{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZA6V5WW3WLJX4OHKAVFJG2QWVR","short_pith_number":"pith:ZA6V5WW3","schema_version":"1.0","canonical_sha256":"c83d5edadbb2d37e38ea054a936a16ac40adb4cba2f9056814185ddd2230f378","source":{"kind":"arxiv","id":"2006.10782","version":2},"attestation_state":"computed","paper":{"title":"AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT","physics.comp-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Tan, Jiahai Feng, Max Tegmark, Orisvaldo Neto, Silviu-Marian Udrescu, Tailin Wu","submitted_at":"2020-06-18T18:01:19Z","abstract_excerpt":"We present an improved method for symbolic regression that seeks to fit data to formulas that are Pareto-optimal, in the sense of having the best accuracy for a given complexity. It improves on the previous state-of-the-art by typically being orders of magnitude more robust toward noise and bad data, and also by discovering many formulas that stumped previous methods. We develop a method for discovering generalized symmetries (arbitrary modularity in the computational graph of a formula) from gradient properties of a neural network fit. We use normalizing flows to generalize our symbolic regre"},"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":"2006.10782","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T18:01:19Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT","physics.comp-ph","stat.ML"],"title_canon_sha256":"77d6ef90d7b8ce6551d0f9f286a84cf38fc2009048209e5e93c210be2e09e6b5","abstract_canon_sha256":"144699788eb95b3633a7b52e2605e88e1e64ea4605977c6d1ada5c6ac79bb4f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:59:56.028962Z","signature_b64":"a7WKQtqq8hOi0FFRh4Na/AfQQ0+j/uxRW+FNkXeS2MWLlfjMQYLZ0U3DPrvcwyviOtD/Qmiz0cImk64ie4DbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c83d5edadbb2d37e38ea054a936a16ac40adb4cba2f9056814185ddd2230f378","last_reissued_at":"2026-07-05T01:59:56.028500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:59:56.028500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT","physics.comp-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Tan, Jiahai Feng, Max Tegmark, Orisvaldo Neto, Silviu-Marian Udrescu, Tailin Wu","submitted_at":"2020-06-18T18:01:19Z","abstract_excerpt":"We present an improved method for symbolic regression that seeks to fit data to formulas that are Pareto-optimal, in the sense of having the best accuracy for a given complexity. It improves on the previous state-of-the-art by typically being orders of magnitude more robust toward noise and bad data, and also by discovering many formulas that stumped previous methods. We develop a method for discovering generalized symmetries (arbitrary modularity in the computational graph of a formula) from gradient properties of a neural network fit. We use normalizing flows to generalize our symbolic regre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10782","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/2006.10782/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":"2006.10782","created_at":"2026-07-05T01:59:56.028557+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.10782v2","created_at":"2026-07-05T01:59:56.028557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10782","created_at":"2026-07-05T01:59:56.028557+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZA6V5WW3WLJX","created_at":"2026-07-05T01:59:56.028557+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZA6V5WW3WLJX4OHK","created_at":"2026-07-05T01:59:56.028557+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZA6V5WW3","created_at":"2026-07-05T01:59:56.028557+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11249","citing_title":"A First Observational Assessment of Cosmic Backreaction Over an Extended Redshift Range","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05822","citing_title":"Model-independent constraints on generalized FLRW consistency relations with bootstrap-based symbolic regression","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZA6V5WW3WLJX4OHKAVFJG2QWVR","json":"https://pith.science/pith/ZA6V5WW3WLJX4OHKAVFJG2QWVR.json","graph_json":"https://pith.science/api/pith-number/ZA6V5WW3WLJX4OHKAVFJG2QWVR/graph.json","events_json":"https://pith.science/api/pith-number/ZA6V5WW3WLJX4OHKAVFJG2QWVR/events.json","paper":"https://pith.science/paper/ZA6V5WW3"},"agent_actions":{"view_html":"https://pith.science/pith/ZA6V5WW3WLJX4OHKAVFJG2QWVR","download_json":"https://pith.science/pith/ZA6V5WW3WLJX4OHKAVFJG2QWVR.json","view_paper":"https://pith.science/paper/ZA6V5WW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.10782&json=true","fetch_graph":"https://pith.science/api/pith-number/ZA6V5WW3WLJX4OHKAVFJG2QWVR/graph.json","fetch_events":"https://pith.science/api/pith-number/ZA6V5WW3WLJX4OHKAVFJG2QWVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZA6V5WW3WLJX4OHKAVFJG2QWVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZA6V5WW3WLJX4OHKAVFJG2QWVR/action/storage_attestation","attest_author":"https://pith.science/pith/ZA6V5WW3WLJX4OHKAVFJG2QWVR/action/author_attestation","sign_citation":"https://pith.science/pith/ZA6V5WW3WLJX4OHKAVFJG2QWVR/action/citation_signature","submit_replication":"https://pith.science/pith/ZA6V5WW3WLJX4OHKAVFJG2QWVR/action/replication_record"}},"created_at":"2026-07-05T01:59:56.028557+00:00","updated_at":"2026-07-05T01:59:56.028557+00:00"}