{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EWBKCBR4V6SMMA3MV2KJCXNSIE","short_pith_number":"pith:EWBKCBR4","canonical_record":{"source":{"id":"2605.20809","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T07:03:42Z","cross_cats_sorted":[],"title_canon_sha256":"75ad86ce7f198d5bbfa6a502a0635b4c4b5463912995d7bdbac160d84c20994a","abstract_canon_sha256":"6758ba27411c0eb1b8eb041afc51378f40636fa11ef36c797561c05a08b8d7f1"},"schema_version":"1.0"},"canonical_sha256":"2582a1063cafa4c6036cae94915db24113776b1281574858826059a1cf39f35a","source":{"kind":"arxiv","id":"2605.20809","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20809","created_at":"2026-05-21T01:04:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20809v1","created_at":"2026-05-21T01:04:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20809","created_at":"2026-05-21T01:04:55Z"},{"alias_kind":"pith_short_12","alias_value":"EWBKCBR4V6SM","created_at":"2026-05-21T01:04:55Z"},{"alias_kind":"pith_short_16","alias_value":"EWBKCBR4V6SMMA3M","created_at":"2026-05-21T01:04:55Z"},{"alias_kind":"pith_short_8","alias_value":"EWBKCBR4","created_at":"2026-05-21T01:04:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EWBKCBR4V6SMMA3MV2KJCXNSIE","target":"record","payload":{"canonical_record":{"source":{"id":"2605.20809","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T07:03:42Z","cross_cats_sorted":[],"title_canon_sha256":"75ad86ce7f198d5bbfa6a502a0635b4c4b5463912995d7bdbac160d84c20994a","abstract_canon_sha256":"6758ba27411c0eb1b8eb041afc51378f40636fa11ef36c797561c05a08b8d7f1"},"schema_version":"1.0"},"canonical_sha256":"2582a1063cafa4c6036cae94915db24113776b1281574858826059a1cf39f35a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:55.644111Z","signature_b64":"XlmKSN4v/GmatGPZqGchgNcm+871v9npqYWbsd7daOBqtAvKmx7alGKWrSdiZXa47/zx1AG513hy3LIMoonLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2582a1063cafa4c6036cae94915db24113776b1281574858826059a1cf39f35a","last_reissued_at":"2026-05-21T01:04:55.643247Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:55.643247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.20809","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":"2026-05-21T01:04:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LPEwmT2hLIegZG1F5ZSYPq1hlQf2JaQsVGiO3YOF0YQITu27C1LpprjgYia6gQPDCsMjHlNhq8ieAUy1903rAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T07:13:53.185935Z"},"content_sha256":"ca563bd4355da4798d4321e998708f379ce53d4f846ee470148fc94bcc32226c","schema_version":"1.0","event_id":"sha256:ca563bd4355da4798d4321e998708f379ce53d4f846ee470148fc94bcc32226c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EWBKCBR4V6SMMA3MV2KJCXNSIE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Refining and Reusing Annotation Guidelines for LLM Annotation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akiko Aizawa, Jin-Dong Kim, Kon Woo Kim","submitted_at":"2026-05-20T07:03:42Z","abstract_excerpt":"While Large Language Models (LLMs) demonstrate remarkable performance on zero-shot annotation tasks, they often struggle with the specialized conventions of gold-standard benchmarks. We propose the systematic reuse and refinement of annotation guidelines as an alignment mechanism, introducing an iterative moderation framework that simulates the early phases of annotation projects. We evaluate three hypotheses: (1) the efficacy of guideline integration, (2) the advantage of reasoning optimized models, and (3) the viability of moderation under minimal supervision. Testing across biomedical NER t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20809","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/2605.20809/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":"2026-05-21T01:04:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x3+Jtshp0saftCqPm+mBaPoAc8iRfXuekjhL6N8f+RMq43yf+gMl3ZvcNBnBoL4PqkMIo8IkYoXvDjr14noUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T07:13:53.186649Z"},"content_sha256":"adc0b82a49c49cd2aafd1ecd8ee1e9ed841c94f0c878d5a904fd8f7beff60c2c","schema_version":"1.0","event_id":"sha256:adc0b82a49c49cd2aafd1ecd8ee1e9ed841c94f0c878d5a904fd8f7beff60c2c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EWBKCBR4V6SMMA3MV2KJCXNSIE/bundle.json","state_url":"https