{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4QDH3RXS6K6BRONFMLW55BADV3","short_pith_number":"pith:4QDH3RXS","canonical_record":{"source":{"id":"2605.16354","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T17:13:08Z","cross_cats_sorted":["cs.AI","cs.CL","cs.HC","stat.ML"],"title_canon_sha256":"4ed472f1e78b563a2eec4e24e660dd71704aae7aa4963c77e6e6262b9f435c4e","abstract_canon_sha256":"efbd1d83cabd374e95f9ae31d7ab76f10646bd1986c75d7647d44b7866274104"},"schema_version":"1.0"},"canonical_sha256":"e4067dc6f2f2bc18b9a562edde8403aed810890997d83da2d1c2eecf562687f2","source":{"kind":"arxiv","id":"2605.16354","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16354","created_at":"2026-05-20T00:02:18Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16354v1","created_at":"2026-05-20T00:02:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16354","created_at":"2026-05-20T00:02:18Z"},{"alias_kind":"pith_short_12","alias_value":"4QDH3RXS6K6B","created_at":"2026-05-20T00:02:18Z"},{"alias_kind":"pith_short_16","alias_value":"4QDH3RXS6K6BRONF","created_at":"2026-05-20T00:02:18Z"},{"alias_kind":"pith_short_8","alias_value":"4QDH3RXS","created_at":"2026-05-20T00:02:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4QDH3RXS6K6BRONFMLW55BADV3","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16354","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T17:13:08Z","cross_cats_sorted":["cs.AI","cs.CL","cs.HC","stat.ML"],"title_canon_sha256":"4ed472f1e78b563a2eec4e24e660dd71704aae7aa4963c77e6e6262b9f435c4e","abstract_canon_sha256":"efbd1d83cabd374e95f9ae31d7ab76f10646bd1986c75d7647d44b7866274104"},"schema_version":"1.0"},"canonical_sha256":"e4067dc6f2f2bc18b9a562edde8403aed810890997d83da2d1c2eecf562687f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:18.036893Z","signature_b64":"8pLEc7ABuVntjwS/TL0dla77AFJ6pcxFAUSngQhYnXBAVKEegFe8E7SXbUleWTt81Emf2ljCUQbBx9x6xR24CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4067dc6f2f2bc18b9a562edde8403aed810890997d83da2d1c2eecf562687f2","last_reissued_at":"2026-05-20T00:02:18.036222Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:18.036222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16354","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":"2026-05-20T00:02:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pu20+TfF3IoH896u4R4TIt1tQJIrzVBgKATc3zT5m87doseTfDxpTQPn82j8Zi5OvcgO2U9QDCHAwq1gJbi2BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T17:26:52.886058Z"},"content_sha256":"8b9a4e9deadadaebb5743bd72bedae52762e6ad7f85753aaaf07611030ab2e00","schema_version":"1.0","event_id":"sha256:8b9a4e9deadadaebb5743bd72bedae52762e6ad7f85753aaaf07611030ab2e00"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4QDH3RXS6K6BRONFMLW55BADV3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Augmenting Human Evaluation with LLM Judges: How Many Human Reviews Do You Need?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jane Paik Kim","submitted_at":"2026-05-08T17:13:08Z","abstract_excerpt":"Large language models (LLMs) are increasingly used as automated evaluators of AI systems, including in high-stakes applications. In this role, LLMs are used to generate judgments about the quality, appropriateness, or even safety of model outputs. This approach is motivated by practical constraints. Expert human ratings are costly and difficult to scale, whereas LLM ratings can be produced quickly at low cost. However, current approaches to deploying LLM evaluators are ad hoc, typically limited to reporting agreement metrics between human and LLM judges as a justification for substitution of h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16354","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/2605.16354/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":"2026-05-20T00:02:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5tunxTlcfX1USsMQfMaXIQ5dcfvSsx5U6FtMS8b8E27qot2NL+TfOHCgKl+NSkJB45EpXPXmbhPc4//vnwCoCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T17:26:52.886832Z"},"content_sha256":"d6fd63438d556ad49de265b5dffaa7985158a811e99d2558e95d2277e52b9329","schema_version":"1.0","event_id":"sha256:d6fd63438d556ad49de265b5dffaa7985158a811e99d2558e95d2277e52b9329"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4QDH3RXS6K6BRONFMLW55BADV3/bundle.json","state_url":"https://pith.science/pith/4