{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:M77ENNZJVMVBDFWUYXXJIPKT73","short_pith_number":"pith:M77ENNZJ","schema_version":"1.0","canonical_sha256":"67fe46b729ab2a1196d4c5ee943d53fefc87645ee303c6d95afa01e6fa06fd8b","source":{"kind":"arxiv","id":"2111.00607","version":3},"attestation_state":"computed","paper":{"title":"A Systematic Investigation of Commonsense Knowledge in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adhiguna Kuncoro, Aida Nematzadeh, Cyprien de Masson d'Autume, Jordan Hoffmann, Phil Blunsom, Xiang Lorraine Li","submitted_at":"2021-10-31T22:20:36Z","abstract_excerpt":"Language models (LMs) trained on large amounts of data have shown impressive performance on many NLP tasks under the zero-shot and few-shot setup. Here we aim to better understand the extent to which such models learn commonsense knowledge -- a critical component of many NLP applications. We conduct a systematic and rigorous zero-shot and few-shot commonsense evaluation of large pre-trained LMs, where we: (i) carefully control for the LMs' ability to exploit potential surface cues and annotation artefacts, and (ii) account for variations in performance that arise from factors that are not rela"},"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":"2111.00607","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-31T22:20:36Z","cross_cats_sorted":[],"title_canon_sha256":"1a2a4dacf5f6273677e050821a0612e8b044d9f2e0ab6d7b0dfd83d087571eba","abstract_canon_sha256":"e418c25d58aaaca59be6461abc1f1cdfcff4191fa2acfb0e67e9a3c030a7f04f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:09.355256Z","signature_b64":"fxCw+j4zyLwDaDMvGNKiTVRP2lstkbxu66xLD+pcJmhDur6k0M5aHbi3FGAZ7nOJYOrPeJXENpm2shx129RjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67fe46b729ab2a1196d4c5ee943d53fefc87645ee303c6d95afa01e6fa06fd8b","last_reissued_at":"2026-07-05T05:12:09.354661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:09.354661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Systematic Investigation of Commonsense Knowledge in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adhiguna Kuncoro, Aida Nematzadeh, Cyprien de Masson d'Autume, Jordan Hoffmann, Phil Blunsom, Xiang Lorraine Li","submitted_at":"2021-10-31T22:20:36Z","abstract_excerpt":"Language models (LMs) trained on large amounts of data have shown impressive performance on many NLP tasks under the zero-shot and few-shot setup. Here we aim to better understand the extent to which such models learn commonsense knowledge -- a critical component of many NLP applications. We conduct a systematic and rigorous zero-shot and few-shot commonsense evaluation of large pre-trained LMs, where we: (i) carefully control for the LMs' ability to exploit potential surface cues and annotation artefacts, and (ii) account for variations in performance that arise from factors that are not rela"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00607","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/2111.00607/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":"2111.00607","created_at":"2026-07-05T05:12:09.354732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.00607v3","created_at":"2026-07-05T05:12:09.354732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00607","created_at":"2026-07-05T05:12:09.354732+00:00"},{"alias_kind":"pith_short_12","alias_value":"M77ENNZJVMVB","created_at":"2026-07-05T05:12:09.354732+00:00"},{"alias_kind":"pith_short_16","alias_value":"M77ENNZJVMVBDFWU","created_at":"2026-07-05T05:12:09.354732+00:00"},{"alias_kind":"pith_short_8","alias_value":"M77ENNZJ","created_at":"2026-07-05T05:12:09.354732+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/M77ENNZJVMVBDFWUYXXJIPKT73","json":"https://pith.science/pith/M77ENNZJVMVBDFWUYXXJIPKT73.json","graph_json":"https://pith.science/api/pith-number/M77ENNZJVMVBDFWUYXXJIPKT73/graph.json","events_json":"https://pith.science/api/pith-number/M77ENNZJVMVBDFWUYXXJIPKT73/events.json","paper":"https://pith.science/paper/M77ENNZJ"},"agent_actions":{"view_html":"https://pith.science/pith/M77ENNZJVMVBDFWUYXXJIPKT73","download_json":"https://pith.science/pith/M77ENNZJVMVBDFWUYXXJIPKT73.json","view_paper":"https://pith.science/paper/M77ENNZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.00607&json=true","fetch_graph":"https://pith.science/api/pith-number/M77ENNZJVMVBDFWUYXXJIPKT73/graph.json","fetch_events":"https://pith.science/api/pith-number/M77ENNZJVMVBDFWUYXXJIPKT73/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M77ENNZJVMVBDFWUYXXJIPKT73/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M77ENNZJVMVBDFWUYXXJIPKT73/action/storage_attestation","attest_author":"https://pith.science/pith/M77ENNZJVMVBDFWUYXXJIPKT73/action/author_attestation","sign_citation":"https://pith.science/pith/M77ENNZJVMVBDFWUYXXJIPKT73/action/citation_signature","submit_replication":"https://pith.science/pith/M77ENNZJVMVBDFWUYXXJIPKT73/action/replication_record"}},"created_at":"2026-07-05T05:12:09.354732+00:00","updated_at":"2026-07-05T05:12:09.354732+00:00"}