{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SEUK7SC5BJ6SSM42Y3PJRHI4VX","short_pith_number":"pith:SEUK7SC5","schema_version":"1.0","canonical_sha256":"9128afc85d0a7d29339ac6de989d1caddcb5eb36a223f187ed3f4527862ecc53","source":{"kind":"arxiv","id":"2506.17301","version":2},"attestation_state":"computed","paper":{"title":"FramePrompt: In-context Controllable Animation with Zero Structural Changes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.GR","authors_text":"Guian Fang, Mike Zheng Shou, Yuchao Gu","submitted_at":"2025-06-17T22:06:20Z","abstract_excerpt":"Generating controllable character animation from a reference image and motion guidance remains a challenging task due to the inherent difficulty of injecting appearance and motion cues into video diffusion models. Prior works often rely on complex architectures, explicit guider modules, or multi-stage processing pipelines, which increase structural overhead and hinder deployment. Inspired by the strong visual context modeling capacity of pre-trained video diffusion transformers, we propose FramePrompt, a minimalist yet powerful framework that treats reference images, skeleton-guided motion, an"},"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":"2506.17301","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2025-06-17T22:06:20Z","cross_cats_sorted":[],"title_canon_sha256":"bb24ccdf85771deade9589a1ac838988e377348267279506b06735f8ccd450ae","abstract_canon_sha256":"4e4cf3229f184fd8fefc809c1665f69a3dd3a1b52a0169d5446ff07368fc64e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:44.942958Z","signature_b64":"SVp9vVpjmLYu9kwQ4Y41pBUXUE+hafHWOMtAc4TUE2H3/UAb2hbq9kCdG+oenhnjksk4C8FWum7FmqirzGhXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9128afc85d0a7d29339ac6de989d1caddcb5eb36a223f187ed3f4527862ecc53","last_reissued_at":"2026-07-05T11:30:44.942439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:44.942439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FramePrompt: In-context Controllable Animation with Zero Structural Changes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.GR","authors_text":"Guian Fang, Mike Zheng Shou, Yuchao Gu","submitted_at":"2025-06-17T22:06:20Z","abstract_excerpt":"Generating controllable character animation from a reference image and motion guidance remains a challenging task due to the inherent difficulty of injecting appearance and motion cues into video diffusion models. Prior works often rely on complex architectures, explicit guider modules, or multi-stage processing pipelines, which increase structural overhead and hinder deployment. Inspired by the strong visual context modeling capacity of pre-trained video diffusion transformers, we propose FramePrompt, a minimalist yet powerful framework that treats reference images, skeleton-guided motion, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17301","kind":"arxiv","version":2},"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/2506.17301/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":"2506.17301","created_at":"2026-07-05T11:30:44.942501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.17301v2","created_at":"2026-07-05T11:30:44.942501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17301","created_at":"2026-07-05T11:30:44.942501+00:00"},{"alias_kind":"pith_short_12","alias_value":"SEUK7SC5BJ6S","created_at":"2026-07-05T11:30:44.942501+00:00"},{"alias_kind":"pith_short_16","alias_value":"SEUK7SC5BJ6SSM42","created_at":"2026-07-05T11:30:44.942501+00:00"},{"alias_kind":"pith_short_8","alias_value":"SEUK7SC5","created_at":"2026-07-05T11:30:44.942501+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17423","citing_title":"Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SEUK7SC5BJ6SSM42Y3PJRHI4VX","json":"https://pith.science/pith/SEUK7SC5BJ6SSM42Y3PJRHI4VX.json","graph_json":"https://pith.science/api/pith-number/SEUK7SC5BJ6SSM42Y3PJRHI4VX/graph.json","events_json":"https://pith.science/api/pith-number/SEUK7SC5BJ6SSM42Y3PJRHI4VX/events.json","paper":"https://pith.science/paper/SEUK7SC5"},"agent_actions":{"view_html":"https://pith.science/pith/SEUK7SC5BJ6SSM42Y3PJRHI4VX","download_json":"https://pith.science/pith/SEUK7SC5BJ6SSM42Y3PJRHI4VX.json","view_paper":"https://pith.science/paper/SEUK7SC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.17301&json=true","fetch_graph":"https://pith.science/api/pith-number/SEUK7SC5BJ6SSM42Y3PJRHI4VX/graph.json","fetch_events":"https://pith.science/api/pith-number/SEUK7SC5BJ6SSM42Y3PJRHI4VX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SEUK7SC5BJ6SSM42Y3PJRHI4VX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SEUK7SC5BJ6SSM42Y3PJRHI4VX/action/storage_attestation","attest_author":"https://pith.science/pith/SEUK7SC5BJ6SSM42Y3PJRHI4VX/action/author_attestation","sign_citation":"https://pith.science/pith/SEUK7SC5BJ6SSM42Y3PJRHI4VX/action/citation_signature","submit_replication":"https://pith.science/pith/SEUK7SC5BJ6SSM42Y3PJRHI4VX/action/replication_record"}},"created_at":"2026-07-05T11:30:44.942501+00:00","updated_at":"2026-07-05T11:30:44.942501+00:00"}