{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:P3MVP7TPGF3FLYC4TDUPMYLTFX","short_pith_number":"pith:P3MVP7TP","schema_version":"1.0","canonical_sha256":"7ed957fe6f317655e05c98e8f661732df22875f5333bb76d01eb2436e846a3df","source":{"kind":"arxiv","id":"1612.00222","version":1},"attestation_state":"computed","paper":{"title":"Interaction Networks for Learning about Objects, Relations and Physics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Danilo Rezende, Koray Kavukcuoglu, Matthew Lai, Peter W. Battaglia, Razvan Pascanu","submitted_at":"2016-12-01T12:34:54Z","abstract_excerpt":"Reasoning about objects, relations, and physics is central to human intelligence, and a key goal of artificial intelligence. Here we introduce the interaction network, a model which can reason about how objects in complex systems interact, supporting dynamical predictions, as well as inferences about the abstract properties of the system. Our model takes graphs as input, performs object- and relation-centric reasoning in a way that is analogous to a simulation, and is implemented using deep neural networks. We evaluate its ability to reason about several challenging physical domains: n-body pr"},"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":"1612.00222","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-12-01T12:34:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9a3e32e745631e0a9bf9ff8030edb821e3cacf589d9bb48daf2a17cf455f657f","abstract_canon_sha256":"ff2c08f92bd33134ce4be524a3ad25d7bceefaf5de218a458b1faaf7dd70f591"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:05.712217Z","signature_b64":"OGR+qbYoa28rFafzj1UCE/zB1aiq5AvYDVCKTyeCe4ADslpipj+CitbQBGJwDHDHWqeyNUmeZSgtgFpBvd/NAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ed957fe6f317655e05c98e8f661732df22875f5333bb76d01eb2436e846a3df","last_reissued_at":"2026-05-18T00:56:05.711687Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:05.711687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interaction Networks for Learning about Objects, Relations and Physics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Danilo Rezende, Koray Kavukcuoglu, Matthew Lai, Peter W. Battaglia, Razvan Pascanu","submitted_at":"2016-12-01T12:34:54Z","abstract_excerpt":"Reasoning about objects, relations, and physics is central to human intelligence, and a key goal of artificial intelligence. Here we introduce the interaction network, a model which can reason about how objects in complex systems interact, supporting dynamical predictions, as well as inferences about the abstract properties of the system. Our model takes graphs as input, performs object- and relation-centric reasoning in a way that is analogous to a simulation, and is implemented using deep neural networks. We evaluate its ability to reason about several challenging physical domains: n-body pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.00222","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":"1612.00222","created_at":"2026-05-18T00:56:05.711771+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.00222v1","created_at":"2026-05-18T00:56:05.711771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.00222","created_at":"2026-05-18T00:56:05.711771+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3MVP7TPGF3F","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3MVP7TPGF3FLYC4","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3MVP7TP","created_at":"2026-05-18T12:30:36.002864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2510.23641","citing_title":"Spatially Aware Linear Transformer (SAL-T) for Particle Jet Tagging","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2510.06860","citing_title":"Towards Generalization of Graph Neural Networks for AC Optimal Power Flow","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2510.22048","citing_title":"PF$\\Delta$: A Benchmark Dataset for Power Flow under Load, Generation, and Topology Variations","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2104.13478","citing_title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28161","citing_title":"RopeDreamer: A Kinematic Recurrent State Space Model for Dynamics of Flexible Deformable Linear Objects","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01542","citing_title":"Mesh Based Simulations with Spatial and Temporal awareness","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P3MVP7TPGF3FLYC4TDUPMYLTFX","json":"https://pith.science/pith/P3MVP7TPGF3FLYC4TDUPMYLTFX.json","graph_json":"https://pith.science/api/pith-number/P3MVP7TPGF3FLYC4TDUPMYLTFX/graph.json","events_json":"https://pith.science/api/pith-number/P3MVP7TPGF3FLYC4TDUPMYLTFX/events.json","paper":"https://pith.science/paper/P3MVP7TP"},"agent_actions":{"view_html":"https://pith.science/pith/P3MVP7TPGF3FLYC4TDUPMYLTFX","download_json":"https://pith.science/pith/P3MVP7TPGF3FLYC4TDUPMYLTFX.json","view_paper":"https://pith.science/paper/P3MVP7TP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.00222&json=true","fetch_graph":"https://pith.science/api/pith-number/P3MVP7TPGF3FLYC4TDUPMYLTFX/graph.json","fetch_events":"https://pith.science/api/pith-number/P3MVP7TPGF3FLYC4TDUPMYLTFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3MVP7TPGF3FLYC4TDUPMYLTFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3MVP7TPGF3FLYC4TDUPMYLTFX/action/storage_attestation","attest_author":"https://pith.science/pith/P3MVP7TPGF3FLYC4TDUPMYLTFX/action/author_attestation","sign_citation":"https://pith.science/pith/P3MVP7TPGF3FLYC4TDUPMYLTFX/action/citation_signature","submit_replication":"https://pith.science/pith/P3MVP7TPGF3FLYC4TDUPMYLTFX/action/replication_record"}},"created_at":"2026-05-18T00:56:05.711771+00:00","updated_at":"2026-05-18T00:56:05.711771+00:00"}