{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5EAJBFY7N3PWI5SJH7CNBA5V3T","short_pith_number":"pith:5EAJBFY7","canonical_record":{"source":{"id":"2606.05308","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T18:01:08Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","stat.AP"],"title_canon_sha256":"88bf6bf819f1cbb8791a553d9d5f3ffd948507fc7c8cb037f30b9485537a45c7","abstract_canon_sha256":"0a8b00d101a248c65a16a705e859ca068ffae775251546208798404c098d674f"},"schema_version":"1.0"},"canonical_sha256":"e90090971f6edf6476493fc4d083b5dcc74bce8002f68e0d1e0c2bd37a2c565a","source":{"kind":"arxiv","id":"2606.05308","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05308","created_at":"2026-06-05T00:13:53Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05308v1","created_at":"2026-06-05T00:13:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05308","created_at":"2026-06-05T00:13:53Z"},{"alias_kind":"pith_short_12","alias_value":"5EAJBFY7N3PW","created_at":"2026-06-05T00:13:53Z"},{"alias_kind":"pith_short_16","alias_value":"5EAJBFY7N3PWI5SJ","created_at":"2026-06-05T00:13:53Z"},{"alias_kind":"pith_short_8","alias_value":"5EAJBFY7","created_at":"2026-06-05T00:13:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5EAJBFY7N3PWI5SJH7CNBA5V3T","target":"record","payload":{"canonical_record":{"source":{"id":"2606.05308","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T18:01:08Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","stat.AP"],"title_canon_sha256":"88bf6bf819f1cbb8791a553d9d5f3ffd948507fc7c8cb037f30b9485537a45c7","abstract_canon_sha256":"0a8b00d101a248c65a16a705e859ca068ffae775251546208798404c098d674f"},"schema_version":"1.0"},"canonical_sha256":"e90090971f6edf6476493fc4d083b5dcc74bce8002f68e0d1e0c2bd37a2c565a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:53.119590Z","signature_b64":"h89Bjf93xbIBiwqEx56YMXohs6itRODm2rTsoRRvDwHFaQAg7dOKelw2X/eEyqAXo5Ha0IbAUM8Zcr4f8SUsCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e90090971f6edf6476493fc4d083b5dcc74bce8002f68e0d1e0c2bd37a2c565a","last_reissued_at":"2026-06-05T00:13:53.118965Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:53.118965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.05308","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":"2026-06-05T00:13:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ecK+yJdURXVr/aRgEnThCZBVMasDX6h74pGdfdgnsdGF3F+ZU41gbClLs5d55w90yifThscmD37tD5ZrmQ0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T22:11:25.612964Z"},"content_sha256":"8e02c6cde85486d40b5cfc3c75beacecc795a8eb750c2ff14e69af79e7ef0e36","schema_version":"1.0","event_id":"sha256:8e02c6cde85486d40b5cfc3c75beacecc795a8eb750c2ff14e69af79e7ef0e36"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5EAJBFY7N3PWI5SJH7CNBA5V3T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Statistically Reliable LLM-Based Ranking Evaluation via Prediction-Powered Inference","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR","stat.AP"],"primary_cat":"cs.LG","authors_text":"Abhishek Divekar","submitted_at":"2026-06-03T18:01:08Z","abstract_excerpt":"With PRECISE, we extended Prediction-Powered Inference to produce bias-corrected estimates of ranking evaluation metrics by combining a small human-labeled set with a large LLM-judged set. PPI is provably unbiased regardless of the LLM judge's error profile. We make it applicable to hierarchical metrics like Precision@K, where annotations are per-document but the metric is per-query, by reducing the output-space computation from O(2^|C|) to O(2^K). On the ESCI benchmark, augmenting 30 human annotations with Claude 3 Sonnet judgments reduces the standard error of Precision@4 estimates from 