QDH3RXS6K6BRONFMLW55BADV3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4QDH3RXS6K6BRONFMLW55BADV3/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":"2026-05-28T17:26:52Z","links":{"resolver":"https://pith.science/pith/4QDH3RXS6K6BRONFMLW55BADV3","bundle":"https://pith.science/pith/4QDH3RXS6K6BRONFMLW55BADV3/bundle.json","state":"https://pith.science/pith/4QDH3RXS6K6BRONFMLW55BADV3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4QDH3RXS6K6BRONFMLW55BADV3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4QDH3RXS6K6BRONFMLW55BADV3","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":"efbd1d83cabd374e95f9ae31d7ab76f10646bd1986c75d7647d44b7866274104","cross_cats_sorted":["cs.AI","cs.CL","cs.HC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T17:13:08Z","title_canon_sha256":"4ed472f1e78b563a2eec4e24e660dd71704aae7aa4963c77e6e6262b9f435c4e"},"schema_version":"1.0","source":{"id":"2605.16354","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16354","created_at":"2026-05-20T00:02:18Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16354v1","created_at":"2026-05-20T00:02:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16354","created_at":"2026-05-20T00:02:18Z"},{"alias_kind":"pith_short_12","alias_value":"4QDH3RXS6K6B","created_at":"2026-05-20T00:02:18Z"},{"alias_kind":"pith_short_16","alias_value":"4QDH3RXS6K6BRONF","created_at":"2026-05-20T00:02:18Z"},{"alias_kind":"pith_short_8","alias_value":"4QDH3RXS","created_at":"2026-05-20T00:02:18Z"}],"graph_snapshots":[{"event_id":"sha256:d6fd63438d556ad49de265b5dffaa7985158a811e99d2558e95d2277e52b9329","target":"graph","created_at":"2026-05-20T00:02:18Z","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/2605.16354/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly used as automated evaluators of AI systems, including in high-stakes applications. In this role, LLMs are used to generate judgments about the quality, appropriateness, or even safety of model outputs. This approach is motivated by practical constraints. Expert human ratings are costly and difficult to scale, whereas LLM ratings can be produced quickly at low cost. However, current approaches to deploying LLM evaluators are ad hoc, typically limited to reporting agreement metrics between human and LLM judges as a justification for substitution of h","authors_text":"Jane Paik Kim","cross_cats":["cs.AI","cs.CL","cs.HC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T17:13:08Z","title":"Augmenting Human Evaluation with LLM Judges: How Many Human Reviews Do You Need?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16354","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":"sha256:8b9a4e9deadadaebb5743bd72bedae52762e6ad7f85753aaaf07611030ab2e00","target":"record","created_at":"2026-05-20T00:02:18Z","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":"efbd1d83cabd374e95f9ae31d7ab76f10646bd1986c75d7647d44b7866274104","cross_cats_sorted":["cs.AI","cs.CL","cs.HC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T17:13:08Z","title_canon_sha256":"4ed472f1e78b563a2eec4e24e660dd71704aae7aa4963c77e6e6262b9f435c4e"},"schema_version":"1.0","source":{"id":"2605.16354","kind":"arxiv","version":1}},"canonical_sha256":"e4067dc6f2f2bc18b9a562edde8403aed810890997d83da2d1c2eecf562687f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4067dc6f2f2bc18b9a562edde8403aed810890997d83da2d1c2eecf562687f2","first_computed_at":"2026-05-20T00:02:18.036222Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:18.036222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8pLEc7ABuVntjwS/TL0dla77AFJ6pcxFAUSngQhYnXBAVKEegFe8E7SXbUleWTt81Emf2ljCUQbBx9x6xR24CA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:18.036893Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16354","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b9a4e9deadadaebb5743bd72bedae52762e6ad7f85753aaaf07611030ab2e00","sha256:d6fd63438d556ad49de265b5dffaa7985158a811e99d2558e95d2277e52b9329"],"state_sha256":"f5752bf24c3485eddb2965677926c9a7d54457c7a95fbb64d9e3d0bfc2a25a29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W2OtM/7whoLLgFLp1VEt/TDu+TVTf0fWBslQdVqV7zLgNM5gAM1caSTHh+moPkXUHQH49RzJbqNyK/bJjaBwDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T17:26:52.890699Z","bundle_sha256":"7349da9a0cf9b0c312060222d75f2052899e0052c9718a58c49af3f6c1724e14"}}