{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6FH6K27IRUUHBBMDBFHULYXHIY","short_pith_number":"pith:6FH6K27I","canonical_record":{"source":{"id":"2506.02178","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-02T19:07:51Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c78aedf4060b53fdacf6646b23bbf4cc8a2a2bfe7868ec58892393b2f441c61e","abstract_canon_sha256":"aa9bfd5ff95f29717b3a73fd4963b1e0f7d25425a53551be04e961650b3f6bcf"},"schema_version":"1.0"},"canonical_sha256":"f14fe56be88d28708583094f45e2e746186af8d409e7cc4ab3fe7b9da8dc6299","source":{"kind":"arxiv","id":"2506.02178","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02178","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02178v1","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02178","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"pith_short_12","alias_value":"6FH6K27IRUUH","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"pith_short_16","alias_value":"6FH6K27IRUUHBBMD","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"pith_short_8","alias_value":"6FH6K27I","created_at":"2026-07-05T11:14:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6FH6K27IRUUHBBMDBFHULYXHIY","target":"record","payload":{"canonical_record":{"source":{"id":"2506.02178","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-02T19:07:51Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c78aedf4060b53fdacf6646b23bbf4cc8a2a2bfe7868ec58892393b2f441c61e","abstract_canon_sha256":"aa9bfd5ff95f29717b3a73fd4963b1e0f7d25425a53551be04e961650b3f6bcf"},"schema_version":"1.0"},"canonical_sha256":"f14fe56be88d28708583094f45e2e746186af8d409e7cc4ab3fe7b9da8dc6299","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:33.795147Z","signature_b64":"PfKTfeFNl240uU0MtyoJW5L4SB8QwCyVOcslS3gNW0OiWi0Ybt4q2gq7biS4nvc5Y9SuU+PcEexY2LEQ6HoQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f14fe56be88d28708583094f45e2e746186af8d409e7cc4ab3fe7b9da8dc6299","last_reissued_at":"2026-07-05T11:14:33.794682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:33.794682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.02178","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":"2026-07-05T11:14:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q0bX6tPZshOueMLOkZmyQ8NHyvm8R/mktanTSkw9cZLhhmKoX46y5HXuVn6bH6pKcwdf4q1zrVkkO2y3/7b1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:28:45.182506Z"},"content_sha256":"2b08da3446306d14277af5f3ae2aa692e57cac28d3b75d315d312b9b35ed408b","schema_version":"1.0","event_id":"sha256:2b08da3446306d14277af5f3ae2aa692e57cac28d3b75d315d312b9b35ed408b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6FH6K27IRUUHBBMDBFHULYXHIY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cocktail-Party Audio-Visual Speech Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Alexander Waibel, Ngoc-Quan Pham, Thai-Binh Nguyen","submitted_at":"2025-06-02T19:07:51Z","abstract_excerpt":"Audio-Visual Speech Recognition (AVSR) offers a robust solution for speech recognition in challenging environments, such as cocktail-party scenarios, where relying solely on audio proves insufficient. However, current AVSR models are often optimized for idealized scenarios with consistently active speakers, overlooking the complexities of real-world settings that include both speaking and silent facial segments. This study addresses this gap by introducing a novel audio-visual cocktail-party dataset designed to benchmark current AVSR systems and highlight the limitations of prior approaches in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02178","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/2506.02178/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":"2026-07-05T11:14:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DwtF3N0LHi2kus0zAz2WLjxyQB8DvVS529Gs/Cf8bcn78qJocMz9fXKYrC9TyQRPvoNIt/vwdGdmHWTqEle3AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:28:45.183050Z"},"content_sha256":"9ff0a95c74bad2cb4648fea802ab9698306683d9f8cfc44b6ada2fbe16e4c8ee","schema_version":"1.0","event_id":"sha256:9ff0a95c74bad2cb4648fea802ab9698306683d9f8cfc44b6ada2fbe16e4c8ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6FH6K27IRUUHBBMDBFHULYXHIY/bundle.json","state_url":"https://pith.science/pith/6FH6K27IRUUHBBMDBFHULYXHIY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6FH6K27IRUUHBBMDBFHULYXHIY/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":"2026-08-18T16:28:45Z","links":{"resolver":"https://pith.science/pith/6FH6K27IRUUHBBMDBFHULYXHIY","bundle":"https://pith.science/pith/6FH6K27IRUUHBBMDBFHULYXHIY/bundle.json","state":"https://pith.science/pith/6FH6K27IRUUHBBMDBFHULYXHIY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6FH6K27IRUUHBBMDBFHULYXHIY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6FH6K27IRUUHBBMDBFHULYXHIY","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":"aa9bfd5ff95f29717b3a73fd4963b1e0f7d25425a53551be04e961650b3f6bcf","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-02T19:07:51Z","title_canon_sha256":"c78aedf4060b53fdacf6646b23bbf4cc8a2a2bfe7868ec58892393b2f441c61e"},"schema_version":"1.0","source":{"id":"2506.02178","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02178","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02178v1","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02178","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"pith_short_12","alias_value":"6FH6K27IRUUH","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"pith_short_16","alias_value":"6FH6K27IRUUHBBMD","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"pith_short_8","alias_value":"6FH6K27I","created_at":"2026-07-05T11:14:33Z"}],"graph_snapshots":[{"event_id":"sha256:9ff0a95c74bad2cb4648fea802ab9698306683d9f8cfc44b6ada2fbe16e4c8ee","target":"graph","created_at":"2026-07-05T11:14:33Z","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/2506.02178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Visual Speech Recognition (AVSR) offers a robust solution for speech recognition in challenging environments, such as cocktail-party scenarios, where relying solely on audio proves insufficient. However, current AVSR models are often optimized for idealized scenarios with consistently active speakers, overlooking the complexities of real-world settings that include both speaking and silent facial segments. This study addresses this gap by introducing a novel audio-visual cocktail-party dataset designed to benchmark current AVSR systems and highlight the limitations of prior approaches in","authors_text":"Alexander Waibel, Ngoc-Quan Pham, Thai-Binh Nguyen","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-02T19:07:51Z","title":"Cocktail-Party Audio-Visual Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02178","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":"sha256:2b08da3446306d14277af5f3ae2aa692e57cac28d3b75d315d312b9b35ed408b","target":"record","created_at":"2026-07-05T11:14:33Z","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":"aa9bfd5ff95f29717b3a73fd4963b1e0f7d25425a53551be04e961650b3f6bcf","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-02T19:07:51Z","title_canon_sha256":"c78aedf4060b53fdacf6646b23bbf4cc8a2a2bfe7868ec58892393b2f441c61e"},"schema_version":"1.0","source":{"id":"2506.02178","kind":"arxiv","version":1}},"canonical_sha256":"f14fe56be88d28708583094f45e2e746186af8d409e7cc4ab3fe7b9da8dc6299","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f14fe56be88d28708583094f45e2e746186af8d409e7cc4ab3fe7b9da8dc6299","first_computed_at":"2026-07-05T11:14:33.794682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:33.794682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PfKTfeFNl240uU0MtyoJW5L4SB8QwCyVOcslS3gNW0OiWi0Ybt4q2gq7biS4nvc5Y9SuU+PcEexY2LEQ6HoQAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:33.795147Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02178","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b08da3446306d14277af5f3ae2aa692e57cac28d3b75d315d312b9b35ed408b","sha256:9ff0a95c74bad2cb4648fea802ab9698306683d9f8cfc44b6ada2fbe16e4c8ee"],"state_sha256":"7ee5165786ec68344a2abe1b27ac497faf38be3f850b966277729ece0cb87f34"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CyGLpWhdVDnvpjuiP2dClVWyQ7MBK/FIKUO0Tnq4ue2+m+FiQHA2JqFTnCxwtMHQ+V5uABpkmV0nngdyrNNoBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T16:28:45.187120Z","bundle_sha256":"53c7b599166c3d2bc6bf244bca9a0653fa1a6773ec3e786fb7a727dde8c7cdd2"}}