{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5RKKVEAOUKFTB6EUQGLMAOUFFJ","short_pith_number":"pith:5RKKVEAO","schema_version":"1.0","canonical_sha256":"ec54aa900ea28b30f8948196c03a852a6cdc3d4d3b55dcfa410af950488de85a","source":{"kind":"arxiv","id":"2007.10784","version":3},"attestation_state":"computed","paper":{"title":"OccamNet: A Fast Neural Model for Symbolic Regression at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Allan Costa, Joseph Jacobson, Marin Solja\\v{c}i\\'c, Owen Dugan, Pawan Goyal, Rumen Dangovski, Samuel Kim","submitted_at":"2020-07-16T21:14:45Z","abstract_excerpt":"Neural networks' expressiveness comes at the cost of complex, black-box models that often extrapolate poorly beyond the domain of the training dataset, conflicting with the goal of finding compact analytic expressions to describe scientific data. We introduce OccamNet, a neural network model that finds interpretable, compact, and sparse symbolic fits to data, \\`a la Occam's razor. Our model defines a probability distribution over functions with efficient sampling and function evaluation. We train by sampling functions and biasing the probability mass toward better fitting solutions, backpropag"},"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":"2007.10784","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-16T21:14:45Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"f7a3b3dfbc742a484759cc7d253037f6102d6c747891cc5e3d482c9a3e7c9728","abstract_canon_sha256":"82c9e7c43dd4e23684700a13707c7860fa9f729d72dabc4b6e035ec11a17d7f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:20.798853Z","signature_b64":"gwHV+l888bs8wyKidmeqp9YnYtf9JJN4THGcK68/qHMaiHRVM3zaDYxxBnGdR4noh/nNVqgmk1qHCg5pDd1oBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec54aa900ea28b30f8948196c03a852a6cdc3d4d3b55dcfa410af950488de85a","last_reissued_at":"2026-07-05T07:17:20.798304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:20.798304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OccamNet: A Fast Neural Model for Symbolic Regression at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Allan Costa, Joseph Jacobson, Marin Solja\\v{c}i\\'c, Owen Dugan, Pawan Goyal, Rumen Dangovski, Samuel Kim","submitted_at":"2020-07-16T21:14:45Z","abstract_excerpt":"Neural networks' expressiveness comes at the cost of complex, black-box models that often extrapolate poorly beyond the domain of the training dataset, conflicting with the goal of finding compact analytic expressions to describe scientific data. We introduce OccamNet, a neural network model that finds interpretable, compact, and sparse symbolic fits to data, \\`a la Occam's razor. Our model defines a probability distribution over functions with efficient sampling and function evaluation. We train by sampling functions and biasing the probability mass toward better fitting solutions, backpropag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.10784","kind":"arxiv","version":3},"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/2007.10784/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":"2007.10784","created_at":"2026-07-05T07:17:20.798385+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.10784v3","created_at":"2026-07-05T07:17:20.798385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.10784","created_at":"2026-07-05T07:17:20.798385+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RKKVEAOUKFT","created_at":"2026-07-05T07:17:20.798385+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RKKVEAOUKFTB6EU","created_at":"2026-07-05T07:17:20.798385+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RKKVEAO","created_at":"2026-07-05T07:17:20.798385+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.19756","citing_title":"KAN: Kolmogorov-Arnold Networks","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16842","citing_title":"Singularity Formation: Synergy in Theoretical, Numerical and Machine Learning Approaches","ref_index":98,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5RKKVEAOUKFTB6EUQGLMAOUFFJ","json":"https://pith.science/pith/5RKKVEAOUKFTB6EUQGLMAOUFFJ.json","graph_json":"https://pith.science/api/pith-number/5RKKVEAOUKFTB6EUQGLMAOUFFJ/graph.json","events_json":"https://pith.science/api/pith-number/5RKKVEAOUKFTB6EUQGLMAOUFFJ/events.json","paper":"https://pith.science/paper/5RKKVEAO"},"agent_actions":{"view_html":"https://pith.science/pith/5RKKVEAOUKFTB6EUQGLMAOUFFJ","download_json":"https://pith.science/pith/5RKKVEAOUKFTB6EUQGLMAOUFFJ.json","view_paper":"https://pith.science/paper/5RKKVEAO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.10784&json=true","fetch_graph":"https://pith.science/api/pith-number/5RKKVEAOUKFTB6EUQGLMAOUFFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/5RKKVEAOUKFTB6EUQGLMAOUFFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RKKVEAOUKFTB6EUQGLMAOUFFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RKKVEAOUKFTB6EUQGLMAOUFFJ/action/storage_attestation","attest_author":"https://pith.science/pith/5RKKVEAOUKFTB6EUQGLMAOUFFJ/action/author_attestation","sign_citation":"https://pith.science/pith/5RKKVEAOUKFTB6EUQGLMAOUFFJ/action/citation_signature","submit_replication":"https://pith.science/pith/5RKKVEAOUKFTB6EUQGLMAOUFFJ/action/replication_record"}},"created_at":"2026-07-05T07:17:20.798385+00:00","updated_at":"2026-07-05T07:17:20.798385+00:00"}