{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:M77ENNZJVMVBDFWUYXXJIPKT73","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e418c25d58aaaca59be6461abc1f1cdfcff4191fa2acfb0e67e9a3c030a7f04f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-31T22:20:36Z","title_canon_sha256":"1a2a4dacf5f6273677e050821a0612e8b044d9f2e0ab6d7b0dfd83d087571eba"},"schema_version":"1.0","source":{"id":"2111.00607","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.00607","created_at":"2026-07-05T05:12:09Z"},{"alias_kind":"arxiv_version","alias_value":"2111.00607v3","created_at":"2026-07-05T05:12:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00607","created_at":"2026-07-05T05:12:09Z"},{"alias_kind":"pith_short_12","alias_value":"M77ENNZJVMVB","created_at":"2026-07-05T05:12:09Z"},{"alias_kind":"pith_short_16","alias_value":"M77ENNZJVMVBDFWU","created_at":"2026-07-05T05:12:09Z"},{"alias_kind":"pith_short_8","alias_value":"M77ENNZJ","created_at":"2026-07-05T05:12:09Z"}],"graph_snapshots":[{"event_id":"sha256:9460e3a692956054eb3c833d31c137b28b713f9cc42ae35c668a9dfbd03f85ce","target":"graph","created_at":"2026-07-05T05:12:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2111.00607/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Adhiguna Kuncoro, Aida Nematzadeh, Cyprien de Masson d'Autume, Jordan Hoffmann, Phil Blunsom, Xiang Lorraine Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-31T22:20:36Z","title":"A Systematic Investigation of Commonsense Knowledge in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00607","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b54a0ee8cfb7e2352122457131eee72d1ff0c34997d8b9bbcbbade988e2ee410","target":"record","created_at":"2026-07-05T05:12:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e418c25d58aaaca59be6461abc1f1cdfcff4191fa2acfb0e67e9a3c030a7f04f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-31T22:20:36Z","title_canon_sha256":"1a2a4dacf5f6273677e050821a0612e8b044d9f2e0ab6d7b0dfd83d087571eba"},"schema_version":"1.0","source":{"id":"2111.00607","kind":"arxiv","version":3}},"canonical_sha256":"67fe46b729ab2a1196d4c5ee943d53fefc87645ee303c6d95afa01e6fa06fd8b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67fe46b729ab2a1196d4c5ee943d53fefc87645ee303c6d95afa01e6fa06fd8b","first_computed_at":"2026-07-05T05:12:09.354661Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:12:09.354661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fxCw+j4zyLwDaDMvGNKiTVRP2lstkbxu66xLD+pcJmhDur6k0M5aHbi3FGAZ7nOJYOrPeJXENpm2shx129RjAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:12:09.355256Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.00607","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b54a0ee8cfb7e2352122457131eee72d1ff0c34997d8b9bbcbbade988e2ee410","sha256:9460e3a692956054eb3c833d31c137b28b713f9cc42ae35c668a9dfbd03f85ce"],"state_sha256":"008084720aa50f7f126e6e798d032e158a8dec0ce71991da10ffae8155979cbf"}