{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SBGM3ZVVS22YKFQTUDBYEUMQFK","short_pith_number":"pith:SBGM3ZVV","canonical_record":{"source":{"id":"2412.16530","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-21T08:15:52Z","cross_cats_sorted":["cs.CL","cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"f52df3befc7d84d6f92dc2b20be65efb5ad79195e25ff4b0d1b03fb320504b62","abstract_canon_sha256":"5b41d024a4916a281ad1472544e02d967197f7f516d36f2468370da76fdc4f8b"},"schema_version":"1.0"},"canonical_sha256":"904ccde6b596b5851613a0c38251902aa54140010cc2e9bd3097dbd67fc45bde","source":{"kind":"arxiv","id":"2412.16530","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16530","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16530v1","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16530","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"pith_short_12","alias_value":"SBGM3ZVVS22Y","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"pith_short_16","alias_value":"SBGM3ZVVS22YKFQT","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"pith_short_8","alias_value":"SBGM3ZVV","created_at":"2026-07-05T09:53:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SBGM3ZVVS22YKFQTUDBYEUMQFK","target":"record","payload":{"canonical_record":{"source":{"id":"2412.16530","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-21T08:15:52Z","cross_cats_sorted":["cs.CL","cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"f52df3befc7d84d6f92dc2b20be65efb5ad79195e25ff4b0d1b03fb320504b62","abstract_canon_sha256":"5b41d024a4916a281ad1472544e02d967197f7f516d36f2468370da76fdc4f8b"},"schema_version":"1.0"},"canonical_sha256":"904ccde6b596b5851613a0c38251902aa54140010cc2e9bd3097dbd67fc45bde","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:10.396386Z","signature_b64":"6RyyvlKpytwlz2+2XXihQ1folWo0gqwRcQtcv1DgvQblzBJVw1Z8uJTRssnqHXKVdk5RHaSukx+cH8or8ZbbCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"904ccde6b596b5851613a0c38251902aa54140010cc2e9bd3097dbd67fc45bde","last_reissued_at":"2026-07-05T09:53:10.395985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:10.395985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.16530","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":"2026-07-05T09:53:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7vykoNYnfz34LdevMyXuGKvBcTCM971F7ZVAtThIiDPDOzJhTkrbVRJg4+A8WSo+FvHgbpyLC3bt73L9TF0fBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T20:45:00.552526Z"},"content_sha256":"7bbc940bf6f4a829edd4ab34d1808472b772beda27feb3b5ecd77a03710207f5","schema_version":"1.0","event_id":"sha256:7bbc940bf6f4a829edd4ab34d1808472b772beda27feb3b5ecd77a03710207f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SBGM3ZVVS22YKFQTUDBYEUMQFK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Lip-synchrony in Direct Audio-Visual Speech-to-Speech Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Anthony Ferritto, Brady Houston, Chandrashekhar Lavania, Lijia Sun, Lucas Goncalves, Prashant Mathur, Srikanth Vishnubhotla, Xing Niu","submitted_at":"2024-12-21T08:15:52Z","abstract_excerpt":"Audio-Visual Speech-to-Speech Translation typically prioritizes improving translation quality and naturalness. However, an equally critical aspect in audio-visual content is lip-synchrony-ensuring that the movements of the lips match the spoken content-essential for maintaining realism in dubbed videos. Despite its importance, the inclusion of lip-synchrony constraints in AVS2S models has been largely overlooked. This study addresses this gap by integrating a lip-synchrony loss into the training process of AVS2S models. Our proposed method significantly enhances lip-synchrony in direct audio-v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16530","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/2412.16530/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":"2026-07-05T09:53:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gqSBkMl0mz8+OFxu1zzkNpR69E/vIrDKCPlDTrMAvnUB63ZTaW51O/KWUbrfclOb30uP58Z8LSRKATXEnJFNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T20:45:00.552910Z"},"content_sha256":"5e8b0874b048cd84f26685a8fbc707786ac9c1f21b7b8ee3f1b53927ed20278e","schema_version":"1.0","event_id":"sha256:5e8b0874b048cd84f26685a8fbc707786ac9c1f21b7b8ee3f1b53927ed20278e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SBGM3ZVVS22YKFQTUDBYEUMQFK/bundle.json","state_url":"https://pith.science