{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PDAF3T72DOVW3NCAKRUZ3UD7OJ","short_pith_number":"pith:PDAF3T72","schema_version":"1.0","canonical_sha256":"78c05dcffa1bab6db44054699dd07f726ff8b206bec0fc34380be3eec6d5490a","source":{"kind":"arxiv","id":"2203.12610","version":2},"attestation_state":"computed","paper":{"title":"AI Poincar\\'{e} 2.0: Machine Learning Conservation Laws from Differential Equations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["astro-ph.EP","nlin.SI","physics.class-ph","physics.flu-dyn"],"primary_cat":"cs.LG","authors_text":"Max Tegmark (MIT), Varun Madhavan (IIT), Ziming Liu (MIT)","submitted_at":"2022-03-23T17:57:01Z","abstract_excerpt":"We present a machine learning algorithm that discovers conservation laws from differential equations, both numerically (parametrized as neural networks) and symbolically, ensuring their functional independence (a non-linear generalization of linear independence). Our independence module can be viewed as a nonlinear generalization of singular value decomposition. Our method can readily handle inductive biases for conservation laws. We validate it with examples including the 3-body problem, the KdV equation and nonlinear Schr\\\"odinger equation."},"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":"2203.12610","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-23T17:57:01Z","cross_cats_sorted":["astro-ph.EP","nlin.SI","physics.class-ph","physics.flu-dyn"],"title_canon_sha256":"cb403e6751f0e9268f6954751589648d73e02405cdad7d4cf3877eba87b66295","abstract_canon_sha256":"c8484881af2621b107c17b774a50c754d1dab816d8bec1a20f0d92f7d575e6dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:37.896578Z","signature_b64":"vbTJDnND/27BD/hzzeWusWNTIZrewy5dVdJYA4yYz9z1v+SB0mEVM5/XmJSZf+B4E1x76clXjybTaVZYXebgAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78c05dcffa1bab6db44054699dd07f726ff8b206bec0fc34380be3eec6d5490a","last_reissued_at":"2026-07-05T05:11:37.896165Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:37.896165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI Poincar\\'{e} 2.0: Machine Learning Conservation Laws from Differential Equations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["astro-ph.EP","nlin.SI","physics.class-ph","physics.flu-dyn"],"primary_cat":"cs.LG","authors_text":"Max Tegmark (MIT), Varun Madhavan (IIT), Ziming Liu (MIT)","submitted_at":"2022-03-23T17:57:01Z","abstract_excerpt":"We present a machine learning algorithm that discovers conservation laws from differential equations, both numerically (parametrized as neural networks) and symbolically, ensuring their functional independence (a non-linear generalization of linear independence). Our independence module can be viewed as a nonlinear generalization of singular value decomposition. Our method can readily handle inductive biases for conservation laws. We validate it with examples including the 3-body problem, the KdV equation and nonlinear Schr\\\"odinger equation."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.12610","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.12610/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":"2203.12610","created_at":"2026-07-05T05:11:37.896222+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.12610v2","created_at":"2026-07-05T05:11:37.896222+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.12610","created_at":"2026-07-05T05:11:37.896222+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDAF3T72DOVW","created_at":"2026-07-05T05:11:37.896222+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDAF3T72DOVW3NCA","created_at":"2026-07-05T05:11:37.896222+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDAF3T72","created_at":"2026-07-05T05:11:37.896222+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.01084","citing_title":"Kernel-Based LMI Approaches to Solving the Hamilton-Jacobi-Bellman Equation and Nonlinear Optimal Control","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PDAF3T72DOVW3NCAKRUZ3UD7OJ","json":"https://pith.science/pith/PDAF3T72DOVW3NCAKRUZ3UD7OJ.json","graph_json":"https://pith.science/api/pith-number/PDAF3T72DOVW3NCAKRUZ3UD7OJ/graph.json","events_json":"https://pith.science/api/pith-number/PDAF3T72DOVW3NCAKRUZ3UD7OJ/events.json","paper":"https://pith.science/paper/PDAF3T72"},"agent_actions":{"view_html":"https://pith.science/pith/PDAF3T72DOVW3NCAKRUZ3UD7OJ","download_json":"https://pith.science/pith/PDAF3T72DOVW3NCAKRUZ3UD7OJ.json","view_paper":"https://pith.science/paper/PDAF3T72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.12610&json=true","fetch_graph":"https://pith.science/api/pith-number/PDAF3T72DOVW3NCAKRUZ3UD7OJ/graph.json","fetch_events":"https://pith.science/api/pith-number/PDAF3T72DOVW3NCAKRUZ3UD7OJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDAF3T72DOVW3NCAKRUZ3UD7OJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDAF3T72DOVW3NCAKRUZ3UD7OJ/action/storage_attestation","attest_author":"https://pith.science/pith/PDAF3T72DOVW3NCAKRUZ3UD7OJ/action/author_attestation","sign_citation":"https://pith.science/pith/PDAF3T72DOVW3NCAKRUZ3UD7OJ/action/citation_signature","submit_replication":"https://pith.science/pith/PDAF3T72DOVW3NCAKRUZ3UD7OJ/action/replication_record"}},"created_at":"2026-07-05T05:11:37.896222+00:00","updated_at":"2026-07-05T05:11:37.896222+00:00"}