{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2M2UANFWVQEDUEIVYNX5K4L7D3","short_pith_number":"pith:2M2UANFW","canonical_record":{"source":{"id":"2503.16022","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-20T10:39:39Z","cross_cats_sorted":[],"title_canon_sha256":"55f98dc87ca44b600e996f4121df6e8ff3f89943fd343224fddcb1cdb3c14824","abstract_canon_sha256":"c457703ff4beadbc2370abe84e05c1255c4cece8c2c1f35db7c53c988267ef16"},"schema_version":"1.0"},"canonical_sha256":"d3354034b6ac083a1115c36fd5717f1ee5fe9a9b8e4520e33e6bad4295e785d5","source":{"kind":"arxiv","id":"2503.16022","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.16022","created_at":"2026-07-05T10:36:04Z"},{"alias_kind":"arxiv_version","alias_value":"2503.16022v1","created_at":"2026-07-05T10:36:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16022","created_at":"2026-07-05T10:36:04Z"},{"alias_kind":"pith_short_12","alias_value":"2M2UANFWVQED","created_at":"2026-07-05T10:36:04Z"},{"alias_kind":"pith_short_16","alias_value":"2M2UANFWVQEDUEIV","created_at":"2026-07-05T10:36:04Z"},{"alias_kind":"pith_short_8","alias_value":"2M2UANFW","created_at":"2026-07-05T10:36:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2M2UANFWVQEDUEIVYNX5K4L7D3","target":"record","payload":{"canonical_record":{"source":{"id":"2503.16022","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-20T10:39:39Z","cross_cats_sorted":[],"title_canon_sha256":"55f98dc87ca44b600e996f4121df6e8ff3f89943fd343224fddcb1cdb3c14824","abstract_canon_sha256":"c457703ff4beadbc2370abe84e05c1255c4cece8c2c1f35db7c53c988267ef16"},"schema_version":"1.0"},"canonical_sha256":"d3354034b6ac083a1115c36fd5717f1ee5fe9a9b8e4520e33e6bad4295e785d5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:04.365074Z","signature_b64":"Kx74EqiG+Be4wkZua647DMWAN6F08QBaREA9GUZ0jz0dMQ4v5SUGZvJFq6Nzk1KjiAE/rhhMLBMD29xRdsJ1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3354034b6ac083a1115c36fd5717f1ee5fe9a9b8e4520e33e6bad4295e785d5","last_reissued_at":"2026-07-05T10:36:04.364466Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:04.364466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.16022","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:36:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Krc22YIrBMXijdfKvLeODZeCPb1Rxm5fCjgq3g8vQw873Be82WKawihlMohCS2Z5J7nKAJsfkiOz9bdv2wa/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T02:25:12.860391Z"},"content_sha256":"ef70b5a7e9ebdc02acfbf281a166d5331e8e5313563e8dca84006138c156e497","schema_version":"1.0","event_id":"sha256:ef70b5a7e9ebdc02acfbf281a166d5331e8e5313563e8dca84006138c156e497"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2M2UANFWVQEDUEIVYNX5K4L7D3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Corrective In-Context Learning: Evaluating Self-Correction in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Katharina von der Wense, Mario Sanz-Guerrero","submitted_at":"2025-03-20T10:39:39Z","abstract_excerpt":"In-context learning (ICL) has transformed the use of large language models (LLMs) for NLP tasks, enabling few-shot learning by conditioning on labeled examples without finetuning. Despite its effectiveness, ICL is prone to errors, especially for challenging examples. With the goal of improving the performance of ICL, we propose corrective in-context learning (CICL), an approach that incorporates a model's incorrect predictions alongside ground truth corrections into the prompt, aiming to enhance classification accuracy through self-correction. However, contrary to our hypothesis, extensive exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16022","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/2503.16022/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:36:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IK2avPpiEsH49+GKjxuoeXqXV/5XPGxlyPNciunRVTMD2F6ocRPnJ/PtmL3tRsF9B83yj9qvbH2vRQAgeUpnDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T02:25:12.860893Z"},"content_sha256":"cdc16868763925345f80bc96d957e84916fae9fdd57fb1b1b347ab23b60df496","schema_version":"1.0","event_id":"sha256:cdc16868763925345f80bc96d957e84916fae9fdd57fb1b1b347ab23b60df496"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2M2UANFWVQEDUEIVYNX5K4L7D3/bundle.json","state_url":"https://pith.science/pith/