{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OAGLHKDUFXMGZ7VBTYWIWPLCC2","short_pith_number":"pith:OAGLHKDU","canonical_record":{"source":{"id":"2309.17249","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-29T13:55:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5e47b33454ea7e18cde7cbf551fea0598271e4c06e0459a7087e2bc5492e232e","abstract_canon_sha256":"1c4896e03af62860e361da42db574b6209350ccc22a23ec618cd4f9674f1a2ab"},"schema_version":"1.0"},"canonical_sha256":"700cb3a8742dd86cfea19e2c8b3d62169c956c5aeb9ea08bfdbc993d02a28004","source":{"kind":"arxiv","id":"2309.17249","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.17249","created_at":"2026-07-05T09:42:20Z"},{"alias_kind":"arxiv_version","alias_value":"2309.17249v3","created_at":"2026-07-05T09:42:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17249","created_at":"2026-07-05T09:42:20Z"},{"alias_kind":"pith_short_12","alias_value":"OAGLHKDUFXMG","created_at":"2026-07-05T09:42:20Z"},{"alias_kind":"pith_short_16","alias_value":"OAGLHKDUFXMGZ7VB","created_at":"2026-07-05T09:42:20Z"},{"alias_kind":"pith_short_8","alias_value":"OAGLHKDU","created_at":"2026-07-05T09:42:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OAGLHKDUFXMGZ7VBTYWIWPLCC2","target":"record","payload":{"canonical_record":{"source":{"id":"2309.17249","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-29T13:55:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5e47b33454ea7e18cde7cbf551fea0598271e4c06e0459a7087e2bc5492e232e","abstract_canon_sha256":"1c4896e03af62860e361da42db574b6209350ccc22a23ec618cd4f9674f1a2ab"},"schema_version":"1.0"},"canonical_sha256":"700cb3a8742dd86cfea19e2c8b3d62169c956c5aeb9ea08bfdbc993d02a28004","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:20.197649Z","signature_b64":"YpbkS2fFuk3e12XzzaJDziMoMf7ObRPr//PRD0C4nmNNHavNPvslVdQmBjUJ3aH4thoHcO1ccOpBFr602/SzDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"700cb3a8742dd86cfea19e2c8b3d62169c956c5aeb9ea08bfdbc993d02a28004","last_reissued_at":"2026-07-05T09:42:20.197128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:20.197128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.17249","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:42:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bY9uotPeQXYDfu+MKD6UBRBSit/ZjBkRZWSciBmxW5/JyiaCo7VWMabYwccHsMssMNeRB6psMlSgbxswR+wIDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:05:11.100111Z"},"content_sha256":"49ab4fbfbb3e25db53a1d8619a70db290c1c6a07c4a2fdf3f401d4ca145675fe","schema_version":"1.0","event_id":"sha256:49ab4fbfbb3e25db53a1d8619a70db290c1c6a07c4a2fdf3f401d4ca145675fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OAGLHKDUFXMGZ7VBTYWIWPLCC2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Diana Mincu, Han Zhou, Jilin Chen, Katherine Heller, Lev Proleev, Subhrajit Roy, Xingchen Wan","submitted_at":"2023-09-29T13:55:45Z","abstract_excerpt":"Prompting and in-context learning (ICL) have become efficient learning paradigms for large language models (LLMs). However, LLMs suffer from prompt brittleness and various bias factors in the prompt, including but not limited to the formatting, the choice verbalizers, and the ICL examples. To address this problem that results in unexpected performance degradation, calibration methods have been developed to mitigate the effects of these biases while recovering LLM performance. In this work, we first conduct a systematic analysis of the existing calibration methods, where we both provide a unifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.17249","kind":"arxiv","version":3},"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/2309.17249/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":"2026-07-05T09:42:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1dhdI7pEBACkPBPASwK5iEXt6puKqfNtMG/syuEVV/bOSbDGtRGB/tijC62iKH7gn2zuv43OHqYaJ59CcK7ICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:05:11.100649Z"},"content_sha256":"79484bdc95543eff6a6c368df84ee1f348eade9af77da6ba6023142da2c92b32","schema_version":"1.0","event_id":"sha256:79484bdc95543eff6a6c368df84ee1f348eade9af77da6ba6023142da2c92b32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OAGLHKDUFXMGZ7VBTYWIWPLCC2/bundle.json","state_url":"https://pith.science/pith/OAGLHKDUFXMGZ7VBTYWIWPLCC2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OAGLHKDUFXMGZ7VBTYWIWPLCC2/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":"2026-08-08T04:05:11Z","links":{"resolver":"https://pith.science/pith/OAGLHKDUFXMGZ7VBTYWIWPLCC2","bundle":"https://pith.science/pith/OAGLHKDUFXMGZ7VBTYWIWPLCC2/bundle.json","state":"https://pith.science/pith/OAGLHKDUFXMGZ7VBTYWIWPLCC2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OAGLHKDUFXMGZ7VBTYWIWPLCC2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OAGLHKDUFXMGZ7VBTYWIWPLCC2","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":"1c4896e03af62860e361da42db574b6209350ccc22a23ec618cd4f9674f1a2ab","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-29T13:55:45Z","title_canon_sha256":"5e47b33454ea7e18cde7cbf551fea0598271e4c06e0459a7087e2bc5492e232e"},"schema_version":"1.0","source":{"id":"2309.17249","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.17249","created_at":"2026-07-05T09:42:20Z"},{"alias_kind":"arxiv_version","alias_value":"2309.17249v3","created_at":"2026-07-05T09:42:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17249","created_at":"2026-07-05T09:42:20Z"},{"alias_kind":"pith_short_12","alias_value":"OAGLHKDUFXMG","created_at":"2026-07-05T09:42:20Z"},{"alias_kind":"pith_short_16","alias_value":"OAGLHKDUFXMGZ7VB","created_at":"2026-07-05T09:42:20Z"},{"alias_kind":"pith_short_8","alias_value":"OAGLHKDU","created_at":"2026-07-05T09:42:20Z"}],"graph_snapshots":[{"event_id":"sha256:79484bdc95543eff6a6c368df84ee1f348eade9af77da6ba6023142da2c92b32","target":"graph","created_at":"2026-07-05T09:42:20Z","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/2309.17249/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompting and in-context learning (ICL) have become efficient learning paradigms for large language models (LLMs). However, LLMs suffer from prompt brittleness and various bias factors in the prompt, including but not limited to the formatting, the choice verbalizers, and the ICL examples. To address this problem that results in unexpected performance degradation, calibration methods have been developed to mitigate the effects of these biases while recovering LLM performance. In this work, we first conduct a systematic analysis of the existing calibration methods, where we both provide a unifi","authors_text":"Diana Mincu, Han Zhou, Jilin Chen, Katherine Heller, Lev Proleev, Subhrajit Roy, Xingchen Wan","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-29T13:55:45Z","title":"Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.17249","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":"sha256:49ab4fbfbb3e25db53a1d8619a70db290c1c6a07c4a2fdf3f401d4ca145675fe","target":"record","created_at":"2026-07-05T09:42:20Z","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":"1c4896e03af62860e361da42db574b6209350ccc22a23ec618cd4f9674f1a2ab","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-29T13:55:45Z","title_canon_sha256":"5e47b33454ea7e18cde7cbf551fea0598271e4c06e0459a7087e2bc5492e232e"},"schema_version":"1.0","source":{"id":"2309.17249","kind":"arxiv","version":3}},"canonical_sha256":"700cb3a8742dd86cfea19e2c8b3d62169c956c5aeb9ea08bfdbc993d02a28004","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"700cb3a8742dd86cfea19e2c8b3d62169c956c5aeb9ea08bfdbc993d02a28004","first_computed_at":"2026-07-05T09:42:20.197128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:20.197128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YpbkS2fFuk3e12XzzaJDziMoMf7ObRPr//PRD0C4nmNNHavNPvslVdQmBjUJ3aH4thoHcO1ccOpBFr602/SzDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:20.197649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.17249","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49ab4fbfbb3e25db53a1d8619a70db290c1c6a07c4a2fdf3f401d4ca145675fe","sha256:79484bdc95543eff6a6c368df84ee1f348eade9af77da6ba6023142da2c92b32"],"state_sha256":"4dbe1392fe2aec0e1bbdbbf95adfe7f16bdda1a67c7c15d5edd8166e855398e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3RvPU4kypDjiH/Iqk2mkzLc2WRl/NnX0dNJsjncyk1GM2gnayO9cUt48uo+y1XG7EIQkJulzshRp3hRANouDCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:05:11.106480Z","bundle_sha256":"a80f98624229e3c0f3e6fe59fb3f0aedf2babedce7e2234cb7ef65417d79078c"}}