/pith/SBGM3ZVVS22YKFQTUDBYEUMQFK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SBGM3ZVVS22YKFQTUDBYEUMQFK/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":"2026-08-21T20:45:00Z","links":{"resolver":"https://pith.science/pith/SBGM3ZVVS22YKFQTUDBYEUMQFK","bundle":"https://pith.science/pith/SBGM3ZVVS22YKFQTUDBYEUMQFK/bundle.json","state":"https://pith.science/pith/SBGM3ZVVS22YKFQTUDBYEUMQFK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SBGM3ZVVS22YKFQTUDBYEUMQFK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SBGM3ZVVS22YKFQTUDBYEUMQFK","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":"5b41d024a4916a281ad1472544e02d967197f7f516d36f2468370da76fdc4f8b","cross_cats_sorted":["cs.CL","cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-21T08:15:52Z","title_canon_sha256":"f52df3befc7d84d6f92dc2b20be65efb5ad79195e25ff4b0d1b03fb320504b62"},"schema_version":"1.0","source":{"id":"2412.16530","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16530","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16530v1","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16530","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"pith_short_12","alias_value":"SBGM3ZVVS22Y","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"pith_short_16","alias_value":"SBGM3ZVVS22YKFQT","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"pith_short_8","alias_value":"SBGM3ZVV","created_at":"2026-07-05T09:53:10Z"}],"graph_snapshots":[{"event_id":"sha256:5e8b0874b048cd84f26685a8fbc707786ac9c1f21b7b8ee3f1b53927ed20278e","target":"graph","created_at":"2026-07-05T09:53:10Z","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/2412.16530/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Visual Speech-to-Speech Translation typically prioritizes improving translation quality and naturalness. However, an equally critical aspect in audio-visual content is lip-synchrony-ensuring that the movements of the lips match the spoken content-essential for maintaining realism in dubbed videos. Despite its importance, the inclusion of lip-synchrony constraints in AVS2S models has been largely overlooked. This study addresses this gap by integrating a lip-synchrony loss into the training process of AVS2S models. Our proposed method significantly enhances lip-synchrony in direct audio-v","authors_text":"Anthony Ferritto, Brady Houston, Chandrashekhar Lavania, Lijia Sun, Lucas Goncalves, Prashant Mathur, Srikanth Vishnubhotla, Xing Niu","cross_cats":["cs.CL","cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-21T08:15:52Z","title":"Improving Lip-synchrony in Direct Audio-Visual Speech-to-Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16530","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":"sha256:7bbc940bf6f4a829edd4ab34d1808472b772beda27feb3b5ecd77a03710207f5","target":"record","created_at":"2026-07-05T09:53:10Z","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":"5b41d024a4916a281ad1472544e02d967197f7f516d36f2468370da76fdc4f8b","cross_cats_sorted":["cs.CL","cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-21T08:15:52Z","title_canon_sha256":"f52df3befc7d84d6f92dc2b20be65efb5ad79195e25ff4b0d1b03fb320504b62"},"schema_version":"1.0","source":{"id":"2412.16530","kind":"arxiv","version":1}},"canonical_sha256":"904ccde6b596b5851613a0c38251902aa54140010cc2e9bd3097dbd67fc45bde","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"904ccde6b596b5851613a0c38251902aa54140010cc2e9bd3097dbd67fc45bde","first_computed_at":"2026-07-05T09:53:10.395985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:10.395985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6RyyvlKpytwlz2+2XXihQ1folWo0gqwRcQtcv1DgvQblzBJVw1Z8uJTRssnqHXKVdk5RHaSukx+cH8or8ZbbCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:10.396386Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16530","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7bbc940bf6f4a829edd4ab34d1808472b772beda27feb3b5ecd77a03710207f5","sha256:5e8b0874b048cd84f26685a8fbc707786ac9c1f21b7b8ee3f1b53927ed20278e"],"state_sha256":"abc11da04fe09b5b862d0f1bddc0c52e34ba85a85938bfff9f148c7b8d2008f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VE7a0vrXmsQzOiLNYRyEvfQPHKprg2kjX0emMuKE95m7qyoiXfEW7H0GD4W8quHocyDEDKmRWJNxBiaNggBzAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T20:45:00.555557Z","bundle_sha256":"9b190eb253c9c7df82e123ca6e77a97ca7730024b355beadff20a037ea4e6c91"}}