89aa774a0b","abstract_canon_sha256":"23ba2d0dd61746b4e9d80690a2f945e1507d8222cb5dea3bc0aa3fcc828bc169"},"schema_version":"1.0"},"canonical_sha256":"cbc24aa31dd9364a112e1a4632d6ef058110a1370f9a58203b6546012a84eb36","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:08.845672Z","signature_b64":"XKelD9OevTIMbhy+1xBjwtBCyknT1ctaCtzqOvw5Az2p6zd9GbE8asCZJWCyrdc/D/nZcfEUQd/XaN+FtZKYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbc24aa31dd9364a112e1a4632d6ef058110a1370f9a58203b6546012a84eb36","last_reissued_at":"2026-07-05T11:10:08.845152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:08.845152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.13971","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":"2026-07-05T11:10:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Z/R1hjpyRpE731kn94qjcmXsSMw17R+ZpOWDZzXrAtKpv9lR2LTxpDOhhFl3K0ZEyv/8g5z04ZFnJz9KWkpBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:57:26.725807Z"},"content_sha256":"7525a3e0d29b44c24eea1d38ebcf129cdeba72b203e73ad5b63086ba27eaa5b7","schema_version":"1.0","event_id":"sha256:7525a3e0d29b44c24eea1d38ebcf129cdeba72b203e73ad5b63086ba27eaa5b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZPBEVIY53E3EUEJODJDDFVXPAW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Multimodal Information Based Speech Processing (MISP) 2025 Challenge: Audio-Visual Diarization and Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chin-Hui Lee, Hang Chen, Jingdong Chen, Jun Du, Ming Gao, Odette Scharenborg, Shilong Wu, Shinji Watanabe, Siniscalchi Sabato Marco","submitted_at":"2025-05-20T06:11:51Z","abstract_excerpt":"Meetings are a valuable yet challenging scenario for speech applications due to complex acoustic conditions. This paper summarizes the outcomes of the MISP 2025 Challenge, hosted at Interspeech 2025, which focuses on multi-modal, multi-device meeting transcription by incorporating video modality alongside audio. The tasks include Audio-Visual Speaker Diarization (AVSD), Audio-Visual Speech Recognition (AVSR), and Audio-Visual Diarization and Recognition (AVDR). We present the challenge's objectives, tasks, dataset, baseline systems, and solutions proposed by participants. The best-performing s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13971","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/2505.13971/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":"2026-07-05T11:10:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fr8pa5jBW7xksn0OGYi8cwv5mhW58b/yCBuW1vBvukWYcRBUaEUaWCo/LF4MzH0AHoqTF6uKLLvyIl+WpKowBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:57:26.726330Z"},"content_sha256":"948d419a2aaa885c9d386b4fce96881b7fb806ee6376d35d7b9de8fc8bfc0761","schema_version":"1.0","event_id":"sha256:948d419a2aaa885c9d386b4fce96881b7fb806ee6376d35d7b9de8fc8bfc0761"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZPBEVIY53E3EUEJODJDDFVXPAW/bundle.json","state_url":"https://pith.science/pith/ZPBEVIY53E3EUEJODJDDFVXPAW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZPBEVIY53E3EUEJODJDDFVXPAW/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":"2026-08-08T09:57:26Z","links":{"resolver":"https://pith.science/pith/ZPBEVIY53E3EUEJODJDDFVXPAW","bundle":"https://pith.science/pith/ZPBEVIY53E3EUEJODJDDFVXPAW/bundle.json","state":"https://pith.science/pith/ZPBEVIY53E3EUEJODJDDFVXPAW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZPBEVIY53E3EUEJODJDDFVXPAW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZPBEVIY53E3EUEJODJDDFVXPAW","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":"23ba2d0dd61746b4e9d80690a2f945e1507d8222cb5dea3bc0aa3fcc828bc169","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-20T06:11:51Z","title_canon_sha256":"45bbb25573482080c3dca95c3d22b38667d042ae1b03ca5918d26b89aa774a0b"},"schema_version":"1.0","source":{"id":"2505.13971","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13971","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13971v2","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13971","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"pith_short_12","alias_value":"ZPBEVIY53E3E","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"pith_short_16","alias_value":"ZPBEVIY53E3EUEJO","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"pith_short_8","alias_value":"ZPBEVIY5","created_at":"2026-07-05T11:10:08Z"}],"graph_snapshots":[{"event_id":"sha256:948d419a2aaa885c9d386b4fce96881b7fb806ee6376d35d7b9de8fc8bfc0761","target":"graph","created_at":"2026-07-05T11:10:08Z","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/2505.13971/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Meetings are a valuable yet challenging scenario for speech applications due to complex acoustic conditions. This paper summarizes the outcomes of the MISP 2025 Challenge, hosted at Interspeech 2025, which focuses on multi-modal, multi-device meeting transcription by incorporating video modality alongside audio. The tasks include Audio-Visual Speaker Diarization (AVSD), Audio-Visual Speech Recognition (AVSR), and Audio-Visual Diarization and Recognition (AVDR). We present the challenge's objectives, tasks, dataset, baseline systems, and solutions proposed by participants. The best-performing s","authors_text":"Chin-Hui Lee, Hang Chen, Jingdong Chen, Jun Du, Ming Gao, Odette Scharenborg, Shilong Wu, Shinji Watanabe, Siniscalchi Sabato Marco","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-20T06:11:51Z","title":"The Multimodal Information Based Speech Processing (MISP) 2025 Challenge: Audio-Visual Diarization and Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13971","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":"sha256:7525a3e0d29b44c24eea1d38ebcf129cdeba72b203e73ad5b63086ba27eaa5b7","target":"record","created_at":"2026-07-05T11:10:08Z","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":"23ba2d0dd61746b4e9d80690a2f945e1507d8222cb5dea3bc0aa3fcc828bc169","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-20T06:11:51Z","title_canon_sha256":"45bbb25573482080c3dca95c3d22b38667d042ae1b03ca5918d26b89aa774a0b"},"schema_version":"1.0","source":{"id":"2505.13971","kind":"arxiv","version":2}},"canonical_sha256":"cbc24aa31dd9364a112e1a4632d6ef058110a1370f9a58203b6546012a84eb36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbc24aa31dd9364a112e1a4632d6ef058110a1370f9a58203b6546012a84eb36","first_computed_at":"2026-07-05T11:10:08.845152Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:08.845152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XKelD9OevTIMbhy+1xBjwtBCyknT1ctaCtzqOvw5Az2p6zd9GbE8asCZJWCyrdc/D/nZcfEUQd/XaN+FtZKYAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:08.845672Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13971","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7525a3e0d29b44c24eea1d38ebcf129cdeba72b203e73ad5b63086ba27eaa5b7","sha256:948d419a2aaa885c9d386b4fce96881b7fb806ee6376d35d7b9de8fc8bfc0761"],"state_sha256":"ded35ac0b20184599e4f1b2e3d086492ab5895360247c1cba0dd23369b9f38a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8yixJ+rgLvLQByO4qqyij2sTIQnyD4yVz26QIYs/GROecF0ZBJ5svw+LpAPxiGn8askHy9wbnuXWYqBzwQoyBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:57:26.730162Z","bundle_sha256":"342718648fa2b5c95ec7ce783fdee293035d913cc872a0967e5a17e71a4693d1"}}