{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JSM6F2K5DBOW3AT5EABE5EWWND","short_pith_number":"pith:JSM6F2K5","canonical_record":{"source":{"id":"2412.03430","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T16:19:47Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"e819a9ff62bd96e779ed4b3556cbe357a83f6bf6725c525cffe19a8e61609e3d","abstract_canon_sha256":"f372f5a5809df22c19f7f75c1f1781d7bc48eed232c93536eb8fb7f8ed60ec5c"},"schema_version":"1.0"},"canonical_sha256":"4c99e2e95d185d6d827d20024e92d668d8d389ddbf0114234ad11447484602b1","source":{"kind":"arxiv","id":"2412.03430","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03430","created_at":"2026-07-05T09:44:29Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03430v1","created_at":"2026-07-05T09:44:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03430","created_at":"2026-07-05T09:44:29Z"},{"alias_kind":"pith_short_12","alias_value":"JSM6F2K5DBOW","created_at":"2026-07-05T09:44:29Z"},{"alias_kind":"pith_short_16","alias_value":"JSM6F2K5DBOW3AT5","created_at":"2026-07-05T09:44:29Z"},{"alias_kind":"pith_short_8","alias_value":"JSM6F2K5","created_at":"2026-07-05T09:44:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JSM6F2K5DBOW3AT5EABE5EWWND","target":"record","payload":{"canonical_record":{"source":{"id":"2412.03430","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T16:19:47Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"e819a9ff62bd96e779ed4b3556cbe357a83f6bf6725c525cffe19a8e61609e3d","abstract_canon_sha256":"f372f5a5809df22c19f7f75c1f1781d7bc48eed232c93536eb8fb7f8ed60ec5c"},"schema_version":"1.0"},"canonical_sha256":"4c99e2e95d185d6d827d20024e92d668d8d389ddbf0114234ad11447484602b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:29.408768Z","signature_b64":"2PHmZv8S1CprisgzHQkpavcSE2f/0DLEheHyUGog40BMzRHiRhYGvxI14CbNjw40jbJml9aDERqOkkiylyX2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c99e2e95d185d6d827d20024e92d668d8d389ddbf0114234ad11447484602b1","last_reissued_at":"2026-07-05T09:44:29.408282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:29.408282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.03430","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":"2026-07-05T09:44:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H5U4HqSXTeIiRDzoBYRtnH6ZnlhJaPL2X/3AhV3QRDS/eDF3gZvW49QjT6PXlSl5qC3oOU0OrNqy/L6VVvLfCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:22:37.475916Z"},"content_sha256":"a3ec2e61dcead6fdebec2fff9cd7a8a388ae4f25626708296939df0926aa5e84","schema_version":"1.0","event_id":"sha256:a3ec2e61dcead6fdebec2fff9cd7a8a388ae4f25626708296939df0926aa5e84"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JSM6F2K5DBOW3AT5EABE5EWWND","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SINGER: Vivid Audio-driven Singing Video Generation with Multi-scale Spectral Diffusion Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"cs.CV","authors_text":"Wei Xue, Wenhan Luo, Yan Li, Yike Guo, Zhiqiang Wang, Ziya Zhou","submitted_at":"2024-12-04T16:19:47Z","abstract_excerpt":"Recent advancements in generative models have significantly enhanced talking face video generation, yet singing video generation remains underexplored. The differences between human talking and singing limit the performance of existing talking face video generation models when applied to singing. The fundamental differences between talking and singing-specifically in audio characteristics and behavioral expressions-limit the effectiveness of existing models. We observe that the differences between singing and talking audios manifest in terms of frequency and amplitude. To address this, we have"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03430","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/2412.03430/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":"2026-07-05T09:44:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/A5wFiVYrazXGz84jBcp6mcm2mZx7pL4Hn1iCAIUl9Zn1WHcEW/YL97FTudFohrxRTShcOaP3VUDyv2CpneMCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:22:37.476898Z"},"content_sha256":"8d5dafa6af8326fe924209e083451c455335987fd0f410db2b76b390f2727ac0","schema_version":"1.0","event_id":"sha256:8d5dafa6af8326fe924209e083451c455335987fd0f410db2b76b390f2727ac0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JSM6F2K5DBOW3AT5EABE5EWWND/bundle.json