{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OREBVW7CEG6JAFLYR3B6ZWEMG4","short_pith_number":"pith:OREBVW7C","canonical_record":{"source":{"id":"2506.02621","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-03T08:38:05Z","cross_cats_sorted":[],"title_canon_sha256":"8342dcca4230ad6ede789e5802bf8106574cf9b9cd0300025c9a89fbf6e76d29","abstract_canon_sha256":"74dac1fa19679a2d5ebe14f97b3855ba8dc6efa123f51133e9c55a56cf576b78"},"schema_version":"1.0"},"canonical_sha256":"74481adbe221bc9015788ec3ecd88c37119c166a2cb42024828bfcdb7b5ad352","source":{"kind":"arxiv","id":"2506.02621","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02621","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02621v1","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02621","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"pith_short_12","alias_value":"OREBVW7CEG6J","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"pith_short_16","alias_value":"OREBVW7CEG6JAFLY","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"pith_short_8","alias_value":"OREBVW7C","created_at":"2026-07-05T11:15:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OREBVW7CEG6JAFLYR3B6ZWEMG4","target":"record","payload":{"canonical_record":{"source":{"id":"2506.02621","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-03T08:38:05Z","cross_cats_sorted":[],"title_canon_sha256":"8342dcca4230ad6ede789e5802bf8106574cf9b9cd0300025c9a89fbf6e76d29","abstract_canon_sha256":"74dac1fa19679a2d5ebe14f97b3855ba8dc6efa123f51133e9c55a56cf576b78"},"schema_version":"1.0"},"canonical_sha256":"74481adbe221bc9015788ec3ecd88c37119c166a2cb42024828bfcdb7b5ad352","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:05.540750Z","signature_b64":"42QcAHyHZZAMgtk6e+Jwnu1D2ROdAobJijP5EZn18+8yj7nEIyjtG6Ltwes0YO95lXJsPRQckDDyHusvV8M2Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74481adbe221bc9015788ec3ecd88c37119c166a2cb42024828bfcdb7b5ad352","last_reissued_at":"2026-07-05T11:15:05.539576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:05.539576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.02621","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":"2026-07-05T11:15:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WoMqFTrgpH65w79YTLe50bEwRxpM+Q3DmOmMUgZ8WxQ6H4GzQDq760BkoEXH67lqj9s889XWwKlNDCOdaJliDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:39:15.749906Z"},"content_sha256":"8aec3451d3af8e081be341a1ac0601a73ec595da5463d7723ec321b37eba9f4f","schema_version":"1.0","event_id":"sha256:8aec3451d3af8e081be341a1ac0601a73ec595da5463d7723ec321b37eba9f4f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OREBVW7CEG6JAFLYR3B6ZWEMG4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-attention and Self-attention for Audio-visual Speaker Diarization in MISP-Meeting Challenge","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Haodong Zhou, Lin Li, Longjie Luo, Qingyang Hong, Xiaoxiao Li, Yongxin Chen, Zhaoyang Li","submitted_at":"2025-06-03T08:38:05Z","abstract_excerpt":"This paper presents the system developed for Task 1 of the Multi-modal Information-based Speech Processing (MISP) 2025 Challenge. We introduce CASA-Net, an embedding fusion method designed for end-to-end audio-visual speaker diarization (AVSD) systems. CASA-Net incorporates a cross-attention (CA) module to effectively capture cross-modal interactions in audio-visual signals and employs a self-attention (SA) module to learn contextual relationships among audio-visual frames. To further enhance performance, we adopt a training strategy that integrates pseudo-label refinement and retraining, impr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02621","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.02621/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":"2026-07-05T11:15:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zqbw8+gYCZUxAIQQPMvVGM96jKW/05Dp5fn8NktNc7e56Mzo5GBElezYxh1Usm5RkNqx0nY7bYKd3E4vjjmtCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:39:15.750884Z"},"content_sha256":"d6cf4616804558b01f6f2277b6f1b10a8b91a8129584eb7f1483c5100d0fa9f2","schema_version":"1.0","event_id":"sha256:d6cf4616804558b01f6f2277b6f1b10a8b91a8129584eb7f1483c5100d0fa9f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OREBVW7CEG6JAFLYR3B6ZWEMG4/bundle.json","state_url":"https://pith