{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GNJEASGUJ7S77QR63OX7UDFPJQ","short_pith_number":"pith:GNJEASGU","schema_version":"1.0","canonical_sha256":"33524048d44fe5ffc23edbaffa0caf4c1aecf5b56da26db67bc1d379d1854b4a","source":{"kind":"arxiv","id":"2412.00932","version":2},"attestation_state":"computed","paper":{"title":"FIction: 4D Future Interaction Prediction from Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Georgios Pavlakos, Kristen Grauman, Kumar Ashutosh","submitted_at":"2024-12-01T18:44:17Z","abstract_excerpt":"Anticipating how a person will interact with objects in an environment is essential for activity understanding, but existing methods are limited to the 2D space of video frames-capturing physically ungrounded predictions of \"what\" and ignoring the \"where\" and \"how\". We introduce FIction for 4D future interaction prediction from videos. Given an input video of a human activity, the goal is to predict which objects at what 3D locations the person will interact with in the next time period (e.g., cabinet, fridge), and how they will execute that interaction (e.g., poses for bending, reaching, pull"},"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":"2412.00932","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-01T18:44:17Z","cross_cats_sorted":[],"title_canon_sha256":"6ed45439edf8c20e16c1d11d051a79933156c41b27359fbcc2551c5a9bb07394","abstract_canon_sha256":"a47a3e4cff691a57fa4fde65db289344d98e777513208f5aa7af32c4b4f0ffb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:56.298994Z","signature_b64":"wiWc7N8+J3s6kkpTmRA8bvl1srD6iiQTbKy1h1v6YI8fKkpWB/4tfnkCIH5WpeEFzbNW5WN7IOPN7cBvMWqeCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33524048d44fe5ffc23edbaffa0caf4c1aecf5b56da26db67bc1d379d1854b4a","last_reissued_at":"2026-07-05T10:47:56.298320Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:56.298320Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FIction: 4D Future Interaction Prediction from Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Georgios Pavlakos, Kristen Grauman, Kumar Ashutosh","submitted_at":"2024-12-01T18:44:17Z","abstract_excerpt":"Anticipating how a person will interact with objects in an environment is essential for activity understanding, but existing methods are limited to the 2D space of video frames-capturing physically ungrounded predictions of \"what\" and ignoring the \"where\" and \"how\". We introduce FIction for 4D future interaction prediction from videos. Given an input video of a human activity, the goal is to predict which objects at what 3D locations the person will interact with in the next time period (e.g., cabinet, fridge), and how they will execute that interaction (e.g., poses for bending, reaching, pull"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00932","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/2412.00932/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":"2412.00932","created_at":"2026-07-05T10:47:56.298407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00932v2","created_at":"2026-07-05T10:47:56.298407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00932","created_at":"2026-07-05T10:47:56.298407+00:00"},{"alias_kind":"pith_short_12","alias_value":"GNJEASGUJ7S7","created_at":"2026-07-05T10:47:56.298407+00:00"},{"alias_kind":"pith_short_16","alias_value":"GNJEASGUJ7S77QR6","created_at":"2026-07-05T10:47:56.298407+00:00"},{"alias_kind":"pith_short_8","alias_value":"GNJEASGU","created_at":"2026-07-05T10:47:56.298407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GNJEASGUJ7S77QR63OX7UDFPJQ","json":"https://pith.science/pith/GNJEASGUJ7S77QR63OX7UDFPJQ.json","graph_json":"https://pith.science/api/pith-number/GNJEASGUJ7S77QR63OX7UDFPJQ/graph.json","events_json":"https://pith.science/api/pith-number/GNJEASGUJ7S77QR63OX7UDFPJQ/events.json","paper":"https://pith.science/paper/GNJEASGU"},"agent_actions":{"view_html":"https://pith.science/pith/GNJEASGUJ7S77QR63OX7UDFPJQ","download_json":"https://pith.science/pith/GNJEASGUJ7S77QR63OX7UDFPJQ.json","view_paper":"https://pith.science/paper/GNJEASGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00932&json=true","fetch_graph":"https://pith.science/api/pith-number/GNJEASGUJ7S77QR63OX7UDFPJQ/graph.json","fetch_events":"https://pith.science/api/pith-number/GNJEASGUJ7S77QR63OX7UDFPJQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GNJEASGUJ7S77QR63OX7UDFPJQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GNJEASGUJ7S77QR63OX7UDFPJQ/action/storage_attestation","attest_author":"https://pith.science/pith/GNJEASGUJ7S77QR63OX7UDFPJQ/action/author_attestation","sign_citation":"https://pith.science/pith/GNJEASGUJ7S77QR63OX7UDFPJQ/action/citation_signature","submit_replication":"https://pith.science/pith/GNJEASGUJ7S77QR63OX7UDFPJQ/action/replication_record"}},"created_at":"2026-07-05T10:47:56.298407+00:00","updated_at":"2026-07-05T10:47:56.298407+00:00"}