{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:U6MSTIQI6F2MNNZWW3ZTM7VZPO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"395bcac9fc68d6e3f4aae5021efc3c7e0204a0acd0126edc8ea5920fcbafef3d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-10T18:25:48Z","title_canon_sha256":"34d9046dde478a0a9acf6b70fde864900c7a861108a4ce8c0d0616c283819bb1"},"schema_version":"1.0","source":{"id":"1912.04871","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.04871","created_at":"2026-07-05T04:37:52Z"},{"alias_kind":"arxiv_version","alias_value":"1912.04871v4","created_at":"2026-07-05T04:37:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.04871","created_at":"2026-07-05T04:37:52Z"},{"alias_kind":"pith_short_12","alias_value":"U6MSTIQI6F2M","created_at":"2026-07-05T04:37:52Z"},{"alias_kind":"pith_short_16","alias_value":"U6MSTIQI6F2MNNZW","created_at":"2026-07-05T04:37:52Z"},{"alias_kind":"pith_short_8","alias_value":"U6MSTIQI","created_at":"2026-07-05T04:37:52Z"}],"graph_snapshots":[{"event_id":"sha256:af5a8d1fdd01eaa9d6773c8426977dc1eaefb1413a0f85549479b305965afd86","target":"graph","created_at":"2026-07-05T04:37:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1912.04871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Discovering the underlying mathematical expressions describing a dataset is a core challenge for artificial intelligence. This is the problem of $\\textit{symbolic regression}$. Despite recent advances in training neural networks to solve complex tasks, deep learning approaches to symbolic regression are underexplored. We propose a framework that leverages deep learning for symbolic regression via a simple idea: use a large model to search the space of small models. Specifically, we use a recurrent neural network to emit a distribution over tractable mathematical expressions and employ a novel ","authors_text":"Brenden K. Petersen, Claudio P. Santiago, Joanne T. Kim, Mikel Landajuela, Soo K. Kim, T. Nathan Mundhenk","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-10T18:25:48Z","title":"Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.04871","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:792289b5caa9733aea872319f0d0592a2a1852b4415cc7bbbc5da4c4d1b71023","target":"record","created_at":"2026-07-05T04:37:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"395bcac9fc68d6e3f4aae5021efc3c7e0204a0acd0126edc8ea5920fcbafef3d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-10T18:25:48Z","title_canon_sha256":"34d9046dde478a0a9acf6b70fde864900c7a861108a4ce8c0d0616c283819bb1"},"schema_version":"1.0","source":{"id":"1912.04871","kind":"arxiv","version":4}},"canonical_sha256":"a79929a208f174c6b736b6f3367eb97b82328c50db0507a217591eff29e513f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a79929a208f174c6b736b6f3367eb97b82328c50db0507a217591eff29e513f2","first_computed_at":"2026-07-05T04:37:52.958134Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:37:52.958134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+GZcjdaBHFaIUDN/wr+e2cqkN6K9dsQeXp/A+PdU9iMoGwHrHzD3+nHFEB1NJsxGhDAYagob+2dSACXpS2y7Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:37:52.958603Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.04871","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:792289b5caa9733aea872319f0d0592a2a1852b4415cc7bbbc5da4c4d1b71023","sha256:af5a8d1fdd01eaa9d6773c8426977dc1eaefb1413a0f85549479b305965afd86"],"state_sha256":"26129a6a9a5a5f25a5eeab03fbb03cd9b63e1a9251a1b2615adca386b8f0c939"}