{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ESQEZKII4O7TY77XNWL2ECUVDP","short_pith_number":"pith:ESQEZKII","schema_version":"1.0","canonical_sha256":"24a04ca908e3bf3c7ff76d97a20a951be9936ca1b80212d7d5912e129a6ff2c4","source":{"kind":"arxiv","id":"2308.07899","version":2},"attestation_state":"computed","paper":{"title":"Correct and Optimal: the Regular Expression Inference Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.FL"],"primary_cat":"cs.LG","authors_text":"Ignacio Iacobacci, Martin Berger, Mojtaba Valizadeh, Philip John Gorinski","submitted_at":"2023-08-15T17:40:10Z","abstract_excerpt":"We propose regular expression inference (REI) as a challenge for code/language modelling, and the wider machine learning community. REI is a supervised machine learning (ML) and program optimisation task, and poses the problem of finding minimal regular expressions from examples: Given two finite sets of strings $P$ and $N$ and a cost function $cost(\\cdot)$, the task is to generate an expression $r$ that accepts all strings in $P$ and rejects all strings in $N$, while no other such expression $r'$ exists with $cost(r')<cost(r)$. REI has advantages as a challenge problem: (i) regular expression"},"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":"2308.07899","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-15T17:40:10Z","cross_cats_sorted":["cs.CL","cs.FL"],"title_canon_sha256":"3439e33febe73d937efc5e11746c75e8092dcbd564830787065b07896a3c7f23","abstract_canon_sha256":"ee9f156f6ae478c4ec04439f9c5f3e99aab350f1c82c5d1b834c61114ea21c97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:28.026096Z","signature_b64":"cYnkZZrzVMTol/E/se8u/q7HfjjExVqvtSDWQea27OPKt/iZFkRxDl7A2Sy+AXI9Z0ar3xYQHvDuegOdTf6IDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24a04ca908e3bf3c7ff76d97a20a951be9936ca1b80212d7d5912e129a6ff2c4","last_reissued_at":"2026-07-05T08:17:28.025681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:28.025681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Correct and Optimal: the Regular Expression Inference Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.FL"],"primary_cat":"cs.LG","authors_text":"Ignacio Iacobacci, Martin Berger, Mojtaba Valizadeh, Philip John Gorinski","submitted_at":"2023-08-15T17:40:10Z","abstract_excerpt":"We propose regular expression inference (REI) as a challenge for code/language modelling, and the wider machine learning community. REI is a supervised machine learning (ML) and program optimisation task, and poses the problem of finding minimal regular expressions from examples: Given two finite sets of strings $P$ and $N$ and a cost function $cost(\\cdot)$, the task is to generate an expression $r$ that accepts all strings in $P$ and rejects all strings in $N$, while no other such expression $r'$ exists with $cost(r')<cost(r)$. REI has advantages as a challenge problem: (i) regular expression"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.07899","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/2308.07899/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":"2308.07899","created_at":"2026-07-05T08:17:28.025746+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.07899v2","created_at":"2026-07-05T08:17:28.025746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.07899","created_at":"2026-07-05T08:17:28.025746+00:00"},{"alias_kind":"pith_short_12","alias_value":"ESQEZKII4O7T","created_at":"2026-07-05T08:17:28.025746+00:00"},{"alias_kind":"pith_short_16","alias_value":"ESQEZKII4O7TY77X","created_at":"2026-07-05T08:17:28.025746+00:00"},{"alias_kind":"pith_short_8","alias_value":"ESQEZKII","created_at":"2026-07-05T08:17:28.025746+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/ESQEZKII4O7TY77XNWL2ECUVDP","json":"https://pith.science/pith/ESQEZKII4O7TY77XNWL2ECUVDP.json","graph_json":"https://pith.science/api/pith-number/ESQEZKII4O7TY77XNWL2ECUVDP/graph.json","events_json":"https://pith.science/api/pith-number/ESQEZKII4O7TY77XNWL2ECUVDP/events.json","paper":"https://pith.science/paper/ESQEZKII"},"agent_actions":{"view_html":"https://pith.science/pith/ESQEZKII4O7TY77XNWL2ECUVDP","download_json":"https://pith.science/pith/ESQEZKII4O7TY77XNWL2ECUVDP.json","view_paper":"https://pith.science/paper/ESQEZKII","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.07899&json=true","fetch_graph":"https://pith.science/api/pith-number/ESQEZKII4O7TY77XNWL2ECUVDP/graph.json","fetch_events":"https://pith.science/api/pith-number/ESQEZKII4O7TY77XNWL2ECUVDP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ESQEZKII4O7TY77XNWL2ECUVDP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ESQEZKII4O7TY77XNWL2ECUVDP/action/storage_attestation","attest_author":"https://pith.science/pith/ESQEZKII4O7TY77XNWL2ECUVDP/action/author_attestation","sign_citation":"https://pith.science/pith/ESQEZKII4O7TY77XNWL2ECUVDP/action/citation_signature","submit_replication":"https://pith.science/pith/ESQEZKII4O7TY77XNWL2ECUVDP/action/replication_record"}},"created_at":"2026-07-05T08:17:28.025746+00:00","updated_at":"2026-07-05T08:17:28.025746+00:00"}