2M2UANFWVQEDUEIVYNX5K4L7D3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2M2UANFWVQEDUEIVYNX5K4L7D3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-01T02:25:12Z","links":{"resolver":"https://pith.science/pith/2M2UANFWVQEDUEIVYNX5K4L7D3","bundle":"https://pith.science/pith/2M2UANFWVQEDUEIVYNX5K4L7D3/bundle.json","state":"https://pith.science/pith/2M2UANFWVQEDUEIVYNX5K4L7D3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2M2UANFWVQEDUEIVYNX5K4L7D3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2M2UANFWVQEDUEIVYNX5K4L7D3","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":"c457703ff4beadbc2370abe84e05c1255c4cece8c2c1f35db7c53c988267ef16","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-20T10:39:39Z","title_canon_sha256":"55f98dc87ca44b600e996f4121df6e8ff3f89943fd343224fddcb1cdb3c14824"},"schema_version":"1.0","source":{"id":"2503.16022","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.16022","created_at":"2026-07-05T10:36:04Z"},{"alias_kind":"arxiv_version","alias_value":"2503.16022v1","created_at":"2026-07-05T10:36:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16022","created_at":"2026-07-05T10:36:04Z"},{"alias_kind":"pith_short_12","alias_value":"2M2UANFWVQED","created_at":"2026-07-05T10:36:04Z"},{"alias_kind":"pith_short_16","alias_value":"2M2UANFWVQEDUEIV","created_at":"2026-07-05T10:36:04Z"},{"alias_kind":"pith_short_8","alias_value":"2M2UANFW","created_at":"2026-07-05T10:36:04Z"}],"graph_snapshots":[{"event_id":"sha256:cdc16868763925345f80bc96d957e84916fae9fdd57fb1b1b347ab23b60df496","target":"graph","created_at":"2026-07-05T10:36:04Z","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/2503.16022/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In-context learning (ICL) has transformed the use of large language models (LLMs) for NLP tasks, enabling few-shot learning by conditioning on labeled examples without finetuning. Despite its effectiveness, ICL is prone to errors, especially for challenging examples. With the goal of improving the performance of ICL, we propose corrective in-context learning (CICL), an approach that incorporates a model's incorrect predictions alongside ground truth corrections into the prompt, aiming to enhance classification accuracy through self-correction. However, contrary to our hypothesis, extensive exp","authors_text":"Katharina von der Wense, Mario Sanz-Guerrero","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-20T10:39:39Z","title":"Corrective In-Context Learning: Evaluating Self-Correction in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16022","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:ef70b5a7e9ebdc02acfbf281a166d5331e8e5313563e8dca84006138c156e497","target":"record","created_at":"2026-07-05T10:36:04Z","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":"c457703ff4beadbc2370abe84e05c1255c4cece8c2c1f35db7c53c988267ef16","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-20T10:39:39Z","title_canon_sha256":"55f98dc87ca44b600e996f4121df6e8ff3f89943fd343224fddcb1cdb3c14824"},"schema_version":"1.0","source":{"id":"2503.16022","kind":"arxiv","version":1}},"canonical_sha256":"d3354034b6ac083a1115c36fd5717f1ee5fe9a9b8e4520e33e6bad4295e785d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3354034b6ac083a1115c36fd5717f1ee5fe9a9b8e4520e33e6bad4295e785d5","first_computed_at":"2026-07-05T10:36:04.364466Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:36:04.364466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kx74EqiG+Be4wkZua647DMWAN6F08QBaREA9GUZ0jz0dMQ4v5SUGZvJFq6Nzk1KjiAE/rhhMLBMD29xRdsJ1CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:36:04.365074Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.16022","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef70b5a7e9ebdc02acfbf281a166d5331e8e5313563e8dca84006138c156e497","sha256:cdc16868763925345f80bc96d957e84916fae9fdd57fb1b1b347ab23b60df496"],"state_sha256":"762b05ee430533163134900766e0b1f4c6704b7c6043078d1cb7194a14b0be3f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lbqXbBPfHpKpbszTutb9Mk+bkecyiE/rtDWfYiH0/Xijn+XANjwMfCVe1MkGBDASlM3I6EQXwJXR6zF0iC6FAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T02:25:12.866478Z","bundle_sha256":"a1e01bdb0f73527380277a9ac0624912c05c185f0e946a007f19f01f18405743"}}