{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DVT6QXLD7XDT5OS6SO4RD74DZE","short_pith_number":"pith:DVT6QXLD","schema_version":"1.0","canonical_sha256":"1d67e85d63fdc73eba5e93b911ff83c91a613543c6ba81ceb7299eff6d2d386a","source":{"kind":"arxiv","id":"2509.02278","version":1},"attestation_state":"computed","paper":{"title":"Think2Sing: Orchestrating Structured Motion Subtitles for Singing-Driven 3D Head Animation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.GR","authors_text":"Cheng Xu, Jing Qin, Shengfeng He, Xiaofen Xing, Xuemiao Xu, Yihan Zhou, Zikai Huang","submitted_at":"2025-09-02T12:59:27Z","abstract_excerpt":"Singing-driven 3D head animation is a challenging yet promising task with applications in virtual avatars, entertainment, and education. Unlike speech, singing involves richer emotional nuance, dynamic prosody, and lyric-based semantics, requiring the synthesis of fine-grained, temporally coherent facial motion. Existing speech-driven approaches often produce oversimplified, emotionally flat, and semantically inconsistent results, which are insufficient for singing animation. To address this, we propose Think2Sing, a diffusion-based framework that leverages pretrained large language models to "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.02278","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.GR","submitted_at":"2025-09-02T12:59:27Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"5041fcc6a2da302ef2dceb3d2b4a2470b76e7c839da0d2d3cc8ade80e060b4b2","abstract_canon_sha256":"5826011b31fdf296e23d339d7993ed79b81ebda63321b8b265318bd2d0bc6761"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:35.406218Z","signature_b64":"YRa4SvuNvWiNdDHlS0a4dw1KhVkKm5OtJ1cLR8U+21dhOvpmwxunrwm+KeLJHR7EY5NvT9ZnamU2yD4GmPYoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d67e85d63fdc73eba5e93b911ff83c91a613543c6ba81ceb7299eff6d2d386a","last_reissued_at":"2026-07-05T12:03:35.405745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:35.405745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Think2Sing: Orchestrating Structured Motion Subtitles for Singing-Driven 3D Head Animation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.GR","authors_text":"Cheng Xu, Jing Qin, Shengfeng He, Xiaofen Xing, Xuemiao Xu, Yihan Zhou, Zikai Huang","submitted_at":"2025-09-02T12:59:27Z","abstract_excerpt":"Singing-driven 3D head animation is a challenging yet promising task with applications in virtual avatars, entertainment, and education. Unlike speech, singing involves richer emotional nuance, dynamic prosody, and lyric-based semantics, requiring the synthesis of fine-grained, temporally coherent facial motion. Existing speech-driven approaches often produce oversimplified, emotionally flat, and semantically inconsistent results, which are insufficient for singing animation. To address this, we propose Think2Sing, a diffusion-based framework that leverages pretrained large language models to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02278","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/2509.02278/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.02278","created_at":"2026-07-05T12:03:35.405812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.02278v1","created_at":"2026-07-05T12:03:35.405812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02278","created_at":"2026-07-05T12:03:35.405812+00:00"},{"alias_kind":"pith_short_12","alias_value":"DVT6QXLD7XDT","created_at":"2026-07-05T12:03:35.405812+00:00"},{"alias_kind":"pith_short_16","alias_value":"DVT6QXLD7XDT5OS6","created_at":"2026-07-05T12:03:35.405812+00:00"},{"alias_kind":"pith_short_8","alias_value":"DVT6QXLD","created_at":"2026-07-05T12:03:35.405812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DVT6QXLD7XDT5OS6SO4RD74DZE","json":"https://pith.science/pith/DVT6QXLD7XDT5OS6SO4RD74DZE.json","graph_json":"https://pith.science/api/pith-number/DVT6QXLD7XDT5OS6SO4RD74DZE/graph.json","events_json":"https://pith.science/api/pith-number/DVT6QXLD7XDT5OS6SO4RD74DZE/events.json","paper":"https://pith.science/paper/DVT6QXLD"},"agent_actions":{"view_html":"https://pith.science/pith/DVT6QXLD7XDT5OS6SO4RD74DZE","download_json":"https://pith.science/pith/DVT6QXLD7XDT5OS6SO4RD74DZE.json","view_paper":"https://pith.science/paper/DVT6QXLD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.02278&json=true","fetch_graph":"https://pith.science/api/pith-number/DVT6QXLD7XDT5OS6SO4RD74DZE/graph.json","fetch_events":"https://pith.science/api/pith-number/DVT6QXLD7XDT5OS6SO4RD74DZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DVT6QXLD7XDT5OS6SO4RD74DZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DVT6QXLD7XDT5OS6SO4RD74DZE/action/storage_attestation","attest_author":"https://pith.science/pith/DVT6QXLD7XDT5OS6SO4RD74DZE/action/author_attestation","sign_citation":"https://pith.science/pith/DVT6QXLD7XDT5OS6SO4RD74DZE/action/citation_signature","submit_replication":"https://pith.science/pith/DVT6QXLD7XDT5OS6SO4RD74DZE/action/replication_record"}},"created_at":"2026-07-05T12:03:35.405812+00:00","updated_at":"2026-07-05T12:03:35.405812+00:00"}