{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H7TWH3BFGAHNYDH54W5C3EUFMG","short_pith_number":"pith:H7TWH3BF","schema_version":"1.0","canonical_sha256":"3fe763ec25300edc0cfde5ba2d9285619e71f89a3f053260df61017a913fd3c1","source":{"kind":"arxiv","id":"2410.12822","version":2},"attestation_state":"computed","paper":{"title":"AVID: Adapting Video Diffusion Models to World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Agrin Hilmkil, Chao Ma, Marc Rigter, Tarun Gupta","submitted_at":"2024-10-01T13:48:31Z","abstract_excerpt":"Large-scale generative models have achieved remarkable success in a number of domains. However, for sequential decision-making problems, such as robotics, action-labelled data is often scarce and therefore scaling-up foundation models for decision-making remains a challenge. A potential solution lies in leveraging widely-available unlabelled videos to train world models that simulate the consequences of actions. If the world model is accurate, it can be used to optimize decision-making in downstream tasks. Image-to-video diffusion models are already capable of generating highly realistic synth"},"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":"2410.12822","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-01T13:48:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"676b38cecdbcb2dc2c8b968f86aed7612f2c8ca5fb5688bd54ae4aa3b16294c3","abstract_canon_sha256":"f338a938d3196274ffdb2a396ce10563bcb1ac2f1c31cf97fe9e775429cb8ce5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:59.149292Z","signature_b64":"FWRFftzUAckhjklRgJd81pD8vO8g/DAYfhdqh10hNhD8AA3jBtqGqNBk+8Lu131/Z/Ec+Lf4+zRYJMb/iW9MBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fe763ec25300edc0cfde5ba2d9285619e71f89a3f053260df61017a913fd3c1","last_reissued_at":"2026-07-05T09:39:59.148754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:59.148754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AVID: Adapting Video Diffusion Models to World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Agrin Hilmkil, Chao Ma, Marc Rigter, Tarun Gupta","submitted_at":"2024-10-01T13:48:31Z","abstract_excerpt":"Large-scale generative models have achieved remarkable success in a number of domains. However, for sequential decision-making problems, such as robotics, action-labelled data is often scarce and therefore scaling-up foundation models for decision-making remains a challenge. A potential solution lies in leveraging widely-available unlabelled videos to train world models that simulate the consequences of actions. If the world model is accurate, it can be used to optimize decision-making in downstream tasks. Image-to-video diffusion models are already capable of generating highly realistic synth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12822","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/2410.12822/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":"2410.12822","created_at":"2026-07-05T09:39:59.148814+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12822v2","created_at":"2026-07-05T09:39:59.148814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12822","created_at":"2026-07-05T09:39:59.148814+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7TWH3BFGAHN","created_at":"2026-07-05T09:39:59.148814+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7TWH3BFGAHNYDH5","created_at":"2026-07-05T09:39:59.148814+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7TWH3BF","created_at":"2026-07-05T09:39:59.148814+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27277","citing_title":"EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23296","citing_title":"IOI: Decoupling Kinematics and Physics for Interactive World Models","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09507","citing_title":"Prisma-World: Camera-Controllable Multi-Agent Video World Model","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05773","citing_title":"PiL-World: A Chunk-Wise World Model for VLA Policy-in-the-Loop Evaluation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02000","citing_title":"Towards 3D-Aware Video Diffusion Models: Render-Free Human Motion Control with Mesh Tokenization","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30542","citing_title":"Physically Viable World Models: A Case for Query-Conditioned Embodied AI","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16395","citing_title":"OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06192","citing_title":"EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7TWH3BFGAHNYDH54W5C3EUFMG","json":"https://pith.science/pith/H7TWH3BFGAHNYDH54W5C3EUFMG.json","graph_json":"https://pith.science/api/pith-number/H7TWH3BFGAHNYDH54W5C3EUFMG/graph.json","events_json":"https://pith.science/api/pith-number/H7TWH3BFGAHNYDH54W5C3EUFMG/events.json","paper":"https://pith.science/paper/H7TWH3BF"},"agent_actions":{"view_html":"https://pith.science/pith/H7TWH3BFGAHNYDH54W5C3EUFMG","download_json":"https://pith.science/pith/H7TWH3BFGAHNYDH54W5C3EUFMG.json","view_paper":"https://pith.science/paper/H7TWH3BF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12822&json=true","fetch_graph":"https://pith.science/api/pith-number/H7TWH3BFGAHNYDH54W5C3EUFMG/graph.json","fetch_events":"https://pith.science/api/pith-number/H7TWH3BFGAHNYDH54W5C3EUFMG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7TWH3BFGAHNYDH54W5C3EUFMG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7TWH3BFGAHNYDH54W5C3EUFMG/action/storage_attestation","attest_author":"https://pith.science/pith/H7TWH3BFGAHNYDH54W5C3EUFMG/action/author_attestation","sign_citation":"https://pith.science/pith/H7TWH3BFGAHNYDH54W5C3EUFMG/action/citation_signature","submit_replication":"https://pith.science/pith/H7TWH3BFGAHNYDH54W5C3EUFMG/action/replication_record"}},"created_at":"2026-07-05T09:39:59.148814+00:00","updated_at":"2026-07-05T09:39:59.148814+00:00"}