{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:CGHPBBTK2BGMXXGOBFORRQTYGA","short_pith_number":"pith:CGHPBBTK","schema_version":"1.0","canonical_sha256":"118ef0866ad04ccbdcce095d18c2783016238936f8da0e83960ac599213750fd","source":{"kind":"arxiv","id":"1610.02995","version":1},"attestation_state":"computed","paper":{"title":"Extrapolation and learning equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Christoph H. Lampert, Georg Martius","submitted_at":"2016-10-10T16:47:36Z","abstract_excerpt":"In classical machine learning, regression is treated as a black box process of identifying a suitable function from a hypothesis set without attempting to gain insight into the mechanism connecting inputs and outputs. In the natural sciences, however, finding an interpretable function for a phenomenon is the prime goal as it allows to understand and generalize results. This paper proposes a novel type of function learning network, called equation learner (EQL), that can learn analytical expressions and is able to extrapolate to unseen domains. It is implemented as an end-to-end differentiable "},"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":"1610.02995","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-10T16:47:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"22c4a36877efde38d1cb9f52fa266d4ca138b983023976efa36a5084a2c64834","abstract_canon_sha256":"d355dda4ee2f2a469b1a1a7ea6843e0189c6a50199320a12c0a421d97e976b45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:02:50.251848Z","signature_b64":"/jBoZXcaSenybyLJBO5FdOfFT2r/ikEcQLmitXC2+r2oP9KEshoK+4MBb4Hhshmq3Y9dEwrULagAxFB4M+00Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"118ef0866ad04ccbdcce095d18c2783016238936f8da0e83960ac599213750fd","last_reissued_at":"2026-05-18T01:02:50.251230Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:02:50.251230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extrapolation and learning equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Christoph H. Lampert, Georg Martius","submitted_at":"2016-10-10T16:47:36Z","abstract_excerpt":"In classical machine learning, regression is treated as a black box process of identifying a suitable function from a hypothesis set without attempting to gain insight into the mechanism connecting inputs and outputs. In the natural sciences, however, finding an interpretable function for a phenomenon is the prime goal as it allows to understand and generalize results. This paper proposes a novel type of function learning network, called equation learner (EQL), that can learn analytical expressions and is able to extrapolate to unseen domains. It is implemented as an end-to-end differentiable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.02995","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":"1610.02995","created_at":"2026-05-18T01:02:50.251329+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.02995v1","created_at":"2026-05-18T01:02:50.251329+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.02995","created_at":"2026-05-18T01:02:50.251329+00:00"},{"alias_kind":"pith_short_12","alias_value":"CGHPBBTK2BGM","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_16","alias_value":"CGHPBBTK2BGMXXGO","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_8","alias_value":"CGHPBBTK","created_at":"2026-05-18T12:30:09.641336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2605.23272","citing_title":"When Good Equations Get Bad Scores: Improving Symbolic Regression Through Better Parameter Optimization","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16724","citing_title":"Discovering interpretable low-dimensional dynamics using maximum entropy","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2512.12448","citing_title":"Optimized Architectures for Kolmogorov-Arnold Networks","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10685","citing_title":"GESR: A Genetic Programming-Based Symbolic Regression Method with Gene Editing","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10685","citing_title":"GESR: A Genetic Programming-Based Symbolic Regression Method with Gene Editing","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11233","citing_title":"A Comparative Study of Model Selection Criteria for Symbolic Regression","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10685","citing_title":"GESR: A Genetic Programming-Based Symbolic Regression Method with Gene Editing","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2404.19756","citing_title":"KAN: Kolmogorov-Arnold Networks","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03841","citing_title":"Complex Equation Learner: Rational Symbolic Regression with Gradient Descent in Complex Domain","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16842","citing_title":"Singularity Formation: Synergy in Theoretical, Numerical and Machine Learning Approaches","ref_index":248,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CGHPBBTK2BGMXXGOBFORRQTYGA","json":"https://pith.science/pith/CGHPBBTK2BGMXXGOBFORRQTYGA.json","graph_json":"https://pith.science/api/pith-number/CGHPBBTK2BGMXXGOBFORRQTYGA/graph.json","events_json":"https://pith.science/api/pith-number/CGHPBBTK2BGMXXGOBFORRQTYGA/events.json","paper":"https://pith.science/paper/CGHPBBTK"},"agent_actions":{"view_html":"https://pith.science/pith/CGHPBBTK2BGMXXGOBFORRQTYGA","download_json":"https://pith.science/pith/CGHPBBTK2BGMXXGOBFORRQTYGA.json","view_paper":"https://pith.science/paper/CGHPBBTK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.02995&json=true","fetch_graph":"https://pith.science/api/pith-number/CGHPBBTK2BGMXXGOBFORRQTYGA/graph.json","fetch_events":"https://pith.science/api/pith-number/CGHPBBTK2BGMXXGOBFORRQTYGA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CGHPBBTK2BGMXXGOBFORRQTYGA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CGHPBBTK2BGMXXGOBFORRQTYGA/action/storage_attestation","attest_author":"https://pith.science/pith/CGHPBBTK2BGMXXGOBFORRQTYGA/action/author_attestation","sign_citation":"https://pith.science/pith/CGHPBBTK2BGMXXGOBFORRQTYGA/action/citation_signature","submit_replication":"https://pith.science/pith/CGHPBBTK2BGMXXGOBFORRQTYGA/action/replication_record"}},"created_at":"2026-05-18T01:02:50.251329+00:00","updated_at":"2026-05-18T01:02:50.251329+00:00"}