","state_url":"https://pith.science/pith/JSM6F2K5DBOW3AT5EABE5EWWND/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JSM6F2K5DBOW3AT5EABE5EWWND/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":"2026-08-08T10:22:37Z","links":{"resolver":"https://pith.science/pith/JSM6F2K5DBOW3AT5EABE5EWWND","bundle":"https://pith.science/pith/JSM6F2K5DBOW3AT5EABE5EWWND/bundle.json","state":"https://pith.science/pith/JSM6F2K5DBOW3AT5EABE5EWWND/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JSM6F2K5DBOW3AT5EABE5EWWND/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JSM6F2K5DBOW3AT5EABE5EWWND","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":"f372f5a5809df22c19f7f75c1f1781d7bc48eed232c93536eb8fb7f8ed60ec5c","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T16:19:47Z","title_canon_sha256":"e819a9ff62bd96e779ed4b3556cbe357a83f6bf6725c525cffe19a8e61609e3d"},"schema_version":"1.0","source":{"id":"2412.03430","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03430","created_at":"2026-07-05T09:44:29Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03430v1","created_at":"2026-07-05T09:44:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03430","created_at":"2026-07-05T09:44:29Z"},{"alias_kind":"pith_short_12","alias_value":"JSM6F2K5DBOW","created_at":"2026-07-05T09:44:29Z"},{"alias_kind":"pith_short_16","alias_value":"JSM6F2K5DBOW3AT5","created_at":"2026-07-05T09:44:29Z"},{"alias_kind":"pith_short_8","alias_value":"JSM6F2K5","created_at":"2026-07-05T09:44:29Z"}],"graph_snapshots":[{"event_id":"sha256:8d5dafa6af8326fe924209e083451c455335987fd0f410db2b76b390f2727ac0","target":"graph","created_at":"2026-07-05T09:44:29Z","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/2412.03430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in generative models have significantly enhanced talking face video generation, yet singing video generation remains underexplored. The differences between human talking and singing limit the performance of existing talking face video generation models when applied to singing. The fundamental differences between talking and singing-specifically in audio characteristics and behavioral expressions-limit the effectiveness of existing models. We observe that the differences between singing and talking audios manifest in terms of frequency and amplitude. To address this, we have","authors_text":"Wei Xue, Wenhan Luo, Yan Li, Yike Guo, Zhiqiang Wang, Ziya Zhou","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T16:19:47Z","title":"SINGER: Vivid Audio-driven Singing Video Generation with Multi-scale Spectral Diffusion Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03430","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:a3ec2e61dcead6fdebec2fff9cd7a8a388ae4f25626708296939df0926aa5e84","target":"record","created_at":"2026-07-05T09:44:29Z","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":"f372f5a5809df22c19f7f75c1f1781d7bc48eed232c93536eb8fb7f8ed60ec5c","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T16:19:47Z","title_canon_sha256":"e819a9ff62bd96e779ed4b3556cbe357a83f6bf6725c525cffe19a8e61609e3d"},"schema_version":"1.0","source":{"id":"2412.03430","kind":"arxiv","version":1}},"canonical_sha256":"4c99e2e95d185d6d827d20024e92d668d8d389ddbf0114234ad11447484602b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c99e2e95d185d6d827d20024e92d668d8d389ddbf0114234ad11447484602b1","first_computed_at":"2026-07-05T09:44:29.408282Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:29.408282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2PHmZv8S1CprisgzHQkpavcSE2f/0DLEheHyUGog40BMzRHiRhYGvxI14CbNjw40jbJml9aDERqOkkiylyX2CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:29.408768Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03430","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3ec2e61dcead6fdebec2fff9cd7a8a388ae4f25626708296939df0926aa5e84","sha256:8d5dafa6af8326fe924209e083451c455335987fd0f410db2b76b390f2727ac0"],"state_sha256":"70c2a800da0e8cedc7ea3b4dbf0986447d5c629829c2fc4a45e42befeaea826c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"61Iht1iTKbAgHSsXQY+yIHqbQi0mvEd8IATn8B5HnKJ50syUluZQ/L07Tgnwbp9GTpsAwNofQsrzuz8lXz/bDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T10:22:37.488755Z","bundle_sha256":"a141ddd128f79a5d53a395c95ab4976b8750af1fe7e52a8e330542eeb6f08cea"}}