{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:7Q5MI6E6XFFK7NA7SQ35HODSPD","short_pith_number":"pith:7Q5MI6E6","schema_version":"1.0","canonical_sha256":"fc3ac4789eb94aafb41f9437d3b87278db29d90b13a3d8a06c4f152ec3025ebc","source":{"kind":"arxiv","id":"1612.00341","version":2},"attestation_state":"computed","paper":{"title":"A Compositional Object-Based Approach to Learning Physical Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Antonio Torralba, Joshua B. Tenenbaum, Michael B. Chang, Tomer Ullman","submitted_at":"2016-12-01T16:39:04Z","abstract_excerpt":"We present the Neural Physics Engine (NPE), a framework for learning simulators of intuitive physics that naturally generalize across variable object count and different scene configurations. We propose a factorization of a physical scene into composable object-based representations and a neural network architecture whose compositional structure factorizes object dynamics into pairwise interactions. Like a symbolic physics engine, the NPE is endowed with generic notions of objects and their interactions; realized as a neural network, it can be trained via stochastic gradient descent to adapt t"},"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":"1612.00341","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-12-01T16:39:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a06fcf5b02d8e9a67c4962cfea9eaa2acce6b3206206d167e9e955aa4eb98d8e","abstract_canon_sha256":"99e4aaa5d79ba41096cc4117b2eb94a7a8aad76c3198620314ccd91c0ba0419f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:31.648435Z","signature_b64":"G5SHJ6xbkNmMvt6jqLhtwNLOL5k0ARhUcZVK5zi7r3d0U6B9fZKsSiNc/xYb8KM0kdSeMn49s9vuV/ULhnsSAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc3ac4789eb94aafb41f9437d3b87278db29d90b13a3d8a06c4f152ec3025ebc","last_reissued_at":"2026-05-18T00:49:31.647687Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:31.647687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Compositional Object-Based Approach to Learning Physical Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Antonio Torralba, Joshua B. Tenenbaum, Michael B. Chang, Tomer Ullman","submitted_at":"2016-12-01T16:39:04Z","abstract_excerpt":"We present the Neural Physics Engine (NPE), a framework for learning simulators of intuitive physics that naturally generalize across variable object count and different scene configurations. We propose a factorization of a physical scene into composable object-based representations and a neural network architecture whose compositional structure factorizes object dynamics into pairwise interactions. Like a symbolic physics engine, the NPE is endowed with generic notions of objects and their interactions; realized as a neural network, it can be trained via stochastic gradient descent to adapt t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.00341","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":""},"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":"1612.00341","created_at":"2026-05-18T00:49:31.647810+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.00341v2","created_at":"2026-05-18T00:49:31.647810+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.00341","created_at":"2026-05-18T00:49:31.647810+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Q5MI6E6XFFK","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Q5MI6E6XFFK7NA7","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Q5MI6E6","created_at":"2026-05-18T12:30:04.600751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"1907.03116","citing_title":"Intrinsic Motivation Driven Intuitive Physics Learning using Deep Reinforcement Learning with Intrinsic Reward Normalization","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"1907.08845","citing_title":"Order Matters: Shuffling Sequence Generation for Video Prediction","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2501.09038","citing_title":"Do generative video models understand physical principles?","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2506.06558","citing_title":"Rapid training of Hamiltonian graph networks using random features","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2409.01652","citing_title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2307.05973","citing_title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09196","citing_title":"RigidFormer: Learning Rigid Dynamics using Transformers","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":139,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07565","citing_title":"Ensemble Distributionally Robust Bayesian Optimisation","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7Q5MI6E6XFFK7NA7SQ35HODSPD","json":"https://pith.science/pith/7Q5MI6E6XFFK7NA7SQ35HODSPD.json","graph_json":"https://pith.science/api/pith-number/7Q5MI6E6XFFK7NA7SQ35HODSPD/graph.json","events_json":"https://pith.science/api/pith-number/7Q5MI6E6XFFK7NA7SQ35HODSPD/events.json","paper":"https://pith.science/paper/7Q5MI6E6"},"agent_actions":{"view_html":"https://pith.science/pith/7Q5MI6E6XFFK7NA7SQ35HODSPD","download_json":"https://pith.science/pith/7Q5MI6E6XFFK7NA7SQ35HODSPD.json","view_paper":"https://pith.science/paper/7Q5MI6E6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.00341&json=true","fetch_graph":"https://pith.science/api/pith-number/7Q5MI6E6XFFK7NA7SQ35HODSPD/graph.json","fetch_events":"https://pith.science/api/pith-number/7Q5MI6E6XFFK7NA7SQ35HODSPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Q5MI6E6XFFK7NA7SQ35HODSPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Q5MI6E6XFFK7NA7SQ35HODSPD/action/storage_attestation","attest_author":"https://pith.science/pith/7Q5MI6E6XFFK7NA7SQ35HODSPD/action/author_attestation","sign_citation":"https://pith.science/pith/7Q5MI6E6XFFK7NA7SQ35HODSPD/action/citation_signature","submit_replication":"https://pith.science/pith/7Q5MI6E6XFFK7NA7SQ35HODSPD/action/replication_record"}},"created_at":"2026-05-18T00:49:31.647810+00:00","updated_at":"2026-05-18T00:49:31.647810+00:00"}