{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GU6OWWMIGQ5BNDQUWCJ3O5N2ME","short_pith_number":"pith:GU6OWWMI","schema_version":"1.0","canonical_sha256":"353ceb5988343a168e14b093b775ba6110c695c9040940343ffac91b95eb4a8c","source":{"kind":"arxiv","id":"2011.09159","version":1},"attestation_state":"computed","paper":{"title":"Do Fine-tuned Commonsense Language Models Really Generalize?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ke Shen, Mayank Kejriwal","submitted_at":"2020-11-18T08:52:49Z","abstract_excerpt":"Recently, transformer-based methods such as RoBERTa and GPT-3 have led to significant experimental advances in natural language processing tasks such as question answering and commonsense reasoning. The latter is typically evaluated through multiple benchmarks framed as multiple-choice instances of the former. According to influential leaderboards hosted by the Allen Institute (evaluating state-of-the-art performance on commonsense reasoning benchmarks), models based on such transformer methods are approaching human-like performance and have average accuracy well over 80% on many benchmarks. S"},"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":"2011.09159","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-18T08:52:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e45c45d29ddbd54e065e6856262f50e948bf7d0893375d6ca41671f68049769f","abstract_canon_sha256":"1fb2626428eb4514ae66abfa9b8e35377b0553c81c3a057862e216b7edcf8c8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:52:41.181962Z","signature_b64":"L+sQBAmcOg3HuKh9LjxsdaFFLq+IbmOxsANfi6WwbI/629p6aq9GStlEwo/eoAQu326zT0EdSRXdCeOwA3E4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"353ceb5988343a168e14b093b775ba6110c695c9040940343ffac91b95eb4a8c","last_reissued_at":"2026-07-05T01:52:41.181611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:52:41.181611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Fine-tuned Commonsense Language Models Really Generalize?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ke Shen, Mayank Kejriwal","submitted_at":"2020-11-18T08:52:49Z","abstract_excerpt":"Recently, transformer-based methods such as RoBERTa and GPT-3 have led to significant experimental advances in natural language processing tasks such as question answering and commonsense reasoning. The latter is typically evaluated through multiple benchmarks framed as multiple-choice instances of the former. According to influential leaderboards hosted by the Allen Institute (evaluating state-of-the-art performance on commonsense reasoning benchmarks), models based on such transformer methods are approaching human-like performance and have average accuracy well over 80% on many benchmarks. S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.09159","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/2011.09159/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":"2011.09159","created_at":"2026-07-05T01:52:41.181668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.09159v1","created_at":"2026-07-05T01:52:41.181668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.09159","created_at":"2026-07-05T01:52:41.181668+00:00"},{"alias_kind":"pith_short_12","alias_value":"GU6OWWMIGQ5B","created_at":"2026-07-05T01:52:41.181668+00:00"},{"alias_kind":"pith_short_16","alias_value":"GU6OWWMIGQ5BNDQU","created_at":"2026-07-05T01:52:41.181668+00:00"},{"alias_kind":"pith_short_8","alias_value":"GU6OWWMI","created_at":"2026-07-05T01:52:41.181668+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/GU6OWWMIGQ5BNDQUWCJ3O5N2ME","json":"https://pith.science/pith/GU6OWWMIGQ5BNDQUWCJ3O5N2ME.json","graph_json":"https://pith.science/api/pith-number/GU6OWWMIGQ5BNDQUWCJ3O5N2ME/graph.json","events_json":"https://pith.science/api/pith-number/GU6OWWMIGQ5BNDQUWCJ3O5N2ME/events.json","paper":"https://pith.science/paper/GU6OWWMI"},"agent_actions":{"view_html":"https://pith.science/pith/GU6OWWMIGQ5BNDQUWCJ3O5N2ME","download_json":"https://pith.science/pith/GU6OWWMIGQ5BNDQUWCJ3O5N2ME.json","view_paper":"https://pith.science/paper/GU6OWWMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.09159&json=true","fetch_graph":"https://pith.science/api/pith-number/GU6OWWMIGQ5BNDQUWCJ3O5N2ME/graph.json","fetch_events":"https://pith.science/api/pith-number/GU6OWWMIGQ5BNDQUWCJ3O5N2ME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GU6OWWMIGQ5BNDQUWCJ3O5N2ME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GU6OWWMIGQ5BNDQUWCJ3O5N2ME/action/storage_attestation","attest_author":"https://pith.science/pith/GU6OWWMIGQ5BNDQUWCJ3O5N2ME/action/author_attestation","sign_citation":"https://pith.science/pith/GU6OWWMIGQ5BNDQUWCJ3O5N2ME/action/citation_signature","submit_replication":"https://pith.science/pith/GU6OWWMIGQ5BNDQUWCJ3O5N2ME/action/replication_record"}},"created_at":"2026-07-05T01:52:41.181668+00:00","updated_at":"2026-07-05T01:52:41.181668+00:00"}