{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JKM2R6O7JAWSM22AYCHX2D45Q2","short_pith_number":"pith:JKM2R6O7","canonical_record":{"source":{"id":"2506.04635","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T05:13:01Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0bb1e4924304339c9a1829687dac1be3add7f45c259bc2a68eedf262bd24ffbd","abstract_canon_sha256":"1cc412dcc2302252dde0a17cb6c16ae11ed2a9c17dcc365a27e1b8f0e8375aee"},"schema_version":"1.0"},"canonical_sha256":"4a99a8f9df482d266b40c08f7d0f9d8694a04cd82e03d848cc469a33741e19db","source":{"kind":"arxiv","id":"2506.04635","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04635","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04635v1","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04635","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"pith_short_12","alias_value":"JKM2R6O7JAWS","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"pith_short_16","alias_value":"JKM2R6O7JAWSM22A","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"pith_short_8","alias_value":"JKM2R6O7","created_at":"2026-07-05T11:16:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JKM2R6O7JAWSM22AYCHX2D45Q2","target":"record","payload":{"canonical_record":{"source":{"id":"2506.04635","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T05:13:01Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0bb1e4924304339c9a1829687dac1be3add7f45c259bc2a68eedf262bd24ffbd","abstract_canon_sha256":"1cc412dcc2302252dde0a17cb6c16ae11ed2a9c17dcc365a27e1b8f0e8375aee"},"schema_version":"1.0"},"canonical_sha256":"4a99a8f9df482d266b40c08f7d0f9d8694a04cd82e03d848cc469a33741e19db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:18.229894Z","signature_b64":"Cx10ZiTYvOM31sED+PJaGrhYrIPu6YTmE1i0SQrHgVSFATbVvlRyNshXL0/laJZGoBwacsnytp2BMxw4Fe+hDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a99a8f9df482d266b40c08f7d0f9d8694a04cd82e03d848cc469a33741e19db","last_reissued_at":"2026-07-05T11:16:18.229427Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:18.229427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.04635","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":"2026-07-05T11:16:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zgoHSP49xy7yTR0gB4/XK1Qk8OHLfQ+Lgsy0laQXwO68waKTNnuWGWGjkuWq1y4Rf6fLlalxgeNXjhBBBQSAAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:41:08.240492Z"},"content_sha256":"2a38406806a928e3903420aee613e9b23a665e4d88193bcece56e846c2f13617","schema_version":"1.0","event_id":"sha256:2a38406806a928e3903420aee613e9b23a665e4d88193bcece56e846c2f13617"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JKM2R6O7JAWSM22AYCHX2D45Q2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ViCocktail: Automated Multi-Modal Data Collection for Vietnamese Audio-Visual Speech Recognition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Chi Mai Luong, Quoc Truong Do, Thai-Binh Nguyen, Thi Van Nguyen","submitted_at":"2025-06-05T05:13:01Z","abstract_excerpt":"Audio-Visual Speech Recognition (AVSR) has gained significant attention recently due to its robustness against noise, which often challenges conventional speech recognition systems that rely solely on audio features. Despite this advantage, AVSR models remain limited by the scarcity of extensive datasets, especially for most languages beyond English. Automated data collection offers a promising solution. This work presents a practical approach to generate AVSR datasets from raw video, refining existing techniques for improved efficiency and accessibility. We demonstrate its broad applicability"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04635","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/2506.04635/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":"2026-07-05T11:16:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v+I1oQARf7b48vM8X0ZclZ+wwsNFYhLBDoQi4hgz+/sh/zV8n3oOQyi95TXXow8loljK2BR6rkPs8e8D66Y0Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:41:08.241004Z"},"content_sha256":"63e36f29218e7f8a835fd48ecc44c55b633491dcddd19ca2546b5a0fc215e04b","schema_version":"1.0","event_id":"sha256:63e36f29218e7f8a835fd48ecc44c55b633491dcddd19ca2546b5a0fc215e04b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JKM2R6O7JAWSM22AYCHX2D45Q2/bundle.json","state_url