{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4XAO2MJ4NNKOGFZX7TOEITNT5R","short_pith_number":"pith:4XAO2MJ4","schema_version":"1.0","canonical_sha256":"e5c0ed313c6b54e31737fcdc444db3ec41b30c410cefca500b35cf105299f3b1","source":{"kind":"arxiv","id":"2201.04600","version":2},"attestation_state":"computed","paper":{"title":"Deep Symbolic Regression for Recurrent Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fran\\c{c}ois Charton, Guillaume Lample, Pierre-Alexandre Kamienny, St\\'ephane d'Ascoli","submitted_at":"2022-01-12T17:53:50Z","abstract_excerpt":"Symbolic regression, i.e. predicting a function from the observation of its values, is well-known to be a challenging task. In this paper, we train Transformers to infer the function or recurrence relation underlying sequences of integers or floats, a typical task in human IQ tests which has hardly been tackled in the machine learning literature. We evaluate our integer model on a subset of OEIS sequences, and show that it outperforms built-in Mathematica functions for recurrence prediction. We also demonstrate that our float model is able to yield informative approximations of out-of-vocabula"},"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":"2201.04600","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-12T17:53:50Z","cross_cats_sorted":[],"title_canon_sha256":"7cccdd301e67ed811046320e8bb6181f45933241c02d580bebd2d2ec2bcf6904","abstract_canon_sha256":"ec7e8c1368608c22fc7ca97f5b1845363f96f3f337e1f26766f44f5aa252286f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:35:41.750038Z","signature_b64":"i5+NMnQERirt7KOiHjSwyYnZ3NvAbxzSitUnwKHsgSDh3r7Wp6Lj+PZthV4mUMAY2tYXlpqLDuKunQQ6JZgTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5c0ed313c6b54e31737fcdc444db3ec41b30c410cefca500b35cf105299f3b1","last_reissued_at":"2026-07-05T04:35:41.749526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:35:41.749526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Symbolic Regression for Recurrent Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fran\\c{c}ois Charton, Guillaume Lample, Pierre-Alexandre Kamienny, St\\'ephane d'Ascoli","submitted_at":"2022-01-12T17:53:50Z","abstract_excerpt":"Symbolic regression, i.e. predicting a function from the observation of its values, is well-known to be a challenging task. In this paper, we train Transformers to infer the function or recurrence relation underlying sequences of integers or floats, a typical task in human IQ tests which has hardly been tackled in the machine learning literature. We evaluate our integer model on a subset of OEIS sequences, and show that it outperforms built-in Mathematica functions for recurrence prediction. We also demonstrate that our float model is able to yield informative approximations of out-of-vocabula"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.04600","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/2201.04600/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":"2201.04600","created_at":"2026-07-05T04:35:41.749587+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.04600v2","created_at":"2026-07-05T04:35:41.749587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.04600","created_at":"2026-07-05T04:35:41.749587+00:00"},{"alias_kind":"pith_short_12","alias_value":"4XAO2MJ4NNKO","created_at":"2026-07-05T04:35:41.749587+00:00"},{"alias_kind":"pith_short_16","alias_value":"4XAO2MJ4NNKOGFZX","created_at":"2026-07-05T04:35:41.749587+00:00"},{"alias_kind":"pith_short_8","alias_value":"4XAO2MJ4","created_at":"2026-07-05T04:35:41.749587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.17448","citing_title":"In Context Learning and Reasoning for Symbolic Regression with Large Language Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19789","citing_title":"From Data to Theory: Autonomous Large Language Model Agents for Materials Science","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16232","citing_title":"Neuro-Symbolic ODE Discovery with Latent Grammar Flow","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4XAO2MJ4NNKOGFZX7TOEITNT5R","json":"https://pith.science/pith/4XAO2MJ4NNKOGFZX7TOEITNT5R.json","graph_json":"https://pith.science/api/pith-number/4XAO2MJ4NNKOGFZX7TOEITNT5R/graph.json","events_json":"https://pith.science/api/pith-number/4XAO2MJ4NNKOGFZX7TOEITNT5R/events.json","paper":"https://pith.science/paper/4XAO2MJ4"},"agent_actions":{"view_html":"https://pith.science/pith/4XAO2MJ4NNKOGFZX7TOEITNT5R","download_json":"https://pith.science/pith/4XAO2MJ4NNKOGFZX7TOEITNT5R.json","view_paper":"https://pith.science/paper/4XAO2MJ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.04600&json=true","fetch_graph":"https://pith.science/api/pith-number/4XAO2MJ4NNKOGFZX7TOEITNT5R/graph.json","fetch_events":"https://pith.science/api/pith-number/4XAO2MJ4NNKOGFZX7TOEITNT5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4XAO2MJ4NNKOGFZX7TOEITNT5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4XAO2MJ4NNKOGFZX7TOEITNT5R/action/storage_attestation","attest_author":"https://pith.science/pith/4XAO2MJ4NNKOGFZX7TOEITNT5R/action/author_attestation","sign_citation":"https://pith.science/pith/4XAO2MJ4NNKOGFZX7TOEITNT5R/action/citation_signature","submit_replication":"https://pith.science/pith/4XAO2MJ4NNKOGFZX7TOEITNT5R/action/replication_record"}},"created_at":"2026-07-05T04:35:41.749587+00:00","updated_at":"2026-07-05T04:35:41.749587+00:00"}