{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6LPO4E7UJ7HMVB2NHC5KQ7BLLY","short_pith_number":"pith:6LPO4E7U","schema_version":"1.0","canonical_sha256":"f2deee13f44fceca874d38baa87c2b5e360782d07b94b9eb45eab14ba378a5f2","source":{"kind":"arxiv","id":"2311.02765","version":1},"attestation_state":"computed","paper":{"title":"Rule Learning as Machine Translation using the Atomic Knowledge Bank","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ana Ozaki, Kristoffer {\\AE}s{\\o}y","submitted_at":"2023-11-05T20:48:54Z","abstract_excerpt":"Machine learning models, and in particular language models, are being applied to various tasks that require reasoning. While such models are good at capturing patterns their ability to reason in a trustable and controlled manner is frequently questioned. On the other hand, logic-based rule systems allow for controlled inspection and already established verification methods. However it is well-known that creating such systems manually is time-consuming and prone to errors. We explore the capability of transformers to translate sentences expressing rules in natural language into logical rules. W"},"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":"2311.02765","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-05T20:48:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6e0035648c31f5fdfccca8ca31be2282c5d372034f04f9d750ca27bf642278e2","abstract_canon_sha256":"6edb7853e93cade8e5743311ac7988e9dcb6914142e05ce70137074b8a9c89c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:17.478112Z","signature_b64":"A08+G5VEdERquiFAI4Seag9bTGnHJITrCt9e+mBv9fgWetPtjAIherPlDMYNjGOdINLfRmdhJgJA9ElWZzO5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2deee13f44fceca874d38baa87c2b5e360782d07b94b9eb45eab14ba378a5f2","last_reissued_at":"2026-07-05T07:09:17.477616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:17.477616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rule Learning as Machine Translation using the Atomic Knowledge Bank","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ana Ozaki, Kristoffer {\\AE}s{\\o}y","submitted_at":"2023-11-05T20:48:54Z","abstract_excerpt":"Machine learning models, and in particular language models, are being applied to various tasks that require reasoning. While such models are good at capturing patterns their ability to reason in a trustable and controlled manner is frequently questioned. On the other hand, logic-based rule systems allow for controlled inspection and already established verification methods. However it is well-known that creating such systems manually is time-consuming and prone to errors. We explore the capability of transformers to translate sentences expressing rules in natural language into logical rules. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02765","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/2311.02765/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":"2311.02765","created_at":"2026-07-05T07:09:17.477671+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.02765v1","created_at":"2026-07-05T07:09:17.477671+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02765","created_at":"2026-07-05T07:09:17.477671+00:00"},{"alias_kind":"pith_short_12","alias_value":"6LPO4E7UJ7HM","created_at":"2026-07-05T07:09:17.477671+00:00"},{"alias_kind":"pith_short_16","alias_value":"6LPO4E7UJ7HMVB2N","created_at":"2026-07-05T07:09:17.477671+00:00"},{"alias_kind":"pith_short_8","alias_value":"6LPO4E7U","created_at":"2026-07-05T07:09:17.477671+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10971","citing_title":"Rule2Text: A Framework for Generating and Evaluating Natural Language Explanations of Knowledge Graph Rules","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6LPO4E7UJ7HMVB2NHC5KQ7BLLY","json":"https://pith.science/pith/6LPO4E7UJ7HMVB2NHC5KQ7BLLY.json","graph_json":"https://pith.science/api/pith-number/6LPO4E7UJ7HMVB2NHC5KQ7BLLY/graph.json","events_json":"https://pith.science/api/pith-number/6LPO4E7UJ7HMVB2NHC5KQ7BLLY/events.json","paper":"https://pith.science/paper/6LPO4E7U"},"agent_actions":{"view_html":"https://pith.science/pith/6LPO4E7UJ7HMVB2NHC5KQ7BLLY","download_json":"https://pith.science/pith/6LPO4E7UJ7HMVB2NHC5KQ7BLLY.json","view_paper":"https://pith.science/paper/6LPO4E7U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.02765&json=true","fetch_graph":"https://pith.science/api/pith-number/6LPO4E7UJ7HMVB2NHC5KQ7BLLY/graph.json","fetch_events":"https://pith.science/api/pith-number/6LPO4E7UJ7HMVB2NHC5KQ7BLLY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6LPO4E7UJ7HMVB2NHC5KQ7BLLY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6LPO4E7UJ7HMVB2NHC5KQ7BLLY/action/storage_attestation","attest_author":"https://pith.science/pith/6LPO4E7UJ7HMVB2NHC5KQ7BLLY/action/author_attestation","sign_citation":"https://pith.science/pith/6LPO4E7UJ7HMVB2NHC5KQ7BLLY/action/citation_signature","submit_replication":"https://pith.science/pith/6LPO4E7UJ7HMVB2NHC5KQ7BLLY/action/replication_record"}},"created_at":"2026-07-05T07:09:17.477671+00:00","updated_at":"2026-07-05T07:09:17.477671+00:00"}