{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TQ2FOUJADFI4E3BJ2X6LQ24EPY","short_pith_number":"pith:TQ2FOUJA","schema_version":"1.0","canonical_sha256":"9c345751201951c26c29d5fcb86b847e34ccc93b3ebe6be49d74dbbeedd01a6d","source":{"kind":"arxiv","id":"2408.09787","version":1},"attestation_state":"computed","paper":{"title":"Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.MM"],"primary_cat":"cs.CL","authors_text":"Baotian Hu, Haoyuan Shi, Jiashun Zhu, Jinyi Xu, Longyue Wang, Min Zhang, Yunxin Li, Zhen Zhao","submitted_at":"2024-08-19T08:27:31Z","abstract_excerpt":"Traditional animation generation methods depend on training generative models with human-labelled data, entailing a sophisticated multi-stage pipeline that demands substantial human effort and incurs high training costs. Due to limited prompting plans, these methods typically produce brief, information-poor, and context-incoherent animations. To overcome these limitations and automate the animation process, we pioneer the introduction of large multimodal models (LMMs) as the core processor to build an autonomous animation-making agent, named Anim-Director. This agent mainly harnesses the advan"},"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":"2408.09787","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-19T08:27:31Z","cross_cats_sorted":["cs.CV","cs.MM"],"title_canon_sha256":"0420b648ec5aff7c030206c2e8bc1a7e71a3cf8d809e8481a74a60cd9242cd53","abstract_canon_sha256":"c32a0514a0c7c66a8eff99aef47fa8867e9c33667c0a5f2d50be5261f920e9e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:37.161865Z","signature_b64":"/gFwpWDjw9kcvGkEkQ0UNM2fp5HXLqrZwOfroxU7B4BF1n1/muczcLEnGEdgvOdcuWLETjg+2+1DeS8S0A7MAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c345751201951c26c29d5fcb86b847e34ccc93b3ebe6be49d74dbbeedd01a6d","last_reissued_at":"2026-07-05T08:56:37.161375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:37.161375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.MM"],"primary_cat":"cs.CL","authors_text":"Baotian Hu, Haoyuan Shi, Jiashun Zhu, Jinyi Xu, Longyue Wang, Min Zhang, Yunxin Li, Zhen Zhao","submitted_at":"2024-08-19T08:27:31Z","abstract_excerpt":"Traditional animation generation methods depend on training generative models with human-labelled data, entailing a sophisticated multi-stage pipeline that demands substantial human effort and incurs high training costs. Due to limited prompting plans, these methods typically produce brief, information-poor, and context-incoherent animations. To overcome these limitations and automate the animation process, we pioneer the introduction of large multimodal models (LMMs) as the core processor to build an autonomous animation-making agent, named Anim-Director. This agent mainly harnesses the advan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09787","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/2408.09787/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":"2408.09787","created_at":"2026-07-05T08:56:37.161433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09787v1","created_at":"2026-07-05T08:56:37.161433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09787","created_at":"2026-07-05T08:56:37.161433+00:00"},{"alias_kind":"pith_short_12","alias_value":"TQ2FOUJADFI4","created_at":"2026-07-05T08:56:37.161433+00:00"},{"alias_kind":"pith_short_16","alias_value":"TQ2FOUJADFI4E3BJ","created_at":"2026-07-05T08:56:37.161433+00:00"},{"alias_kind":"pith_short_8","alias_value":"TQ2FOUJA","created_at":"2026-07-05T08:56:37.161433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25318","citing_title":"Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TQ2FOUJADFI4E3BJ2X6LQ24EPY","json":"https://pith.science/pith/TQ2FOUJADFI4E3BJ2X6LQ24EPY.json","graph_json":"https://pith.science/api/pith-number/TQ2FOUJADFI4E3BJ2X6LQ24EPY/graph.json","events_json":"https://pith.science/api/pith-number/TQ2FOUJADFI4E3BJ2X6LQ24EPY/events.json","paper":"https://pith.science/paper/TQ2FOUJA"},"agent_actions":{"view_html":"https://pith.science/pith/TQ2FOUJADFI4E3BJ2X6LQ24EPY","download_json":"https://pith.science/pith/TQ2FOUJADFI4E3BJ2X6LQ24EPY.json","view_paper":"https://pith.science/paper/TQ2FOUJA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09787&json=true","fetch_graph":"https://pith.science/api/pith-number/TQ2FOUJADFI4E3BJ2X6LQ24EPY/graph.json","fetch_events":"https://pith.science/api/pith-number/TQ2FOUJADFI4E3BJ2X6LQ24EPY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TQ2FOUJADFI4E3BJ2X6LQ24EPY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TQ2FOUJADFI4E3BJ2X6LQ24EPY/action/storage_attestation","attest_author":"https://pith.science/pith/TQ2FOUJADFI4E3BJ2X6LQ24EPY/action/author_attestation","sign_citation":"https://pith.science/pith/TQ2FOUJADFI4E3BJ2X6LQ24EPY/action/citation_signature","submit_replication":"https://pith.science/pith/TQ2FOUJADFI4E3BJ2X6LQ24EPY/action/replication_record"}},"created_at":"2026-07-05T08:56:37.161433+00:00","updated_at":"2026-07-05T08:56:37.161433+00:00"}