{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UDJJKHZL75EZ4O6NYYNVEEXE7Q","short_pith_number":"pith:UDJJKHZL","schema_version":"1.0","canonical_sha256":"a0d2951f2bff499e3bcdc61b5212e4fc21d55ebb70d1ff044f96a4515d8edef4","source":{"kind":"arxiv","id":"2504.02918","version":3},"attestation_state":"computed","paper":{"title":"Evaluating Newtonian Mechanics in Video Generative Models with Real Physical Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrii Zadaianchuk, Antonios Tragoudaras, Antonios Vozikis, Chenyu Zhang, Daniil Cherniavskii, Derck W. E. Prinzhorn, Efstratios Gavves, Mark Bodracska, Nicu Sebe, Thijmen Nijdam","submitted_at":"2025-04-03T15:21:17Z","abstract_excerpt":"Recent advances in image and video generation raise hopes that these models possess world modeling capabilities-the ability to generate realistic, physically plausible videos. This could revolutionize applications in robotics, autonomous driving, and scientific simulation. However, before treating these models as world models, we must ask: Do they adhere to physical laws? Current evaluation methods rely on subjective judgments or trajectory matching, limiting their usage for physical reasoning estimation, where many generations could be physically plausible. Thus, we introduce Morpheus, one of"},"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":"2504.02918","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T15:21:17Z","cross_cats_sorted":[],"title_canon_sha256":"2b7d2c94272e993743d0f85b749dd6647c9647f33e0ac99ba90da90190aa329d","abstract_canon_sha256":"38fbe1a1ccc5f740bf1497d937239435451433b905932609431883148db62251"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:16:50.680240Z","signature_b64":"zrgnkzKpF9xNyUd1vDX5Y7kgBCp+8ik51WMlcAiyqnUyyBjh/KyyIqX/UtnQjwKt1eNoSnGlzTXygxmeJZSqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0d2951f2bff499e3bcdc61b5212e4fc21d55ebb70d1ff044f96a4515d8edef4","last_reissued_at":"2026-06-30T02:16:50.679641Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:16:50.679641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Newtonian Mechanics in Video Generative Models with Real Physical Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrii Zadaianchuk, Antonios Tragoudaras, Antonios Vozikis, Chenyu Zhang, Daniil Cherniavskii, Derck W. E. Prinzhorn, Efstratios Gavves, Mark Bodracska, Nicu Sebe, Thijmen Nijdam","submitted_at":"2025-04-03T15:21:17Z","abstract_excerpt":"Recent advances in image and video generation raise hopes that these models possess world modeling capabilities-the ability to generate realistic, physically plausible videos. This could revolutionize applications in robotics, autonomous driving, and scientific simulation. However, before treating these models as world models, we must ask: Do they adhere to physical laws? Current evaluation methods rely on subjective judgments or trajectory matching, limiting their usage for physical reasoning estimation, where many generations could be physically plausible. Thus, we introduce Morpheus, one of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02918","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/2504.02918/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":"2504.02918","created_at":"2026-06-30T02:16:50.679727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02918v3","created_at":"2026-06-30T02:16:50.679727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02918","created_at":"2026-06-30T02:16:50.679727+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDJJKHZL75EZ","created_at":"2026-06-30T02:16:50.679727+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDJJKHZL75EZ4O6N","created_at":"2026-06-30T02:16:50.679727+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDJJKHZL","created_at":"2026-06-30T02:16:50.679727+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":16,"sample":[{"citing_arxiv_id":"2606.28385","citing_title":"RoboGaze: Evaluating Robot World Models via Structured Vision-Language Analysis","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30542","citing_title":"Physically Viable World Models: A Case for Query-Conditioned Embodied AI","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30346","citing_title":"YoCausal: How Far is Video Generation from World Model? A Causality Perspective","ref_index":131,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30339","citing_title":"Benchmarking Single-Factor Physical Video-to-Audio Generation","ref_index":76,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00499","citing_title":"OptiWorld: Optimal Control for Video World Generation under Physical Constraints","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18586","citing_title":"APT: Atomic Physical Transitions for Causal Video-Language Understanding","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23699","citing_title":"CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08567","citing_title":"ACWM-Phys: Investigating Generalized Physical Interaction in Action-Conditioned Video World Models","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15458","citing_title":"Video Models Can Reason with Verifiable Rewards","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2511.18373","citing_title":"MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2509.20328","citing_title":"Video models are zero-shot learners and reasoners","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08567","citing_title":"ACWM-Phys: Investigating Generalized Physical Interaction in Action-Conditioned Video World Models","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10806","citing_title":"PhyGround: Benchmarking Physical Reasoning in Generative World Models","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01694","citing_title":"Latent State Design for World Models under Sufficiency Constraints","ref_index":71,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09415","citing_title":"PhysInOne: Visual Physics Learning and Reasoning in One Suite","ref_index":97,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22851","citing_title":"EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UDJJKHZL75EZ4O6NYYNVEEXE7Q","json":"https://pith.science/pith/UDJJKHZL75EZ4O6NYYNVEEXE7Q.json","graph_json":"https://pith.science/api/pith-number/UDJJKHZL75EZ4O6NYYNVEEXE7Q/graph.json","events_json":"https://pith.science/api/pith-number/UDJJKHZL75EZ4O6NYYNVEEXE7Q/events.json","paper":"https://pith.science/paper/UDJJKHZL"},"agent_actions":{"view_html":"https://pith.science/pith/UDJJKHZL75EZ4O6NYYNVEEXE7Q","download_json":"https://pith.science/pith/UDJJKHZL75EZ4O6NYYNVEEXE7Q.json","view_paper":"https://pith.science/paper/UDJJKHZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02918&json=true","fetch_graph":"https://pith.science/api/pith-number/UDJJKHZL75EZ4O6NYYNVEEXE7Q/graph.json","fetch_events":"https://pith.science/api/pith-number/UDJJKHZL75EZ4O6NYYNVEEXE7Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDJJKHZL75EZ4O6NYYNVEEXE7Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDJJKHZL75EZ4O6NYYNVEEXE7Q/action/storage_attestation","attest_author":"https://pith.science/pith/UDJJKHZL75EZ4O6NYYNVEEXE7Q/action/author_attestation","sign_citation":"https://pith.science/pith/UDJJKHZL75EZ4O6NYYNVEEXE7Q/action/citation_signature","submit_replication":"https://pith.science/pith/UDJJKHZL75EZ4O6NYYNVEEXE7Q/action/replication_record"}},"created_at":"2026-06-30T02:16:50.679727+00:00","updated_at":"2026-06-30T02:16:50.679727+00:00"}