{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3TR5QYLNQGL3PSXF77HDQ5KO5Q","short_pith_number":"pith:3TR5QYLN","schema_version":"1.0","canonical_sha256":"dce3d8616d8197b7cae5ffce38754eec3d8c36ba9d34d2a685c9eaf0bd046ebd","source":{"kind":"arxiv","id":"2412.04189","version":5},"attestation_state":"computed","paper":{"title":"HANDI: Hand-Centric Text-and-Image Conditioned Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jason J. Corso, Yayuan Li, Zhi Cao","submitted_at":"2024-12-05T14:29:10Z","abstract_excerpt":"Despite the recent strides in video generation, state-of-the-art methods still struggle with elements of visual detail. One particularly challenging case is the class of videos in which the intricate motion of the hand coupled with a mostly stable and otherwise distracting environment is necessary to convey the execution of some complex action and its effects. To address these challenges, we introduce a new method for video generation that focuses on hand-centric actions. Our diffusion-based method incorporates two distinct innovations. First, we propose an automatic method to generate the mot"},"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":"2412.04189","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T14:29:10Z","cross_cats_sorted":[],"title_canon_sha256":"2ced2f1e9d466b21fc5019d4556f93a83d42f15cade208f000111b464b769987","abstract_canon_sha256":"f516fa15c47e80a3a0025c9bfa2c09233866c9eb77e6b078d127f6e80ea533c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:26.108096Z","signature_b64":"140dsGFo5o+4+tNygF61S5NEJ84IAjt5mEus2Q/LGDlF14qJSZvyPMTQw6RiksYsOVkzL0g+zKXi/CgdvMbFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dce3d8616d8197b7cae5ffce38754eec3d8c36ba9d34d2a685c9eaf0bd046ebd","last_reissued_at":"2026-07-05T11:36:26.107511Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:26.107511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HANDI: Hand-Centric Text-and-Image Conditioned Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jason J. Corso, Yayuan Li, Zhi Cao","submitted_at":"2024-12-05T14:29:10Z","abstract_excerpt":"Despite the recent strides in video generation, state-of-the-art methods still struggle with elements of visual detail. One particularly challenging case is the class of videos in which the intricate motion of the hand coupled with a mostly stable and otherwise distracting environment is necessary to convey the execution of some complex action and its effects. To address these challenges, we introduce a new method for video generation that focuses on hand-centric actions. Our diffusion-based method incorporates two distinct innovations. First, we propose an automatic method to generate the mot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04189","kind":"arxiv","version":5},"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/2412.04189/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":"2412.04189","created_at":"2026-07-05T11:36:26.107580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04189v5","created_at":"2026-07-05T11:36:26.107580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04189","created_at":"2026-07-05T11:36:26.107580+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TR5QYLNQGL3","created_at":"2026-07-05T11:36:26.107580+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TR5QYLNQGL3PSXF","created_at":"2026-07-05T11:36:26.107580+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TR5QYLN","created_at":"2026-07-05T11:36:26.107580+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18374","citing_title":"Towards Effective Human-in-the-Loop Assistive AI Agents","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3TR5QYLNQGL3PSXF77HDQ5KO5Q","json":"https://pith.science/pith/3TR5QYLNQGL3PSXF77HDQ5KO5Q.json","graph_json":"https://pith.science/api/pith-number/3TR5QYLNQGL3PSXF77HDQ5KO5Q/graph.json","events_json":"https://pith.science/api/pith-number/3TR5QYLNQGL3PSXF77HDQ5KO5Q/events.json","paper":"https://pith.science/paper/3TR5QYLN"},"agent_actions":{"view_html":"https://pith.science/pith/3TR5QYLNQGL3PSXF77HDQ5KO5Q","download_json":"https://pith.science/pith/3TR5QYLNQGL3PSXF77HDQ5KO5Q.json","view_paper":"https://pith.science/paper/3TR5QYLN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04189&json=true","fetch_graph":"https://pith.science/api/pith-number/3TR5QYLNQGL3PSXF77HDQ5KO5Q/graph.json","fetch_events":"https://pith.science/api/pith-number/3TR5QYLNQGL3PSXF77HDQ5KO5Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TR5QYLNQGL3PSXF77HDQ5KO5Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TR5QYLNQGL3PSXF77HDQ5KO5Q/action/storage_attestation","attest_author":"https://pith.science/pith/3TR5QYLNQGL3PSXF77HDQ5KO5Q/action/author_attestation","sign_citation":"https://pith.science/pith/3TR5QYLNQGL3PSXF77HDQ5KO5Q/action/citation_signature","submit_replication":"https://pith.science/pith/3TR5QYLNQGL3PSXF77HDQ5KO5Q/action/replication_record"}},"created_at":"2026-07-05T11:36:26.107580+00:00","updated_at":"2026-07-05T11:36:26.107580+00:00"}