{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:B2AVNQO5X6BX2QLWNAE2CY2JQH","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":"31d912097a70ba972ade922f04ab55350f04cda106f3629b5a114d22413640dc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T13:25:24Z","title_canon_sha256":"45ff96eb0e039c1dd6268ab4e8b5edcd2be9d98837c5678379cb309063b158c6"},"schema_version":"1.0","source":{"id":"2310.13486","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13486","created_at":"2026-07-05T07:03:04Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13486v1","created_at":"2026-07-05T07:03:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13486","created_at":"2026-07-05T07:03:04Z"},{"alias_kind":"pith_short_12","alias_value":"B2AVNQO5X6BX","created_at":"2026-07-05T07:03:04Z"},{"alias_kind":"pith_short_16","alias_value":"B2AVNQO5X6BX2QLW","created_at":"2026-07-05T07:03:04Z"},{"alias_kind":"pith_short_8","alias_value":"B2AVNQO5","created_at":"2026-07-05T07:03:04Z"}],"graph_snapshots":[{"event_id":"sha256:d5be4e17119fea5d6b218e2fd6ba963ed5ac6e93b6607dd1c627597ecface537","target":"graph","created_at":"2026-07-05T07:03:04Z","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/2310.13486/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Finding the best way of adapting pre-trained language models to a task is a big challenge in current NLP. Just like the previous generation of task-tuned models (TT), models that are adapted to tasks via in-context-learning (ICL) are robust in some setups but not in others. Here, we present a detailed analysis of which design choices cause instabilities and inconsistencies in LLM predictions. First, we show how spurious correlations between input distributions and labels -- a known issue in TT models -- form only a minor problem for prompted models. Then, we engage in a systematic, holistic ev","authors_text":"Dieuwke Hupkes, Elia Bruni, Lucas Weber","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T13:25:24Z","title":"Mind the instructions: a holistic evaluation of consistency and interactions in prompt-based learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13486","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:fd2cfac0ee3766d82084aa03e84c9ea836e72bbfc763f7618df50ef735d95c2c","target":"record","created_at":"2026-07-05T07:03:04Z","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":"31d912097a70ba972ade922f04ab55350f04cda106f3629b5a114d22413640dc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T13:25:24Z","title_canon_sha256":"45ff96eb0e039c1dd6268ab4e8b5edcd2be9d98837c5678379cb309063b158c6"},"schema_version":"1.0","source":{"id":"2310.13486","kind":"arxiv","version":1}},"canonical_sha256":"0e8156c1ddbf837d41766809a1634981d4f105d5722c549247c7a779ec31263d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e8156c1ddbf837d41766809a1634981d4f105d5722c549247c7a779ec31263d","first_computed_at":"2026-07-05T07:03:04.361469Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:04.361469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iPuLzrxcYmGRzT8HtJU0l8ktEyJX+26JgC6zuRh1iP5e+oo4k/L2bqdum1L3PBu75ajX/DHNlF2a8+twKXD0Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:04.361934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.13486","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd2cfac0ee3766d82084aa03e84c9ea836e72bbfc763f7618df50ef735d95c2c","sha256:d5be4e17119fea5d6b218e2fd6ba963ed5ac6e93b6607dd1c627597ecface537"],"state_sha256":"23c05c225bf1a2d52a2ad70e673d9ebca1c05da3725b8075bfa247e8b0c2149e"}