{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:P5NZSWFLJJYNFTI3ZRZT3L7YCK","short_pith_number":"pith:P5NZSWFL","schema_version":"1.0","canonical_sha256":"7f5b9958ab4a70d2cd1bcc733daff812bda17a58bd8c63f342b21d142109f1bb","source":{"kind":"arxiv","id":"2311.12631","version":3},"attestation_state":"computed","paper":{"title":"GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiancheng Huang, Jianzhuang Liu, Jiaxi Lv, Mingfu Yan, Shifeng Chen, Xiaoxin Chen, Yafei Wen, Yifan Liu, Yi Huang","submitted_at":"2023-11-21T14:24:37Z","abstract_excerpt":"Recent advances in text-to-video generation have harnessed the power of diffusion models to create visually compelling content conditioned on text prompts. However, they usually encounter high computational costs and often struggle to produce videos with coherent physical motions. To tackle these issues, we propose GPT4Motion, a training-free framework that leverages the planning capability of large language models such as GPT, the physical simulation strength of Blender, and the excellent image generation ability of text-to-image diffusion models to enhance the quality of video synthesis. Spe"},"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":"2311.12631","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-21T14:24:37Z","cross_cats_sorted":[],"title_canon_sha256":"1fa9d643daafc63ba037c24a2a71cdb110121417b03d962ccc70d4159f82d49c","abstract_canon_sha256":"ecee6ac2835b676fb0812938ee168dadc63c614cd8d95e4bbc963ea7d057f295"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:58.757763Z","signature_b64":"6at9Uh6cqnsm4XFEtWFmchk118d9xL55ljInOK1FrurP8oT9LqrVE4z4Ex86Sy1B/iDixYu58lcdlg4bdCLtAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f5b9958ab4a70d2cd1bcc733daff812bda17a58bd8c63f342b21d142109f1bb","last_reissued_at":"2026-07-05T08:10:58.757344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:58.757344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiancheng Huang, Jianzhuang Liu, Jiaxi Lv, Mingfu Yan, Shifeng Chen, Xiaoxin Chen, Yafei Wen, Yifan Liu, Yi Huang","submitted_at":"2023-11-21T14:24:37Z","abstract_excerpt":"Recent advances in text-to-video generation have harnessed the power of diffusion models to create visually compelling content conditioned on text prompts. However, they usually encounter high computational costs and often struggle to produce videos with coherent physical motions. To tackle these issues, we propose GPT4Motion, a training-free framework that leverages the planning capability of large language models such as GPT, the physical simulation strength of Blender, and the excellent image generation ability of text-to-image diffusion models to enhance the quality of video synthesis. Spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12631","kind":"arxiv","version":3},"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/2311.12631/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":"2311.12631","created_at":"2026-07-05T08:10:58.757403+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.12631v3","created_at":"2026-07-05T08:10:58.757403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12631","created_at":"2026-07-05T08:10:58.757403+00:00"},{"alias_kind":"pith_short_12","alias_value":"P5NZSWFLJJYN","created_at":"2026-07-05T08:10:58.757403+00:00"},{"alias_kind":"pith_short_16","alias_value":"P5NZSWFLJJYNFTI3","created_at":"2026-07-05T08:10:58.757403+00:00"},{"alias_kind":"pith_short_8","alias_value":"P5NZSWFL","created_at":"2026-07-05T08:10:58.757403+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.13294","citing_title":"VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P5NZSWFLJJYNFTI3ZRZT3L7YCK","json":"https://pith.science/pith/P5NZSWFLJJYNFTI3ZRZT3L7YCK.json","graph_json":"https://pith.science/api/pith-number/P5NZSWFLJJYNFTI3ZRZT3L7YCK/graph.json","events_json":"https://pith.science/api/pith-number/P5NZSWFLJJYNFTI3ZRZT3L7YCK/events.json","paper":"https://pith.science/paper/P5NZSWFL"},"agent_actions":{"view_html":"https://pith.science/pith/P5NZSWFLJJYNFTI3ZRZT3L7YCK","download_json":"https://pith.science/pith/P5NZSWFLJJYNFTI3ZRZT3L7YCK.json","view_paper":"https://pith.science/paper/P5NZSWFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.12631&json=true","fetch_graph":"https://pith.science/api/pith-number/P5NZSWFLJJYNFTI3ZRZT3L7YCK/graph.json","fetch_events":"https://pith.science/api/pith-number/P5NZSWFLJJYNFTI3ZRZT3L7YCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P5NZSWFLJJYNFTI3ZRZT3L7YCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P5NZSWFLJJYNFTI3ZRZT3L7YCK/action/storage_attestation","attest_author":"https://pith.science/pith/P5NZSWFLJJYNFTI3ZRZT3L7YCK/action/author_attestation","sign_citation":"https://pith.science/pith/P5NZSWFLJJYNFTI3ZRZT3L7YCK/action/citation_signature","submit_replication":"https://pith.science/pith/P5NZSWFLJJYNFTI3ZRZT3L7YCK/action/replication_record"}},"created_at":"2026-07-05T08:10:58.757403+00:00","updated_at":"2026-07-05T08:10:58.757403+00:00"}