{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RUAEW4HJGYZIOVFN5Q7LQW7JN4","short_pith_number":"pith:RUAEW4HJ","schema_version":"1.0","canonical_sha256":"8d004b70e936328754adec3eb85be96f1c5723145367dc6441be0fdfb63370ba","source":{"kind":"arxiv","id":"2302.09458","version":1},"attestation_state":"computed","paper":{"title":"Learning Language Representations with Logical Inductive Bias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.LO"],"primary_cat":"cs.CL","authors_text":"Jianshu Chen","submitted_at":"2023-02-19T02:21:32Z","abstract_excerpt":"Transformer architectures have achieved great success in solving natural language tasks, which learn strong language representations from large-scale unlabeled texts. In this paper, we seek to go further beyond and explore a new logical inductive bias for better language representation learning. Logic reasoning is known as a formal methodology to reach answers from given knowledge and facts. Inspired by such a view, we develop a novel neural architecture named FOLNet (First-Order Logic Network), to encode this new inductive bias. We construct a set of neural logic operators as learnable Horn c"},"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":"2302.09458","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-19T02:21:32Z","cross_cats_sorted":["cs.LG","cs.LO"],"title_canon_sha256":"0daf3666d14b399baaa074a130a9080ca9e9f8d54c9adb519d8de5165f190eff","abstract_canon_sha256":"bf0931197e34b246e27e5e18207369c351b5b49de271510f7c342f7ab2fbd58c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:25.994943Z","signature_b64":"lPiCE+Vz5j4Trv4DSE98pUKloPw8SqSYe9Rgd9e3gpVJFTU6b1MuKp7gECDulMwce/N5PLV45oWwvAZCtMKrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d004b70e936328754adec3eb85be96f1c5723145367dc6441be0fdfb63370ba","last_reissued_at":"2026-07-05T05:43:25.994525Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:25.994525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Language Representations with Logical Inductive Bias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.LO"],"primary_cat":"cs.CL","authors_text":"Jianshu Chen","submitted_at":"2023-02-19T02:21:32Z","abstract_excerpt":"Transformer architectures have achieved great success in solving natural language tasks, which learn strong language representations from large-scale unlabeled texts. In this paper, we seek to go further beyond and explore a new logical inductive bias for better language representation learning. Logic reasoning is known as a formal methodology to reach answers from given knowledge and facts. Inspired by such a view, we develop a novel neural architecture named FOLNet (First-Order Logic Network), to encode this new inductive bias. We construct a set of neural logic operators as learnable Horn c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.09458","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/2302.09458/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":"2302.09458","created_at":"2026-07-05T05:43:25.994582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.09458v1","created_at":"2026-07-05T05:43:25.994582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.09458","created_at":"2026-07-05T05:43:25.994582+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUAEW4HJGYZI","created_at":"2026-07-05T05:43:25.994582+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUAEW4HJGYZIOVFN","created_at":"2026-07-05T05:43:25.994582+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUAEW4HJ","created_at":"2026-07-05T05:43:25.994582+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00759","citing_title":"Enhancing Transformers for Generalizable First-Order Logical Entailment","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RUAEW4HJGYZIOVFN5Q7LQW7JN4","json":"https://pith.science/pith/RUAEW4HJGYZIOVFN5Q7LQW7JN4.json","graph_json":"https://pith.science/api/pith-number/RUAEW4HJGYZIOVFN5Q7LQW7JN4/graph.json","events_json":"https://pith.science/api/pith-number/RUAEW4HJGYZIOVFN5Q7LQW7JN4/events.json","paper":"https://pith.science/paper/RUAEW4HJ"},"agent_actions":{"view_html":"https://pith.science/pith/RUAEW4HJGYZIOVFN5Q7LQW7JN4","download_json":"https://pith.science/pith/RUAEW4HJGYZIOVFN5Q7LQW7JN4.json","view_paper":"https://pith.science/paper/RUAEW4HJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.09458&json=true","fetch_graph":"https://pith.science/api/pith-number/RUAEW4HJGYZIOVFN5Q7LQW7JN4/graph.json","fetch_events":"https://pith.science/api/pith-number/RUAEW4HJGYZIOVFN5Q7LQW7JN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUAEW4HJGYZIOVFN5Q7LQW7JN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUAEW4HJGYZIOVFN5Q7LQW7JN4/action/storage_attestation","attest_author":"https://pith.science/pith/RUAEW4HJGYZIOVFN5Q7LQW7JN4/action/author_attestation","sign_citation":"https://pith.science/pith/RUAEW4HJGYZIOVFN5Q7LQW7JN4/action/citation_signature","submit_replication":"https://pith.science/pith/RUAEW4HJGYZIOVFN5Q7LQW7JN4/action/replication_record"}},"created_at":"2026-07-05T05:43:25.994582+00:00","updated_at":"2026-07-05T05:43:25.994582+00:00"}