.science/pith/OREBVW7CEG6JAFLYR3B6ZWEMG4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OREBVW7CEG6JAFLYR3B6ZWEMG4/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":"2026-08-08T13:39:15Z","links":{"resolver":"https://pith.science/pith/OREBVW7CEG6JAFLYR3B6ZWEMG4","bundle":"https://pith.science/pith/OREBVW7CEG6JAFLYR3B6ZWEMG4/bundle.json","state":"https://pith.science/pith/OREBVW7CEG6JAFLYR3B6ZWEMG4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OREBVW7CEG6JAFLYR3B6ZWEMG4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OREBVW7CEG6JAFLYR3B6ZWEMG4","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":"74dac1fa19679a2d5ebe14f97b3855ba8dc6efa123f51133e9c55a56cf576b78","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-03T08:38:05Z","title_canon_sha256":"8342dcca4230ad6ede789e5802bf8106574cf9b9cd0300025c9a89fbf6e76d29"},"schema_version":"1.0","source":{"id":"2506.02621","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02621","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02621v1","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02621","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"pith_short_12","alias_value":"OREBVW7CEG6J","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"pith_short_16","alias_value":"OREBVW7CEG6JAFLY","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"pith_short_8","alias_value":"OREBVW7C","created_at":"2026-07-05T11:15:05Z"}],"graph_snapshots":[{"event_id":"sha256:d6cf4616804558b01f6f2277b6f1b10a8b91a8129584eb7f1483c5100d0fa9f2","target":"graph","created_at":"2026-07-05T11:15:05Z","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/2506.02621/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents the system developed for Task 1 of the Multi-modal Information-based Speech Processing (MISP) 2025 Challenge. We introduce CASA-Net, an embedding fusion method designed for end-to-end audio-visual speaker diarization (AVSD) systems. CASA-Net incorporates a cross-attention (CA) module to effectively capture cross-modal interactions in audio-visual signals and employs a self-attention (SA) module to learn contextual relationships among audio-visual frames. To further enhance performance, we adopt a training strategy that integrates pseudo-label refinement and retraining, impr","authors_text":"Haodong Zhou, Lin Li, Longjie Luo, Qingyang Hong, Xiaoxiao Li, Yongxin Chen, Zhaoyang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-03T08:38:05Z","title":"Cross-attention and Self-attention for Audio-visual Speaker Diarization in MISP-Meeting Challenge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02621","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":"sha256:8aec3451d3af8e081be341a1ac0601a73ec595da5463d7723ec321b37eba9f4f","target":"record","created_at":"2026-07-05T11:15:05Z","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":"74dac1fa19679a2d5ebe14f97b3855ba8dc6efa123f51133e9c55a56cf576b78","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-03T08:38:05Z","title_canon_sha256":"8342dcca4230ad6ede789e5802bf8106574cf9b9cd0300025c9a89fbf6e76d29"},"schema_version":"1.0","source":{"id":"2506.02621","kind":"arxiv","version":1}},"canonical_sha256":"74481adbe221bc9015788ec3ecd88c37119c166a2cb42024828bfcdb7b5ad352","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74481adbe221bc9015788ec3ecd88c37119c166a2cb42024828bfcdb7b5ad352","first_computed_at":"2026-07-05T11:15:05.539576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:05.539576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"42QcAHyHZZAMgtk6e+Jwnu1D2ROdAobJijP5EZn18+8yj7nEIyjtG6Ltwes0YO95lXJsPRQckDDyHusvV8M2Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:05.540750Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02621","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8aec3451d3af8e081be341a1ac0601a73ec595da5463d7723ec321b37eba9f4f","sha256:d6cf4616804558b01f6f2277b6f1b10a8b91a8129584eb7f1483c5100d0fa9f2"],"state_sha256":"19cbe82491ace6dc69f841b75a1140eab4719d44925404a1734b004b9c5448c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3+3M0ZHRl73ITFhdxffewjfHX4+0LzGnsd25DKX6LD9sul0jdS2G36WTfiI+e0ey0pSpNjOc5dKZEMhLsUshCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:39:15.757337Z","bundle_sha256":"760f9de0f66bd9cc6027a0ec376b25675b2c363e827b3e781301ef2904958383"}}