":"https://pith.science/pith/JKM2R6O7JAWSM22AYCHX2D45Q2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JKM2R6O7JAWSM22AYCHX2D45Q2/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":"2026-08-08T17:41:08Z","links":{"resolver":"https://pith.science/pith/JKM2R6O7JAWSM22AYCHX2D45Q2","bundle":"https://pith.science/pith/JKM2R6O7JAWSM22AYCHX2D45Q2/bundle.json","state":"https://pith.science/pith/JKM2R6O7JAWSM22AYCHX2D45Q2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JKM2R6O7JAWSM22AYCHX2D45Q2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JKM2R6O7JAWSM22AYCHX2D45Q2","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":"1cc412dcc2302252dde0a17cb6c16ae11ed2a9c17dcc365a27e1b8f0e8375aee","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T05:13:01Z","title_canon_sha256":"0bb1e4924304339c9a1829687dac1be3add7f45c259bc2a68eedf262bd24ffbd"},"schema_version":"1.0","source":{"id":"2506.04635","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04635","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04635v1","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04635","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"pith_short_12","alias_value":"JKM2R6O7JAWS","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"pith_short_16","alias_value":"JKM2R6O7JAWSM22A","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"pith_short_8","alias_value":"JKM2R6O7","created_at":"2026-07-05T11:16:18Z"}],"graph_snapshots":[{"event_id":"sha256:63e36f29218e7f8a835fd48ecc44c55b633491dcddd19ca2546b5a0fc215e04b","target":"graph","created_at":"2026-07-05T11:16:18Z","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/2506.04635/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Visual Speech Recognition (AVSR) has gained significant attention recently due to its robustness against noise, which often challenges conventional speech recognition systems that rely solely on audio features. Despite this advantage, AVSR models remain limited by the scarcity of extensive datasets, especially for most languages beyond English. Automated data collection offers a promising solution. This work presents a practical approach to generate AVSR datasets from raw video, refining existing techniques for improved efficiency and accessibility. We demonstrate its broad applicability","authors_text":"Chi Mai Luong, Quoc Truong Do, Thai-Binh Nguyen, Thi Van Nguyen","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T05:13:01Z","title":"ViCocktail: Automated Multi-Modal Data Collection for Vietnamese Audio-Visual Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04635","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":"sha256:2a38406806a928e3903420aee613e9b23a665e4d88193bcece56e846c2f13617","target":"record","created_at":"2026-07-05T11:16:18Z","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":"1cc412dcc2302252dde0a17cb6c16ae11ed2a9c17dcc365a27e1b8f0e8375aee","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T05:13:01Z","title_canon_sha256":"0bb1e4924304339c9a1829687dac1be3add7f45c259bc2a68eedf262bd24ffbd"},"schema_version":"1.0","source":{"id":"2506.04635","kind":"arxiv","version":1}},"canonical_sha256":"4a99a8f9df482d266b40c08f7d0f9d8694a04cd82e03d848cc469a33741e19db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a99a8f9df482d266b40c08f7d0f9d8694a04cd82e03d848cc469a33741e19db","first_computed_at":"2026-07-05T11:16:18.229427Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:18.229427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cx10ZiTYvOM31sED+PJaGrhYrIPu6YTmE1i0SQrHgVSFATbVvlRyNshXL0/laJZGoBwacsnytp2BMxw4Fe+hDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:18.229894Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04635","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a38406806a928e3903420aee613e9b23a665e4d88193bcece56e846c2f13617","sha256:63e36f29218e7f8a835fd48ecc44c55b633491dcddd19ca2546b5a0fc215e04b"],"state_sha256":"7c366cbc5a8562433c153262ba4effa97159890ec24994dc68c01f984be746f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mfKlkRsomQ2iCSnJRHi0peI45qaUlQbqyYzPUVEDC8FGwGykpwiHzFdzIv1oM2cWq4D1ter45CYG471PgGw+AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:41:08.246832Z","bundle_sha256":"74eef5d0046e0d121e5f6cb9463a5327dd506c3536f92da1cdbc31936382f23c"}}