{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MQS2ERQUIKAMETVTIJQUVKC4OR","short_pith_number":"pith:MQS2ERQU","schema_version":"1.0","canonical_sha256":"6425a246144280c24eb342614aa85c746849bd32667c0feb6f31bb9881274524","source":{"kind":"arxiv","id":"2203.15099","version":3},"attestation_state":"computed","paper":{"title":"LogicInference: A New Dataset for Teaching Logical Inference to seq2seq Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Joshua Ainslie, Santiago Ontanon, Vaclav Cvicek, Zachary Fisher","submitted_at":"2022-03-28T21:13:22Z","abstract_excerpt":"Machine learning models such as Transformers or LSTMs struggle with tasks that are compositional in nature such as those involving reasoning/inference. Although many datasets exist to evaluate compositional generalization, when it comes to evaluating inference abilities, options are more limited. This paper presents LogicInference, a new dataset to evaluate the ability of models to perform logical inference. The dataset focuses on inference using propositional logic and a small subset of first-order logic, represented both in semi-formal logical notation, as well as in natural language. We als"},"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":"2203.15099","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-03-28T21:13:22Z","cross_cats_sorted":[],"title_canon_sha256":"489edfdf549a5bdbbf172b8a8bfab1ce432ab5eb1c950212e9a6ca77395d586c","abstract_canon_sha256":"1fd0eb3d00f64b89ed8e0cfce0d90fe12ab41e38caee96af6a4096b6762e0a1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:14.420988Z","signature_b64":"PHDoSYN1AeS/nHRyDi6lZHgl6jb0VeuPDSN/noJ9pd+RO+K54o2CsrFeUgNWsnTx23owRZII+JOC2rKebzK5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6425a246144280c24eb342614aa85c746849bd32667c0feb6f31bb9881274524","last_reissued_at":"2026-07-05T04:13:14.420457Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:14.420457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LogicInference: A New Dataset for Teaching Logical Inference to seq2seq Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Joshua Ainslie, Santiago Ontanon, Vaclav Cvicek, Zachary Fisher","submitted_at":"2022-03-28T21:13:22Z","abstract_excerpt":"Machine learning models such as Transformers or LSTMs struggle with tasks that are compositional in nature such as those involving reasoning/inference. Although many datasets exist to evaluate compositional generalization, when it comes to evaluating inference abilities, options are more limited. This paper presents LogicInference, a new dataset to evaluate the ability of models to perform logical inference. The dataset focuses on inference using propositional logic and a small subset of first-order logic, represented both in semi-formal logical notation, as well as in natural language. We als"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15099","kind":"arxiv","version":3},"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/2203.15099/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":"2203.15099","created_at":"2026-07-05T04:13:14.420523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.15099v3","created_at":"2026-07-05T04:13:14.420523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15099","created_at":"2026-07-05T04:13:14.420523+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQS2ERQUIKAM","created_at":"2026-07-05T04:13:14.420523+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQS2ERQUIKAMETVT","created_at":"2026-07-05T04:13:14.420523+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQS2ERQU","created_at":"2026-07-05T04:13:14.420523+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17905","citing_title":"ChLogic: Evaluating Robustness of Logical Reasoning in Chinese Expressions","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MQS2ERQUIKAMETVTIJQUVKC4OR","json":"https://pith.science/pith/MQS2ERQUIKAMETVTIJQUVKC4OR.json","graph_json":"https://pith.science/api/pith-number/MQS2ERQUIKAMETVTIJQUVKC4OR/graph.json","events_json":"https://pith.science/api/pith-number/MQS2ERQUIKAMETVTIJQUVKC4OR/events.json","paper":"https://pith.science/paper/MQS2ERQU"},"agent_actions":{"view_html":"https://pith.science/pith/MQS2ERQUIKAMETVTIJQUVKC4OR","download_json":"https://pith.science/pith/MQS2ERQUIKAMETVTIJQUVKC4OR.json","view_paper":"https://pith.science/paper/MQS2ERQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.15099&json=true","fetch_graph":"https://pith.science/api/pith-number/MQS2ERQUIKAMETVTIJQUVKC4OR/graph.json","fetch_events":"https://pith.science/api/pith-number/MQS2ERQUIKAMETVTIJQUVKC4OR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQS2ERQUIKAMETVTIJQUVKC4OR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQS2ERQUIKAMETVTIJQUVKC4OR/action/storage_attestation","attest_author":"https://pith.science/pith/MQS2ERQUIKAMETVTIJQUVKC4OR/action/author_attestation","sign_citation":"https://pith.science/pith/MQS2ERQUIKAMETVTIJQUVKC4OR/action/citation_signature","submit_replication":"https://pith.science/pith/MQS2ERQUIKAMETVTIJQUVKC4OR/action/replication_record"}},"created_at":"2026-07-05T04:13:14.420523+00:00","updated_at":"2026-07-05T04:13:14.420523+00:00"}