{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OXRFZYOYKGBTEBSQA6QG4LV7BM","short_pith_number":"pith:OXRFZYOY","schema_version":"1.0","canonical_sha256":"75e25ce1d8518332065007a06e2ebf0b19b85e93322f81f11668dd660476b79f","source":{"kind":"arxiv","id":"2405.14864","version":3},"attestation_state":"computed","paper":{"title":"Video Diffusion Models are Training-free Motion Interpreter and Controller","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shuai Yang, Xingang Pan, Yifan Zhou, Zeqi Xiao","submitted_at":"2024-05-23T17:59:40Z","abstract_excerpt":"Video generation primarily aims to model authentic and customized motion across frames, making understanding and controlling the motion a crucial topic. Most diffusion-based studies on video motion focus on motion customization with training-based paradigms, which, however, demands substantial training resources and necessitates retraining for diverse models. Crucially, these approaches do not explore how video diffusion models encode cross-frame motion information in their features, lacking interpretability and transparency in their effectiveness. To answer this question, this paper introduce"},"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":"2405.14864","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T17:59:40Z","cross_cats_sorted":[],"title_canon_sha256":"bbbd21b02c350b618883e5846a1acfbb24adc9c8b1fc4b46f9643306d4414e2d","abstract_canon_sha256":"4ea54094517fc80a1df055bd3efaff8155d79d56e8ce8e771532e7a29872d670"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:14.023335Z","signature_b64":"wZtX/lm8bX5vxmZo891OdEEOBcaqiTtTaLLt8Rv0oNEEnDMsfk9Yj8KGZjIe4Gtnd/ZFDAKU/dKiD7PLIUkuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75e25ce1d8518332065007a06e2ebf0b19b85e93322f81f11668dd660476b79f","last_reissued_at":"2026-07-05T09:34:14.022870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:14.022870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Diffusion Models are Training-free Motion Interpreter and Controller","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shuai Yang, Xingang Pan, Yifan Zhou, Zeqi Xiao","submitted_at":"2024-05-23T17:59:40Z","abstract_excerpt":"Video generation primarily aims to model authentic and customized motion across frames, making understanding and controlling the motion a crucial topic. Most diffusion-based studies on video motion focus on motion customization with training-based paradigms, which, however, demands substantial training resources and necessitates retraining for diverse models. Crucially, these approaches do not explore how video diffusion models encode cross-frame motion information in their features, lacking interpretability and transparency in their effectiveness. To answer this question, this paper introduce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14864","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/2405.14864/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":"2405.14864","created_at":"2026-07-05T09:34:14.022929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14864v3","created_at":"2026-07-05T09:34:14.022929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14864","created_at":"2026-07-05T09:34:14.022929+00:00"},{"alias_kind":"pith_short_12","alias_value":"OXRFZYOYKGBT","created_at":"2026-07-05T09:34:14.022929+00:00"},{"alias_kind":"pith_short_16","alias_value":"OXRFZYOYKGBTEBSQ","created_at":"2026-07-05T09:34:14.022929+00:00"},{"alias_kind":"pith_short_8","alias_value":"OXRFZYOY","created_at":"2026-07-05T09:34:14.022929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09646","citing_title":"Do Video Foundation Models Understand Intuitive Physics? A Layerwise Probing Analysis","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07209","citing_title":"INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling","ref_index":91,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OXRFZYOYKGBTEBSQA6QG4LV7BM","json":"https://pith.science/pith/OXRFZYOYKGBTEBSQA6QG4LV7BM.json","graph_json":"https://pith.science/api/pith-number/OXRFZYOYKGBTEBSQA6QG4LV7BM/graph.json","events_json":"https://pith.science/api/pith-number/OXRFZYOYKGBTEBSQA6QG4LV7BM/events.json","paper":"https://pith.science/paper/OXRFZYOY"},"agent_actions":{"view_html":"https://pith.science/pith/OXRFZYOYKGBTEBSQA6QG4LV7BM","download_json":"https://pith.science/pith/OXRFZYOYKGBTEBSQA6QG4LV7BM.json","view_paper":"https://pith.science/paper/OXRFZYOY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14864&json=true","fetch_graph":"https://pith.science/api/pith-number/OXRFZYOYKGBTEBSQA6QG4LV7BM/graph.json","fetch_events":"https://pith.science/api/pith-number/OXRFZYOYKGBTEBSQA6QG4LV7BM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OXRFZYOYKGBTEBSQA6QG4LV7BM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OXRFZYOYKGBTEBSQA6QG4LV7BM/action/storage_attestation","attest_author":"https://pith.science/pith/OXRFZYOYKGBTEBSQA6QG4LV7BM/action/author_attestation","sign_citation":"https://pith.science/pith/OXRFZYOYKGBTEBSQA6QG4LV7BM/action/citation_signature","submit_replication":"https://pith.science/pith/OXRFZYOYKGBTEBSQA6QG4LV7BM/action/replication_record"}},"created_at":"2026-07-05T09:34:14.022929+00:00","updated_at":"2026-07-05T09:34:14.022929+00:00"}