{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2QX5QOOOSBJI5TZ2TXBFXHF4CR","short_pith_number":"pith:2QX5QOOO","canonical_record":{"source":{"id":"2306.00489","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-01T09:40:47Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"cf3b9c69bd8f20d923f0f265c0f219bc0db76167b90d78ff17a4ba0ca5eb7a4a","abstract_canon_sha256":"5f72be7c1051827c5bb3b610b12df4901955dcb0b13d0f17bea477e6a35b0ce8"},"schema_version":"1.0"},"canonical_sha256":"d42fd839ce90528ecf3a9dc25b9cbc1471446c2f6f8b44e623809fbfa2cfc761","source":{"kind":"arxiv","id":"2306.00489","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00489","created_at":"2026-07-05T06:16:27Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00489v1","created_at":"2026-07-05T06:16:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00489","created_at":"2026-07-05T06:16:27Z"},{"alias_kind":"pith_short_12","alias_value":"2QX5QOOOSBJI","created_at":"2026-07-05T06:16:27Z"},{"alias_kind":"pith_short_16","alias_value":"2QX5QOOOSBJI5TZ2","created_at":"2026-07-05T06:16:27Z"},{"alias_kind":"pith_short_8","alias_value":"2QX5QOOO","created_at":"2026-07-05T06:16:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2QX5QOOOSBJI5TZ2TXBFXHF4CR","target":"record","payload":{"canonical_record":{"source":{"id":"2306.00489","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-01T09:40:47Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"cf3b9c69bd8f20d923f0f265c0f219bc0db76167b90d78ff17a4ba0ca5eb7a4a","abstract_canon_sha256":"5f72be7c1051827c5bb3b610b12df4901955dcb0b13d0f17bea477e6a35b0ce8"},"schema_version":"1.0"},"canonical_sha256":"d42fd839ce90528ecf3a9dc25b9cbc1471446c2f6f8b44e623809fbfa2cfc761","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:27.106382Z","signature_b64":"6oFhMbXfXAmxvgybY+tGR1WGvTrWX7CsVUMhDgsbieFoIqsmKhB8O7bexeGitO6RB0oNCIQ4LFFDXN97LGBFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d42fd839ce90528ecf3a9dc25b9cbc1471446c2f6f8b44e623809fbfa2cfc761","last_reissued_at":"2026-07-05T06:16:27.105944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:27.105944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.00489","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":"2026-07-05T06:16:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y6HFKvfNXOmYmwhV54DuW/XZoVySYr7PukMIi7v+elqHyKJ1e7gah1UQzyW3oWu+HN3to6QfzoFfRG09HHdZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T13:26:21.338848Z"},"content_sha256":"1096e70e24f88be0e5a0a45817627e5dac6927c68bc7917becce25ae68b66840","schema_version":"1.0","event_id":"sha256:1096e70e24f88be0e5a0a45817627e5dac6927c68bc7917becce25ae68b66840"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2QX5QOOOSBJI5TZ2TXBFXHF4CR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speech inpainting: Context-based speech synthesis guided by video","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Daniel Michelsanti, Gloria Haro, Jesper Jensen, Juan F. Montesinos, Zheng-Hua Tan","submitted_at":"2023-06-01T09:40:47Z","abstract_excerpt":"Audio and visual modalities are inherently connected in speech signals: lip movements and facial expressions are correlated with speech sounds. This motivates studies that incorporate the visual modality to enhance an acoustic speech signal or even restore missing audio information. Specifically, this paper focuses on the problem of audio-visual speech inpainting, which is the task of synthesizing the speech in a corrupted audio segment in a way that it is consistent with the corresponding visual content and the uncorrupted audio context. We present an audio-visual transformer-based deep learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00489","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/2306.00489/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":"2026-07-05T06:16:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fWyoaG6WwCybiyAlKPq3yAco1kLhzb6eytS9CWpIu3ZDcZkMxbLHSx+ePIP1NvEsfLVazgh1j3bSzx87mF8FBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T13:26:21.339347Z"},"content_sha256":"d439678a6ae6426fc83717c7e5cbe7c494164abec0c688c61546838965daff4c","schema_version":"1.0","event_id":"sha256:d439678a6ae6426fc83717c7e5cbe7c494164abec0c688c61546838965daff4c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2QX5QOOOSBJI5TZ2TXBFXHF4CR/bundle.json","state_url":"https://pith