{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TZ7WSOGTTVA2BSCFMCUKO43PZX","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":"23b0fc090435fd547bbd8aab90c50783428653668a04d55852e9c5b6da8c0c28","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T10:22:43Z","title_canon_sha256":"3fb0042a85aa3c98b5597755507b6aeb75dfe0b4195707d57f9b0efe272e60d4"},"schema_version":"1.0","source":{"id":"2312.04945","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.04945","created_at":"2026-07-05T07:21:54Z"},{"alias_kind":"arxiv_version","alias_value":"2312.04945v1","created_at":"2026-07-05T07:21:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04945","created_at":"2026-07-05T07:21:54Z"},{"alias_kind":"pith_short_12","alias_value":"TZ7WSOGTTVA2","created_at":"2026-07-05T07:21:54Z"},{"alias_kind":"pith_short_16","alias_value":"TZ7WSOGTTVA2BSCF","created_at":"2026-07-05T07:21:54Z"},{"alias_kind":"pith_short_8","alias_value":"TZ7WSOGT","created_at":"2026-07-05T07:21:54Z"}],"graph_snapshots":[{"event_id":"sha256:e74a9c9b274e45f19e1123011f4e2e6702dfc858fd2c820db9ba52e233824cf5","target":"graph","created_at":"2026-07-05T07:21:54Z","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/2312.04945/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Just like the previous generation of task-tuned models, large language models (LLMs) that are adapted to tasks via prompt-based methods like in-context-learning (ICL) perform well in some setups but not in others. This lack of consistency in prompt-based learning hints at a lack of robust generalisation. We here introduce the ICL consistency test -- a contribution to the GenBench collaborative benchmark task (CBT) -- which evaluates how consistent a model makes predictions across many different setups while using the same data. The test is based on different established natural language infere","authors_text":"Dieuwke Hupkes, Elia Bruni, Lucas Weber","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T10:22:43Z","title":"The ICL Consistency Test"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04945","kind":"arxiv","version":1},"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":"sha256:7823255d8042b5d38e412f5707ee693d042867cc649fbf21cd5fa31fcdebdb4d","target":"record","created_at":"2026-07-05T07:21:54Z","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":"23b0fc090435fd547bbd8aab90c50783428653668a04d55852e9c5b6da8c0c28","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T10:22:43Z","title_canon_sha256":"3fb0042a85aa3c98b5597755507b6aeb75dfe0b4195707d57f9b0efe272e60d4"},"schema_version":"1.0","source":{"id":"2312.04945","kind":"arxiv","version":1}},"canonical_sha256":"9e7f6938d39d41a0c84560a8a7736fcdecc8333715afc4b0be30c87e5e8ee963","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e7f6938d39d41a0c84560a8a7736fcdecc8333715afc4b0be30c87e5e8ee963","first_computed_at":"2026-07-05T07:21:54.802398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:21:54.802398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Mw+hTTv/y6qejTcFS6+tjcJDNZLQSZ12DOaYeL9PWA3RfoyWZslaTZkiW9wjWXIQ0IVBHxx2r8vip2DlDx2sCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:21:54.802856Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.04945","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7823255d8042b5d38e412f5707ee693d042867cc649fbf21cd5fa31fcdebdb4d","sha256:e74a9c9b274e45f19e1123011f4e2e6702dfc858fd2c820db9ba52e233824cf5"],"state_sha256":"866c2b5f6071af20ed998401651bee223212c360ebc782302e42b049782be14d"}