{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XGLI2B44DVMRFGIFWEFVQHLNUM","short_pith_number":"pith:XGLI2B44","schema_version":"1.0","canonical_sha256":"b9968d079c1d59129905b10b581d6da30ce03b4901a20d4f63b772d2fb7893df","source":{"kind":"arxiv","id":"1803.07616","version":3},"attestation_state":"computed","paper":{"title":"IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Adam Lerer, Emmanuel Dupoux, Mario Ynocente Castro, Mathieu Bernard, Rob Fergus, Ronan Riochet, V\\'eronique Izard","submitted_at":"2018-03-20T19:29:46Z","abstract_excerpt":"In order to reach human performance on complexvisual tasks, artificial systems need to incorporate a sig-nificant amount of understanding of the world in termsof macroscopic objects, movements, forces, etc. Inspiredby work on intuitive physics in infants, we propose anevaluation benchmark which diagnoses how much a givensystem understands about physics by testing whether itcan tell apart well matched videos of possible versusimpossible events constructed with a game engine. Thetest requires systems to compute a physical plausibilityscore over an entire video. It is free of bias and cantest a r"},"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":"1803.07616","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-03-20T19:29:46Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"eb0a523b8179d3bc6e7b063e30a5ff5323ba8189be17b577b5425cebc71d7258","abstract_canon_sha256":"f851ff8c7052ba58b0eb3542dafed4bd962b05eb879b7430e47ee720127187bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:39:29.643195Z","signature_b64":"RXZSa2NnDGoB96uvdbt/s182hKMkh1O7uzWxGtOBdcDbIZEsTTvnPUKKpW46ck6q+X/ZE2593xZUFC41yF8ZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9968d079c1d59129905b10b581d6da30ce03b4901a20d4f63b772d2fb7893df","last_reissued_at":"2026-07-05T00:39:29.642699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:39:29.642699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Adam Lerer, Emmanuel Dupoux, Mario Ynocente Castro, Mathieu Bernard, Rob Fergus, Ronan Riochet, V\\'eronique Izard","submitted_at":"2018-03-20T19:29:46Z","abstract_excerpt":"In order to reach human performance on complexvisual tasks, artificial systems need to incorporate a sig-nificant amount of understanding of the world in termsof macroscopic objects, movements, forces, etc. Inspiredby work on intuitive physics in infants, we propose anevaluation benchmark which diagnoses how much a givensystem understands about physics by testing whether itcan tell apart well matched videos of possible versusimpossible events constructed with a game engine. Thetest requires systems to compute a physical plausibilityscore over an entire video. It is free of bias and cantest a r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.07616","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/1803.07616/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":"1803.07616","created_at":"2026-07-05T00:39:29.642760+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.07616v3","created_at":"2026-07-05T00:39:29.642760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.07616","created_at":"2026-07-05T00:39:29.642760+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGLI2B44DVMR","created_at":"2026-07-05T00:39:29.642760+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGLI2B44DVMRFGIF","created_at":"2026-07-05T00:39:29.642760+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGLI2B44","created_at":"2026-07-05T00:39:29.642760+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18943","citing_title":"Physics-IQ Verified","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10620","citing_title":"Can Image Models Imagine Time? ImageTime: A Novel Benchmark for Probing Visual World Modeling Through Spatiotemporal Consistency","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07687","citing_title":"What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05328","citing_title":"The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31689","citing_title":"ScratchWorld: Evaluating If World Models Compute Executable Consequences","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24322","citing_title":"Causal Physics Steering in Video World Models via Concept Activation Vectors","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30346","citing_title":"YoCausal: How Far is Video Generation from World Model? A Causality Perspective","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29360","citing_title":"MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26969","citing_title":"Einstein World Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13294","citing_title":"VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2501.09038","citing_title":"Do generative video models understand physical principles?","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2602.07064","citing_title":"OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimization","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2603.03944","citing_title":"SCP: Spatial Causal Prediction in Video","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20328","citing_title":"Video models are zero-shot learners and reasoners","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28169","citing_title":"PhyCo: Learning Controllable Physical Priors for Generative Motion","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04515","citing_title":"From Priors to Perception: Grounding Video-LLMs in Physical Reality","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XGLI2B44DVMRFGIFWEFVQHLNUM","json":"https://pith.science/pith/XGLI2B44DVMRFGIFWEFVQHLNUM.json","graph_json":"https://pith.science/api/pith-number/XGLI2B44DVMRFGIFWEFVQHLNUM/graph.json","events_json":"https://pith.science/api/pith-number/XGLI2B44DVMRFGIFWEFVQHLNUM/events.json","paper":"https://pith.science/paper/XGLI2B44"},"agent_actions":{"view_html":"https://pith.science/pith/XGLI2B44DVMRFGIFWEFVQHLNUM","download_json":"https://pith.science/pith/XGLI2B44DVMRFGIFWEFVQHLNUM.json","view_paper":"https://pith.science/paper/XGLI2B44","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.07616&json=true","fetch_graph":"https://pith.science/api/pith-number/XGLI2B44DVMRFGIFWEFVQHLNUM/graph.json","fetch_events":"https://pith.science/api/pith-number/XGLI2B44DVMRFGIFWEFVQHLNUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGLI2B44DVMRFGIFWEFVQHLNUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGLI2B44DVMRFGIFWEFVQHLNUM/action/storage_attestation","attest_author":"https://pith.science/pith/XGLI2B44DVMRFGIFWEFVQHLNUM/action/author_attestation","sign_citation":"https://pith.science/pith/XGLI2B44DVMRFGIFWEFVQHLNUM/action/citation_signature","submit_replication":"https://pith.science/pith/XGLI2B44DVMRFGIFWEFVQHLNUM/action/replication_record"}},"created_at":"2026-07-05T00:39:29.642760+00:00","updated_at":"2026-07-05T00:39:29.642760+00:00"}