.science/pith/2QX5QOOOSBJI5TZ2TXBFXHF4CR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2QX5QOOOSBJI5TZ2TXBFXHF4CR/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":"2026-07-31T13:26:21Z","links":{"resolver":"https://pith.science/pith/2QX5QOOOSBJI5TZ2TXBFXHF4CR","bundle":"https://pith.science/pith/2QX5QOOOSBJI5TZ2TXBFXHF4CR/bundle.json","state":"https://pith.science/pith/2QX5QOOOSBJI5TZ2TXBFXHF4CR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2QX5QOOOSBJI5TZ2TXBFXHF4CR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2QX5QOOOSBJI5TZ2TXBFXHF4CR","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":"5f72be7c1051827c5bb3b610b12df4901955dcb0b13d0f17bea477e6a35b0ce8","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-01T09:40:47Z","title_canon_sha256":"cf3b9c69bd8f20d923f0f265c0f219bc0db76167b90d78ff17a4ba0ca5eb7a4a"},"schema_version":"1.0","source":{"id":"2306.00489","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00489","created_at":"2026-07-05T06:16:27Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00489v1","created_at":"2026-07-05T06:16:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00489","created_at":"2026-07-05T06:16:27Z"},{"alias_kind":"pith_short_12","alias_value":"2QX5QOOOSBJI","created_at":"2026-07-05T06:16:27Z"},{"alias_kind":"pith_short_16","alias_value":"2QX5QOOOSBJI5TZ2","created_at":"2026-07-05T06:16:27Z"},{"alias_kind":"pith_short_8","alias_value":"2QX5QOOO","created_at":"2026-07-05T06:16:27Z"}],"graph_snapshots":[{"event_id":"sha256:d439678a6ae6426fc83717c7e5cbe7c494164abec0c688c61546838965daff4c","target":"graph","created_at":"2026-07-05T06:16:27Z","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/2306.00489/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio and visual modalities are inherently connected in speech signals: lip movements and facial expressions are correlated with speech sounds. This motivates studies that incorporate the visual modality to enhance an acoustic speech signal or even restore missing audio information. Specifically, this paper focuses on the problem of audio-visual speech inpainting, which is the task of synthesizing the speech in a corrupted audio segment in a way that it is consistent with the corresponding visual content and the uncorrupted audio context. We present an audio-visual transformer-based deep learn","authors_text":"Daniel Michelsanti, Gloria Haro, Jesper Jensen, Juan F. Montesinos, Zheng-Hua Tan","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-01T09:40:47Z","title":"Speech inpainting: Context-based speech synthesis guided by video"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00489","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":"sha256:1096e70e24f88be0e5a0a45817627e5dac6927c68bc7917becce25ae68b66840","target":"record","created_at":"2026-07-05T06:16:27Z","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":"5f72be7c1051827c5bb3b610b12df4901955dcb0b13d0f17bea477e6a35b0ce8","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-01T09:40:47Z","title_canon_sha256":"cf3b9c69bd8f20d923f0f265c0f219bc0db76167b90d78ff17a4ba0ca5eb7a4a"},"schema_version":"1.0","source":{"id":"2306.00489","kind":"arxiv","version":1}},"canonical_sha256":"d42fd839ce90528ecf3a9dc25b9cbc1471446c2f6f8b44e623809fbfa2cfc761","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d42fd839ce90528ecf3a9dc25b9cbc1471446c2f6f8b44e623809fbfa2cfc761","first_computed_at":"2026-07-05T06:16:27.105944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:16:27.105944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6oFhMbXfXAmxvgybY+tGR1WGvTrWX7CsVUMhDgsbieFoIqsmKhB8O7bexeGitO6RB0oNCIQ4LFFDXN97LGBFCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:16:27.106382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.00489","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1096e70e24f88be0e5a0a45817627e5dac6927c68bc7917becce25ae68b66840","sha256:d439678a6ae6426fc83717c7e5cbe7c494164abec0c688c61546838965daff4c"],"state_sha256":"4425741db487fc105f400089408d0c37431d6d6fcd3005d8b4efcbf5c6afbad1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VG58IdkGsykUaM+Xy8If9VduSE0h/QvGtzvNN6e6Tf3d4C6th1ngrZZTmEpAaBTW6P4CobODThgtmuBTUkX9Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T13:26:21.344432Z","bundle_sha256":"eefb1964bfed6400a49437ba0dc759c838b6a75b7e45a0cf0c738786c5c624c4"}}