://pith.science/pith/EWBKCBR4V6SMMA3MV2KJCXNSIE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EWBKCBR4V6SMMA3MV2KJCXNSIE/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":"2026-05-24T07:13:53Z","links":{"resolver":"https://pith.science/pith/EWBKCBR4V6SMMA3MV2KJCXNSIE","bundle":"https://pith.science/pith/EWBKCBR4V6SMMA3MV2KJCXNSIE/bundle.json","state":"https://pith.science/pith/EWBKCBR4V6SMMA3MV2KJCXNSIE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EWBKCBR4V6SMMA3MV2KJCXNSIE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EWBKCBR4V6SMMA3MV2KJCXNSIE","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":"6758ba27411c0eb1b8eb041afc51378f40636fa11ef36c797561c05a08b8d7f1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T07:03:42Z","title_canon_sha256":"75ad86ce7f198d5bbfa6a502a0635b4c4b5463912995d7bdbac160d84c20994a"},"schema_version":"1.0","source":{"id":"2605.20809","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20809","created_at":"2026-05-21T01:04:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20809v1","created_at":"2026-05-21T01:04:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20809","created_at":"2026-05-21T01:04:55Z"},{"alias_kind":"pith_short_12","alias_value":"EWBKCBR4V6SM","created_at":"2026-05-21T01:04:55Z"},{"alias_kind":"pith_short_16","alias_value":"EWBKCBR4V6SMMA3M","created_at":"2026-05-21T01:04:55Z"},{"alias_kind":"pith_short_8","alias_value":"EWBKCBR4","created_at":"2026-05-21T01:04:55Z"}],"graph_snapshots":[{"event_id":"sha256:adc0b82a49c49cd2aafd1ecd8ee1e9ed841c94f0c878d5a904fd8f7beff60c2c","target":"graph","created_at":"2026-05-21T01:04:55Z","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/2605.20809/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Large Language Models (LLMs) demonstrate remarkable performance on zero-shot annotation tasks, they often struggle with the specialized conventions of gold-standard benchmarks. We propose the systematic reuse and refinement of annotation guidelines as an alignment mechanism, introducing an iterative moderation framework that simulates the early phases of annotation projects. We evaluate three hypotheses: (1) the efficacy of guideline integration, (2) the advantage of reasoning optimized models, and (3) the viability of moderation under minimal supervision. Testing across biomedical NER t","authors_text":"Akiko Aizawa, Jin-Dong Kim, Kon Woo Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T07:03:42Z","title":"Refining and Reusing Annotation Guidelines for LLM Annotation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20809","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:ca563bd4355da4798d4321e998708f379ce53d4f846ee470148fc94bcc32226c","target":"record","created_at":"2026-05-21T01:04:55Z","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":"6758ba27411c0eb1b8eb041afc51378f40636fa11ef36c797561c05a08b8d7f1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T07:03:42Z","title_canon_sha256":"75ad86ce7f198d5bbfa6a502a0635b4c4b5463912995d7bdbac160d84c20994a"},"schema_version":"1.0","source":{"id":"2605.20809","kind":"arxiv","version":1}},"canonical_sha256":"2582a1063cafa4c6036cae94915db24113776b1281574858826059a1cf39f35a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2582a1063cafa4c6036cae94915db24113776b1281574858826059a1cf39f35a","first_computed_at":"2026-05-21T01:04:55.643247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:55.643247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XlmKSN4v/GmatGPZqGchgNcm+871v9npqYWbsd7daOBqtAvKmx7alGKWrSdiZXa47/zx1AG513hy3LIMoonLCg==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:55.644111Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20809","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca563bd4355da4798d4321e998708f379ce53d4f846ee470148fc94bcc32226c","sha256:adc0b82a49c49cd2aafd1ecd8ee1e9ed841c94f0c878d5a904fd8f7beff60c2c"],"state_sha256":"36964fca7591e7642bb5c6747cff36eff2cf5bf6d24c564fe4fe18bda78f42be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LKY1F04Wc0vzpLLFvNwu6qzjdTCS41Fc0kqNbv27kqWcWm/AcrXiFNCIHIQZVeDRkAcNufALW9jn950bECllBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T07:13:53.190097Z","bundle_sha256":"291102b7dd0173088cabb9067d936d341847faccb3051a2dd44998d7c60f4e31"}}