{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MZR3I62OG5I7ZYJ5QJ63HKPJHJ","short_pith_number":"pith:MZR3I62O","canonical_record":{"source":{"id":"2401.06301","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T00:11:24Z","cross_cats_sorted":[],"title_canon_sha256":"d7e57371882712fe7a05e633abf1fcd9214899df6d12685226b9c54b33d54e20","abstract_canon_sha256":"7572abf1bff1c7ef55a9e3d3c7e0f65d5f538e73822d60c5ba2e564d68b9b498"},"schema_version":"1.0"},"canonical_sha256":"6663b47b4e3751fce13d827db3a9e93a7a641535f3fdd1ee714bcf9eddb3f024","source":{"kind":"arxiv","id":"2401.06301","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06301","created_at":"2026-07-05T07:32:48Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06301v1","created_at":"2026-07-05T07:32:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06301","created_at":"2026-07-05T07:32:48Z"},{"alias_kind":"pith_short_12","alias_value":"MZR3I62OG5I7","created_at":"2026-07-05T07:32:48Z"},{"alias_kind":"pith_short_16","alias_value":"MZR3I62OG5I7ZYJ5","created_at":"2026-07-05T07:32:48Z"},{"alias_kind":"pith_short_8","alias_value":"MZR3I62O","created_at":"2026-07-05T07:32:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MZR3I62OG5I7ZYJ5QJ63HKPJHJ","target":"record","payload":{"canonical_record":{"source":{"id":"2401.06301","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T00:11:24Z","cross_cats_sorted":[],"title_canon_sha256":"d7e57371882712fe7a05e633abf1fcd9214899df6d12685226b9c54b33d54e20","abstract_canon_sha256":"7572abf1bff1c7ef55a9e3d3c7e0f65d5f538e73822d60c5ba2e564d68b9b498"},"schema_version":"1.0"},"canonical_sha256":"6663b47b4e3751fce13d827db3a9e93a7a641535f3fdd1ee714bcf9eddb3f024","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:48.930481Z","signature_b64":"IOanM19QKfB0aQy9uSzxXHZPSeSm04gezYmOgo0iceoYFgAcHZeII609L6IGcd0cSL3+51tc1DFCoYQKEBE5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6663b47b4e3751fce13d827db3a9e93a7a641535f3fdd1ee714bcf9eddb3f024","last_reissued_at":"2026-07-05T07:32:48.930046Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:48.930046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.06301","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":"2026-07-05T07:32:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MnMNho4Bwqb5bdy1o0Ovc5H6Gnh87+4ivVxaiJtatJhjQfOmZRUJk9wi4RhA+pjEk1gPbV/Ap5zNoLXFwi4GCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:16:35.246236Z"},"content_sha256":"5fe160fc8614a5b43914435d5301e3e7fdc0ccee67a5052f170810ee0d705416","schema_version":"1.0","event_id":"sha256:5fe160fc8614a5b43914435d5301e3e7fdc0ccee67a5052f170810ee0d705416"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MZR3I62OG5I7ZYJ5QJ63HKPJHJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Misconfidence-based Demonstration Selection for LLM In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao Zhang (Georgia Institute of Technology), Shangqing Xu","submitted_at":"2024-01-12T00:11:24Z","abstract_excerpt":"In-context learning with large language models (LLMs) excels at adapting to various tasks rapidly. However, its success hinges on carefully selecting demonstrations, which remains an obstacle in practice. Current approaches to this problem either rely on hard-to-acquire external supervision or require frequent interactions with LLMs, resulting in high costs. We propose a new method called In-Context Reflection (ICR) to overcome these challenges. ICR strategically selects demonstrations to reduce the discrepancy between the LLM's outputs and the actual input-output mappings. Specifically, ICR s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06301","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/2401.06301/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":"2026-07-05T07:32:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wQNieQXjmtA2cn8d8hVCEH/S4Qt274Xlgytv2Vj2nO9yh1JXLmhjHEsqU3+fY+LYpxfG1FkyaoHxkudW9krOCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:16:35.246754Z"},"content_sha256":"37d432a9066e1effe3f8aeb18d9b30f36187b39729512b752cd7ef6c06affff5","schema_version":"1.0","event_id":"sha256:37d432a9066e1effe3f8aeb18d9b30f36187b39729512b752cd7ef6c06affff5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MZR3I62OG5I7ZYJ5QJ63HKPJHJ/bundle.json","state_url":"https://pith.science/pith/MZR3I62OG5I7ZYJ5QJ63HKPJHJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MZR3I62OG5I7ZYJ5QJ63HKPJHJ/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":"2026-08-09T07:16:35Z","links":{"resolver":"https://pith.science/pith/MZR3I62OG5I7ZYJ5QJ63HKPJHJ","bundle":"https://pith.science/pith/MZR3I62OG5I7ZYJ5QJ63HKPJHJ/bundle.json","state":"https://pith.science/pith/MZR3I62OG5I7ZYJ5QJ63HKPJHJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MZR3I62OG5I7ZYJ5QJ63HKPJHJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MZR3I62OG5I7ZYJ5QJ63HKPJHJ","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":"7572abf1bff1c7ef55a9e3d3c7e0f65d5f538e73822d60c5ba2e564d68b9b498","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T00:11:24Z","title_canon_sha256":"d7e57371882712fe7a05e633abf1fcd9214899df6d12685226b9c54b33d54e20"},"schema_version":"1.0","source":{"id":"2401.06301","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06301","created_at":"2026-07-05T07:32:48Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06301v1","created_at":"2026-07-05T07:32:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06301","created_at":"2026-07-05T07:32:48Z"},{"alias_kind":"pith_short_12","alias_value":"MZR3I62OG5I7","created_at":"2026-07-05T07:32:48Z"},{"alias_kind":"pith_short_16","alias_value":"MZR3I62OG5I7ZYJ5","created_at":"2026-07-05T07:32:48Z"},{"alias_kind":"pith_short_8","alias_value":"MZR3I62O","created_at":"2026-07-05T07:32:48Z"}],"graph_snapshots":[{"event_id":"sha256:37d432a9066e1effe3f8aeb18d9b30f36187b39729512b752cd7ef6c06affff5","target":"graph","created_at":"2026-07-05T07:32:48Z","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/2401.06301/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In-context learning with large language models (LLMs) excels at adapting to various tasks rapidly. However, its success hinges on carefully selecting demonstrations, which remains an obstacle in practice. Current approaches to this problem either rely on hard-to-acquire external supervision or require frequent interactions with LLMs, resulting in high costs. We propose a new method called In-Context Reflection (ICR) to overcome these challenges. ICR strategically selects demonstrations to reduce the discrepancy between the LLM's outputs and the actual input-output mappings. Specifically, ICR s","authors_text":"Chao Zhang (Georgia Institute of Technology), Shangqing Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T00:11:24Z","title":"Misconfidence-based Demonstration Selection for LLM In-Context Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06301","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":"sha256:5fe160fc8614a5b43914435d5301e3e7fdc0ccee67a5052f170810ee0d705416","target":"record","created_at":"2026-07-05T07:32:48Z","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":"7572abf1bff1c7ef55a9e3d3c7e0f65d5f538e73822d60c5ba2e564d68b9b498","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T00:11:24Z","title_canon_sha256":"d7e57371882712fe7a05e633abf1fcd9214899df6d12685226b9c54b33d54e20"},"schema_version":"1.0","source":{"id":"2401.06301","kind":"arxiv","version":1}},"canonical_sha256":"6663b47b4e3751fce13d827db3a9e93a7a641535f3fdd1ee714bcf9eddb3f024","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6663b47b4e3751fce13d827db3a9e93a7a641535f3fdd1ee714bcf9eddb3f024","first_computed_at":"2026-07-05T07:32:48.930046Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:32:48.930046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IOanM19QKfB0aQy9uSzxXHZPSeSm04gezYmOgo0iceoYFgAcHZeII609L6IGcd0cSL3+51tc1DFCoYQKEBE5Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T07:32:48.930481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.06301","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fe160fc8614a5b43914435d5301e3e7fdc0ccee67a5052f170810ee0d705416","sha256:37d432a9066e1effe3f8aeb18d9b30f36187b39729512b752cd7ef6c06affff5"],"state_sha256":"082486738d29fc63985291249ce1428dd1af783fc121c70d818d87cf0c05d28e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2DCVhIBGwL+dqYK8KDaCArxO6DBHzojINcTTVxwyJCkv5UnEoTQONt8duSmVYE4hiCqxjwHpGDxXT6YYCBvOBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:16:35.251219Z","bundle_sha256":"7f10643bf6904120ce778062177a9490d215d19d371e2cf381a1cbbca2bdbefc"}}