{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PW242HYTT634F5JTLHF6URLWNQ","short_pith_number":"pith:PW242HYT","canonical_record":{"source":{"id":"2608.15690","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-16T11:40:20Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"66055f8e9bea9f21a0dee839f43c6313567c13f6a2a87f23a345f969bc8d6adf","abstract_canon_sha256":"d7f67596d7a0a5de1a1f22536c98cea2b750ec4c5d0a703639f83ce1cf6ea6c4"},"schema_version":"1.0"},"canonical_sha256":"7db5cd1f139fb7c2f53359cbea45766c0bd86e6c3895ea530480ac95d1fa50f1","source":{"kind":"arxiv","id":"2608.15690","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.15690","created_at":"2026-08-18T01:15:59Z"},{"alias_kind":"arxiv_version","alias_value":"2608.15690v1","created_at":"2026-08-18T01:15:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.15690","created_at":"2026-08-18T01:15:59Z"},{"alias_kind":"pith_short_12","alias_value":"PW242HYTT634","created_at":"2026-08-18T01:15:59Z"},{"alias_kind":"pith_short_16","alias_value":"PW242HYTT634F5JT","created_at":"2026-08-18T01:15:59Z"},{"alias_kind":"pith_short_8","alias_value":"PW242HYT","created_at":"2026-08-18T01:15:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PW242HYTT634F5JTLHF6URLWNQ","target":"record","payload":{"canonical_record":{"source":{"id":"2608.15690","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-16T11:40:20Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"66055f8e9bea9f21a0dee839f43c6313567c13f6a2a87f23a345f969bc8d6adf","abstract_canon_sha256":"d7f67596d7a0a5de1a1f22536c98cea2b750ec4c5d0a703639f83ce1cf6ea6c4"},"schema_version":"1.0"},"canonical_sha256":"7db5cd1f139fb7c2f53359cbea45766c0bd86e6c3895ea530480ac95d1fa50f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-18T01:15:59.302271Z","signature_b64":"own0Qpp9MJ2+tGUR/ncfy1JtL4Et8FNx/SpBk1vVok/HYrId/IBVp2x82OQMCmauYsCPt2yrYVMa9iDXaI51AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7db5cd1f139fb7c2f53359cbea45766c0bd86e6c3895ea530480ac95d1fa50f1","last_reissued_at":"2026-08-18T01:15:59.300789Z","signature_status":"signed_v1","first_computed_at":"2026-08-18T01:15:59.300789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.15690","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":"2026-08-18T01:15:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EV2USD9gJ4wJiGvQfwLhFtRsgcGQSnjAaf2jZb0jRPfVw+jUEKJMThK5B1ofJFPm2KO9cu3pVGATctG5adrwAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T10:04:09.493991Z"},"content_sha256":"bfea7ec6e2f682a50ab533925ffce9db58efbb57655363e372990df319e14985","schema_version":"1.0","event_id":"sha256:bfea7ec6e2f682a50ab533925ffce9db58efbb57655363e372990df319e14985"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PW242HYTT634F5JTLHF6URLWNQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adding Voice Cloning to Text-to-Audio-Video Models with a Single Zero-Initialised Layer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.SD","authors_text":"Alexey Letunovskiy, Anna Dmitrienko, Denis Dimitrov, Ivan Kirillov, Ivan Mikheev, Kirill Chernyshev, Viacheslav Vasilev","submitted_at":"2026-08-16T11:40:20Z","abstract_excerpt":"Text-to-audio-video (T2AV) generation models produce a video and its soundtrack from a textual description, but offer no control over whose voice speaks in the output. We show that a base T2AV model can be turned into a voice-cloning model by adding a single zero-initialized linear layer on top of its audio backbone, fine-tuning for a comparatively short training schedule, and conditioning on a short reference recording at inference time. The reference is injected through two complementary signals: its diffusion latents are prepended to the audio stream, and a global speaker embedding modulate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.15690","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/2608.15690/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":"2026-08-18T01:15:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cl/Ns4da+Uo9Z/vLohFHiCZIfa0VgRBz224zNGvn4mnxc7DQzZqkzU42LKbZh0O3503AtDdREO1fYJSMm3VmAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T10:04:09.494511Z"},"content_sha256":"614ef951bef5948bdf61748c07382b86d73bc60d783707a18ac21531e685ea5f","schema_version":"1.0","event_id":"sha256:614ef951bef5948bdf61748c07382b86d73bc60d783707a18ac21531e685ea5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PW242HYTT634F5JTLHF6URLWNQ/bundle.json","state_url":"