{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2SKATHIWBVUAWA65NNBDPTTAMH","short_pith_number":"pith:2SKATHIW","schema_version":"1.0","canonical_sha256":"d494099d160d680b03dd6b4237ce6061eb7707231f313e15054e7746c47518f6","source":{"kind":"arxiv","id":"1909.12000","version":2},"attestation_state":"computed","paper":{"title":"CoPhy: Counterfactual Learning of Physical Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Wolf, Fabien Baradel, Greg Mori, Julien Mille, Natalia Neverova","submitted_at":"2019-09-26T09:34:48Z","abstract_excerpt":"Understanding causes and effects in mechanical systems is an essential component of reasoning in the physical world. This work poses a new problem of counterfactual learning of object mechanics from visual input. We develop the CoPhy benchmark to assess the capacity of the state-of-the-art models for causal physical reasoning in a synthetic 3D environment and propose a model for learning the physical dynamics in a counterfactual setting. Having observed a mechanical experiment that involves, for example, a falling tower of blocks, a set of bouncing balls or colliding objects, we learn to predi"},"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":"1909.12000","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-26T09:34:48Z","cross_cats_sorted":[],"title_canon_sha256":"42f7d595710ef4ec2463dbb0acd963ed8c31b9e176b7582531ad936850762d6d","abstract_canon_sha256":"234c1875edbb36de62353208001369bdfa1a67560c268dc7015b2077842c2f17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:53:07.864890Z","signature_b64":"w92+u22cCRJxaAIXVpYUKX8F+O+Ts9droA2+zzRvsU8NcI8Jb5VDIkm7CiAVsANWn5pNupUGBS9rt3AP5efCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d494099d160d680b03dd6b4237ce6061eb7707231f313e15054e7746c47518f6","last_reissued_at":"2026-07-05T00:53:07.864489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:53:07.864489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoPhy: Counterfactual Learning of Physical Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Wolf, Fabien Baradel, Greg Mori, Julien Mille, Natalia Neverova","submitted_at":"2019-09-26T09:34:48Z","abstract_excerpt":"Understanding causes and effects in mechanical systems is an essential component of reasoning in the physical world. This work poses a new problem of counterfactual learning of object mechanics from visual input. We develop the CoPhy benchmark to assess the capacity of the state-of-the-art models for causal physical reasoning in a synthetic 3D environment and propose a model for learning the physical dynamics in a counterfactual setting. Having observed a mechanical experiment that involves, for example, a falling tower of blocks, a set of bouncing balls or colliding objects, we learn to predi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.12000","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/1909.12000/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":"1909.12000","created_at":"2026-07-05T00:53:07.864542+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.12000v2","created_at":"2026-07-05T00:53:07.864542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.12000","created_at":"2026-07-05T00:53:07.864542+00:00"},{"alias_kind":"pith_short_12","alias_value":"2SKATHIWBVUA","created_at":"2026-07-05T00:53:07.864542+00:00"},{"alias_kind":"pith_short_16","alias_value":"2SKATHIWBVUAWA65","created_at":"2026-07-05T00:53:07.864542+00:00"},{"alias_kind":"pith_short_8","alias_value":"2SKATHIW","created_at":"2026-07-05T00:53:07.864542+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18943","citing_title":"Physics-IQ Verified","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":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20576","citing_title":"$\\Delta$ynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videos","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16054","citing_title":"Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making","ref_index":181,"is_internal_anchor":false},{"citing_arxiv_id":"2501.09038","citing_title":"Do generative video models understand physical principles?","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28169","citing_title":"PhyCo: Learning Controllable Physical Priors for Generative Motion","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2SKATHIWBVUAWA65NNBDPTTAMH","json":"https://pith.science/pith/2SKATHIWBVUAWA65NNBDPTTAMH.json","graph_json":"https://pith.science/api/pith-number/2SKATHIWBVUAWA65NNBDPTTAMH/graph.json","events_json":"https://pith.science/api/pith-number/2SKATHIWBVUAWA65NNBDPTTAMH/events.json","paper":"https://pith.science/paper/2SKATHIW"},"agent_actions":{"view_html":"https://pith.science/pith/2SKATHIWBVUAWA65NNBDPTTAMH","download_json":"https://pith.science/pith/2SKATHIWBVUAWA65NNBDPTTAMH.json","view_paper":"https://pith.science/paper/2SKATHIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.12000&json=true","fetch_graph":"https://pith.science/api/pith-number/2SKATHIWBVUAWA65NNBDPTTAMH/graph.json","fetch_events":"https://pith.science/api/pith-number/2SKATHIWBVUAWA65NNBDPTTAMH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2SKATHIWBVUAWA65NNBDPTTAMH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2SKATHIWBVUAWA65NNBDPTTAMH/action/storage_attestation","attest_author":"https://pith.science/pith/2SKATHIWBVUAWA65NNBDPTTAMH/action/author_attestation","sign_citation":"https://pith.science/pith/2SKATHIWBVUAWA65NNBDPTTAMH/action/citation_signature","submit_replication":"https://pith.science/pith/2SKATHIWBVUAWA65NNBDPTTAMH/action/replication_record"}},"created_at":"2026-07-05T00:53:07.864542+00:00","updated_at":"2026-07-05T00:53:07.864542+00:00"}