{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JGGASND7DETLDFOTKLN5QOQK6G","short_pith_number":"pith:JGGASND7","schema_version":"1.0","canonical_sha256":"498c09347f1926b195d352dbd83a0af1999f929dd8bc5f653297f3c7e2e1903e","source":{"kind":"arxiv","id":"2106.06427","version":1},"attestation_state":"computed","paper":{"title":"Neural Symbolic Regression that Scales","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Neitz, Aurelien Lucchi, Giambattista Parascandolo, Luca Biggio, Tommaso Bendinelli","submitted_at":"2021-06-11T14:35:22Z","abstract_excerpt":"Symbolic equations are at the core of scientific discovery. The task of discovering the underlying equation from a set of input-output pairs is called symbolic regression. Traditionally, symbolic regression methods use hand-designed strategies that do not improve with experience. In this paper, we introduce the first symbolic regression method that leverages large scale pre-training. We procedurally generate an unbounded set of equations, and simultaneously pre-train a Transformer to predict the symbolic equation from a corresponding set of input-output-pairs. At test time, we query the model "},"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":"2106.06427","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-11T14:35:22Z","cross_cats_sorted":[],"title_canon_sha256":"ba1aea7c060c18f972878dc25e52b59e8fbb33419f44115d23332c772b5f9e13","abstract_canon_sha256":"41dda89678414c80e6ebd27a590390a3a9c8ab2fb2be56a56ca557b26fa70d45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:29.769153Z","signature_b64":"BRuPfJvYHV8hKxaEouanAmTzJHPzKrPfDJtaLQyM3Z3iPsKynTQYlBEcUumm8Gt7f0nJdVRXlYjpauFKwmYRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"498c09347f1926b195d352dbd83a0af1999f929dd8bc5f653297f3c7e2e1903e","last_reissued_at":"2026-07-05T02:48:29.768648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:29.768648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Symbolic Regression that Scales","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Neitz, Aurelien Lucchi, Giambattista Parascandolo, Luca Biggio, Tommaso Bendinelli","submitted_at":"2021-06-11T14:35:22Z","abstract_excerpt":"Symbolic equations are at the core of scientific discovery. The task of discovering the underlying equation from a set of input-output pairs is called symbolic regression. Traditionally, symbolic regression methods use hand-designed strategies that do not improve with experience. In this paper, we introduce the first symbolic regression method that leverages large scale pre-training. We procedurally generate an unbounded set of equations, and simultaneously pre-train a Transformer to predict the symbolic equation from a corresponding set of input-output-pairs. At test time, we query the model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06427","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.06427/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":"2106.06427","created_at":"2026-07-05T02:48:29.768707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06427v1","created_at":"2026-07-05T02:48:29.768707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06427","created_at":"2026-07-05T02:48:29.768707+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGGASND7DETL","created_at":"2026-07-05T02:48:29.768707+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGGASND7DETLDFOT","created_at":"2026-07-05T02:48:29.768707+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGGASND7","created_at":"2026-07-05T02:48:29.768707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JGGASND7DETLDFOTKLN5QOQK6G","json":"https://pith.science/pith/JGGASND7DETLDFOTKLN5QOQK6G.json","graph_json":"https://pith.science/api/pith-number/JGGASND7DETLDFOTKLN5QOQK6G/graph.json","events_json":"https://pith.science/api/pith-number/JGGASND7DETLDFOTKLN5QOQK6G/events.json","paper":"https://pith.science/paper/JGGASND7"},"agent_actions":{"view_html":"https://pith.science/pith/JGGASND7DETLDFOTKLN5QOQK6G","download_json":"https://pith.science/pith/JGGASND7DETLDFOTKLN5QOQK6G.json","view_paper":"https://pith.science/paper/JGGASND7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06427&json=true","fetch_graph":"https://pith.science/api/pith-number/JGGASND7DETLDFOTKLN5QOQK6G/graph.json","fetch_events":"https://pith.science/api/pith-number/JGGASND7DETLDFOTKLN5QOQK6G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGGASND7DETLDFOTKLN5QOQK6G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGGASND7DETLDFOTKLN5QOQK6G/action/storage_attestation","attest_author":"https://pith.science/pith/JGGASND7DETLDFOTKLN5QOQK6G/action/author_attestation","sign_citation":"https://pith.science/pith/JGGASND7DETLDFOTKLN5QOQK6G/action/citation_signature","submit_replication":"https://pith.science/pith/JGGASND7DETLDFOTKLN5QOQK6G/action/replication_record"}},"created_at":"2026-07-05T02:48:29.768707+00:00","updated_at":"2026-07-05T02:48:29.768707+00:00"}