https://pith.science/pith/PW242HYTT634F5JTLHF6URLWNQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PW242HYTT634F5JTLHF6URLWNQ/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":"2026-08-21T10:04:09Z","links":{"resolver":"https://pith.science/pith/PW242HYTT634F5JTLHF6URLWNQ","bundle":"https://pith.science/pith/PW242HYTT634F5JTLHF6URLWNQ/bundle.json","state":"https://pith.science/pith/PW242HYTT634F5JTLHF6URLWNQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PW242HYTT634F5JTLHF6URLWNQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PW242HYTT634F5JTLHF6URLWNQ","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":"d7f67596d7a0a5de1a1f22536c98cea2b750ec4c5d0a703639f83ce1cf6ea6c4","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-16T11:40:20Z","title_canon_sha256":"66055f8e9bea9f21a0dee839f43c6313567c13f6a2a87f23a345f969bc8d6adf"},"schema_version":"1.0","source":{"id":"2608.15690","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.15690","created_at":"2026-08-18T01:15:59Z"},{"alias_kind":"arxiv_version","alias_value":"2608.15690v1","created_at":"2026-08-18T01:15:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.15690","created_at":"2026-08-18T01:15:59Z"},{"alias_kind":"pith_short_12","alias_value":"PW242HYTT634","created_at":"2026-08-18T01:15:59Z"},{"alias_kind":"pith_short_16","alias_value":"PW242HYTT634F5JT","created_at":"2026-08-18T01:15:59Z"},{"alias_kind":"pith_short_8","alias_value":"PW242HYT","created_at":"2026-08-18T01:15:59Z"}],"graph_snapshots":[{"event_id":"sha256:614ef951bef5948bdf61748c07382b86d73bc60d783707a18ac21531e685ea5f","target":"graph","created_at":"2026-08-18T01:15:59Z","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/2608.15690/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-audio-video (T2AV) generation models produce a video and its soundtrack from a textual description, but offer no control over whose voice speaks in the output. We show that a base T2AV model can be turned into a voice-cloning model by adding a single zero-initialized linear layer on top of its audio backbone, fine-tuning for a comparatively short training schedule, and conditioning on a short reference recording at inference time. The reference is injected through two complementary signals: its diffusion latents are prepended to the audio stream, and a global speaker embedding modulate","authors_text":"Alexey Letunovskiy, Anna Dmitrienko, Denis Dimitrov, Ivan Kirillov, Ivan Mikheev, Kirill Chernyshev, Viacheslav Vasilev","cross_cats":["cs.AI","cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-16T11:40:20Z","title":"Adding Voice Cloning to Text-to-Audio-Video Models with a Single Zero-Initialised Layer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.15690","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:bfea7ec6e2f682a50ab533925ffce9db58efbb57655363e372990df319e14985","target":"record","created_at":"2026-08-18T01:15:59Z","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":"d7f67596d7a0a5de1a1f22536c98cea2b750ec4c5d0a703639f83ce1cf6ea6c4","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-16T11:40:20Z","title_canon_sha256":"66055f8e9bea9f21a0dee839f43c6313567c13f6a2a87f23a345f969bc8d6adf"},"schema_version":"1.0","source":{"id":"2608.15690","kind":"arxiv","version":1}},"canonical_sha256":"7db5cd1f139fb7c2f53359cbea45766c0bd86e6c3895ea530480ac95d1fa50f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7db5cd1f139fb7c2f53359cbea45766c0bd86e6c3895ea530480ac95d1fa50f1","first_computed_at":"2026-08-18T01:15:59.300789Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-18T01:15:59.300789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"own0Qpp9MJ2+tGUR/ncfy1JtL4Et8FNx/SpBk1vVok/HYrId/IBVp2x82OQMCmauYsCPt2yrYVMa9iDXaI51AA==","signature_status":"signed_v1","signed_at":"2026-08-18T01:15:59.302271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.15690","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfea7ec6e2f682a50ab533925ffce9db58efbb57655363e372990df319e14985","sha256:614ef951bef5948bdf61748c07382b86d73bc60d783707a18ac21531e685ea5f"],"state_sha256":"4e368cd0818cbbb9c77d70ec5b280810460fada93daf135ecde9a3f61f15203d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Fygk55VeECuqc59/MdMaGmv/AAT7WkE3AdvbEUJvhjo3p26lk6qCp7QLz3R8pA8GHlL8JWuObBu1w2oUSkcDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T10:04:09.498992Z","bundle_sha256":"bb4034d31c5df06ca84bca3279bcc95e524ca61f6a8fa8766a99cbc538561383"}}