{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TBB4EZ7IDAVEICNVLP4YI7IRTW","short_pith_number":"pith:TBB4EZ7I","schema_version":"1.0","canonical_sha256":"9843c267e8182a4409b55bf9847d119d9c766245ed8715cf44349f02ea6bb7c2","source":{"kind":"arxiv","id":"1806.01242","version":1},"attestation_state":"computed","paper":{"title":"Graph networks as learnable physics engines for inference and control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alvaro Sanchez-Gonzalez, Josh Merel, Jost Tobias Springenberg, Martin Riedmiller, Nicolas Heess, Peter Battaglia, Raia Hadsell","submitted_at":"2018-06-04T17:29:40Z","abstract_excerpt":"Understanding and interacting with everyday physical scenes requires rich knowledge about the structure of the world, represented either implicitly in a value or policy function, or explicitly in a transition model. Here we introduce a new class of learnable models--based on graph networks--which implement an inductive bias for object- and relation-centric representations of complex, dynamical systems. Our results show that as a forward model, our approach supports accurate predictions from real and simulated data, and surprisingly strong and efficient generalization, across eight distinct phy"},"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":"1806.01242","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-04T17:29:40Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"93854b5ff709f1718526e5f80c53f6f91c92bf81b741962260740111c0a46382","abstract_canon_sha256":"e4b7ed81bb67f7e4d2051614fffa4bc4c576192ddf573e7cf0b776b2cbe90ec6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:17.008279Z","signature_b64":"h4XUVZDLmL0pqwPC/cB2TTwmUW8rhq9R6y9twTA5q3VrSI0AVxQFXdHMSW/uvnjz9iQ7hG6/Xa54jwVdqYMRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9843c267e8182a4409b55bf9847d119d9c766245ed8715cf44349f02ea6bb7c2","last_reissued_at":"2026-05-18T00:14:17.007720Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:17.007720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph networks as learnable physics engines for inference and control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alvaro Sanchez-Gonzalez, Josh Merel, Jost Tobias Springenberg, Martin Riedmiller, Nicolas Heess, Peter Battaglia, Raia Hadsell","submitted_at":"2018-06-04T17:29:40Z","abstract_excerpt":"Understanding and interacting with everyday physical scenes requires rich knowledge about the structure of the world, represented either implicitly in a value or policy function, or explicitly in a transition model. Here we introduce a new class of learnable models--based on graph networks--which implement an inductive bias for object- and relation-centric representations of complex, dynamical systems. Our results show that as a forward model, our approach supports accurate predictions from real and simulated data, and surprisingly strong and efficient generalization, across eight distinct phy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01242","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":""},"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":"1806.01242","created_at":"2026-05-18T00:14:17.007808+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.01242v1","created_at":"2026-05-18T00:14:17.007808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01242","created_at":"2026-05-18T00:14:17.007808+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBB4EZ7IDAVE","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBB4EZ7IDAVEICNV","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBB4EZ7I","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.11909","citing_title":"Comparing Semi-Parametric Model Learning Algorithms for Dynamic Model Estimation in Robotics","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TBB4EZ7IDAVEICNVLP4YI7IRTW","json":"https://pith.science/pith/TBB4EZ7IDAVEICNVLP4YI7IRTW.json","graph_json":"https://pith.science/api/pith-number/TBB4EZ7IDAVEICNVLP4YI7IRTW/graph.json","events_json":"https://pith.science/api/pith-number/TBB4EZ7IDAVEICNVLP4YI7IRTW/events.json","paper":"https://pith.science/paper/TBB4EZ7I"},"agent_actions":{"view_html":"https://pith.science/pith/TBB4EZ7IDAVEICNVLP4YI7IRTW","download_json":"https://pith.science/pith/TBB4EZ7IDAVEICNVLP4YI7IRTW.json","view_paper":"https://pith.science/paper/TBB4EZ7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.01242&json=true","fetch_graph":"https://pith.science/api/pith-number/TBB4EZ7IDAVEICNVLP4YI7IRTW/graph.json","fetch_events":"https://pith.science/api/pith-number/TBB4EZ7IDAVEICNVLP4YI7IRTW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBB4EZ7IDAVEICNVLP4YI7IRTW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBB4EZ7IDAVEICNVLP4YI7IRTW/action/storage_attestation","attest_author":"https://pith.science/pith/TBB4EZ7IDAVEICNVLP4YI7IRTW/action/author_attestation","sign_citation":"https://pith.science/pith/TBB4EZ7IDAVEICNVLP4YI7IRTW/action/citation_signature","submit_replication":"https://pith.science/pith/TBB4EZ7IDAVEICNVLP4YI7IRTW/action/replication_record"}},"created_at":"2026-05-18T00:14:17.007808+00:00","updated_at":"2026-05-18T00:14:17.007808+00:00"}