{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FXG2RID4V7ONV7IVQWYLR3KWRM","short_pith_number":"pith:FXG2RID4","schema_version":"1.0","canonical_sha256":"2dcda8a07cafdcdafd1585b0b8ed568b291f404472d25d90f55fce20ddbbe85f","source":{"kind":"arxiv","id":"2205.01089","version":1},"attestation_state":"computed","paper":{"title":"ComPhy: Compositional Physical Reasoning of Objects and Events from Videos","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Chuang Gan, Joshua B. Tenenbaum, Kexin Yi, Mingyu Ding, Yunzhu Li, Zhenfang Chen","submitted_at":"2022-05-02T17:59:13Z","abstract_excerpt":"Objects' motions in nature are governed by complex interactions and their properties. While some properties, such as shape and material, can be identified via the object's visual appearances, others like mass and electric charge are not directly visible. The compositionality between the visible and hidden properties poses unique challenges for AI models to reason from the physical world, whereas humans can effortlessly infer them with limited observations. Existing studies on video reasoning mainly focus on visually observable elements such as object appearance, movement, and contact interacti"},"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":"2205.01089","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-02T17:59:13Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"3e6bc92974ae37f021f5c08c59d0395ad5a3744e7d17bba87e7adf95908028d3","abstract_canon_sha256":"ca78ad26d374e591d068af299d656ae74339958f3c9ff8d2474c1ee96c7e8bb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:27.983762Z","signature_b64":"VEWDME5f0pWrNdwYMhsloJkJAoy+EYCYcyFQ41O1+AvQGrlVcCF3tTotGMk2e45NPfTSnWu75IMMvymxls0MBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2dcda8a07cafdcdafd1585b0b8ed568b291f404472d25d90f55fce20ddbbe85f","last_reissued_at":"2026-07-05T04:19:27.983335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:27.983335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ComPhy: Compositional Physical Reasoning of Objects and Events from Videos","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Chuang Gan, Joshua B. Tenenbaum, Kexin Yi, Mingyu Ding, Yunzhu Li, Zhenfang Chen","submitted_at":"2022-05-02T17:59:13Z","abstract_excerpt":"Objects' motions in nature are governed by complex interactions and their properties. While some properties, such as shape and material, can be identified via the object's visual appearances, others like mass and electric charge are not directly visible. The compositionality between the visible and hidden properties poses unique challenges for AI models to reason from the physical world, whereas humans can effortlessly infer them with limited observations. Existing studies on video reasoning mainly focus on visually observable elements such as object appearance, movement, and contact interacti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.01089","kind":"arxiv","version":1},"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/2205.01089/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":"2205.01089","created_at":"2026-07-05T04:19:27.983393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.01089v1","created_at":"2026-07-05T04:19:27.983393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.01089","created_at":"2026-07-05T04:19:27.983393+00:00"},{"alias_kind":"pith_short_12","alias_value":"FXG2RID4V7ON","created_at":"2026-07-05T04:19:27.983393+00:00"},{"alias_kind":"pith_short_16","alias_value":"FXG2RID4V7ONV7IV","created_at":"2026-07-05T04:19:27.983393+00:00"},{"alias_kind":"pith_short_8","alias_value":"FXG2RID4","created_at":"2026-07-05T04:19:27.983393+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07962","citing_title":"ChronoPhyBench: Do MLLMs Truly Understand the World or Merely Exploit Language Priors?","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05966","citing_title":"Causal Scaffolding for Physical Reasoning: A Benchmark for Causally-Informed Physical World Understanding in VLMs","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20448","citing_title":"Do Vision-Language Models Understand 3D Scenes or Just Catalogue Objects?","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29360","citing_title":"MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17180","citing_title":"We'll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedback","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20448","citing_title":"Do Vision-Language Models Understand 3D Scenes or Just Catalogue Objects?","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28169","citing_title":"PhyCo: Learning Controllable Physical Priors for Generative Motion","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00018","citing_title":"What Physics do Data-Driven MoCap-to-Radar Models Learn?","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FXG2RID4V7ONV7IVQWYLR3KWRM","json":"https://pith.science/pith/FXG2RID4V7ONV7IVQWYLR3KWRM.json","graph_json":"https://pith.science/api/pith-number/FXG2RID4V7ONV7IVQWYLR3KWRM/graph.json","events_json":"https://pith.science/api/pith-number/FXG2RID4V7ONV7IVQWYLR3KWRM/events.json","paper":"https://pith.science/paper/FXG2RID4"},"agent_actions":{"view_html":"https://pith.science/pith/FXG2RID4V7ONV7IVQWYLR3KWRM","download_json":"https://pith.science/pith/FXG2RID4V7ONV7IVQWYLR3KWRM.json","view_paper":"https://pith.science/paper/FXG2RID4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.01089&json=true","fetch_graph":"https://pith.science/api/pith-number/FXG2RID4V7ONV7IVQWYLR3KWRM/graph.json","fetch_events":"https://pith.science/api/pith-number/FXG2RID4V7ONV7IVQWYLR3KWRM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FXG2RID4V7ONV7IVQWYLR3KWRM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FXG2RID4V7ONV7IVQWYLR3KWRM/action/storage_attestation","attest_author":"https://pith.science/pith/FXG2RID4V7ONV7IVQWYLR3KWRM/action/author_attestation","sign_citation":"https://pith.science/pith/FXG2RID4V7ONV7IVQWYLR3KWRM/action/citation_signature","submit_replication":"https://pith.science/pith/FXG2RID4V7ONV7IVQWYLR3KWRM/action/replication_record"}},"created_at":"2026-07-05T04:19:27.983393+00:00","updated_at":"2026-07-05T04:19:27.983393+00:00"}