4.45"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05308","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/2606.05308/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":"2026-06-05T00:13:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SiVwbEFE1BvSQrEkW3yIOwuhspYQEwzvoDfDFOGqV4BWRuME70YlMbf1lu5BxnTnO489DmMPYT9RQ7cSmIraDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T22:11:25.613372Z"},"content_sha256":"b431176c0401bb76da9fc3fb39545c52e30a0989d3c22f3618b7239372f10c7e","schema_version":"1.0","event_id":"sha256:b431176c0401bb76da9fc3fb39545c52e30a0989d3c22f3618b7239372f10c7e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5EAJBFY7N3PWI5SJH7CNBA5V3T/bundle.json","state_url":"https://pith.science/pith/5EAJBFY7N3PWI5SJH7CNBA5V3T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5EAJBFY7N3PWI5SJH7CNBA5V3T/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":"2026-06-30T22:11:25Z","links":{"resolver":"https://pith.science/pith/5EAJBFY7N3PWI5SJH7CNBA5V3T","bundle":"https://pith.science/pith/5EAJBFY7N3PWI5SJH7CNBA5V3T/bundle.json","state":"https://pith.science/pith/5EAJBFY7N3PWI5SJH7CNBA5V3T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5EAJBFY7N3PWI5SJH7CNBA5V3T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5EAJBFY7N3PWI5SJH7CNBA5V3T","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":"0a8b00d101a248c65a16a705e859ca068ffae775251546208798404c098d674f","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","stat.AP"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T18:01:08Z","title_canon_sha256":"88bf6bf819f1cbb8791a553d9d5f3ffd948507fc7c8cb037f30b9485537a45c7"},"schema_version":"1.0","source":{"id":"2606.05308","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05308","created_at":"2026-06-05T00:13:53Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05308v1","created_at":"2026-06-05T00:13:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05308","created_at":"2026-06-05T00:13:53Z"},{"alias_kind":"pith_short_12","alias_value":"5EAJBFY7N3PW","created_at":"2026-06-05T00:13:53Z"},{"alias_kind":"pith_short_16","alias_value":"5EAJBFY7N3PWI5SJ","created_at":"2026-06-05T00:13:53Z"},{"alias_kind":"pith_short_8","alias_value":"5EAJBFY7","created_at":"2026-06-05T00:13:53Z"}],"graph_snapshots":[{"event_id":"sha256:b431176c0401bb76da9fc3fb39545c52e30a0989d3c22f3618b7239372f10c7e","target":"graph","created_at":"2026-06-05T00:13:53Z","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/2606.05308/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With PRECISE, we extended Prediction-Powered Inference to produce bias-corrected estimates of ranking evaluation metrics by combining a small human-labeled set with a large LLM-judged set. PPI is provably unbiased regardless of the LLM judge's error profile. We make it applicable to hierarchical metrics like Precision@K, where annotations are per-document but the metric is per-query, by reducing the output-space computation from O(2^|C|) to O(2^K). On the ESCI benchmark, augmenting 30 human annotations with Claude 3 Sonnet judgments reduces the standard error of Precision@4 estimates from 4.45","authors_text":"Abhishek Divekar","cross_cats":["cs.AI","cs.CL","cs.IR","stat.AP"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T18:01:08Z","title":"Statistically Reliable LLM-Based Ranking Evaluation via Prediction-Powered Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05308","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":"sha256:8e02c6cde85486d40b5cfc3c75beacecc795a8eb750c2ff14e69af79e7ef0e36","target":"record","created_at":"2026-06-05T00:13:53Z","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":"0a8b00d101a248c65a16a705e859ca068ffae775251546208798404c098d674f","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","stat.AP"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T18:01:08Z","title_canon_sha256":"88bf6bf819f1cbb8791a553d9d5f3ffd948507fc7c8cb037f30b9485537a45c7"},"schema_version":"1.0","source":{"id":"2606.05308","kind":"arxiv","version":1}},"canonical_sha256":"e90090971f6edf6476493fc4d083b5dcc74bce8002f68e0d1e0c2bd37a2c565a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e90090971f6edf6476493fc4d083b5dcc74bce8002f68e0d1e0c2bd37a2c565a","first_computed_at":"2026-06-05T00:13:53.118965Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T00:13:53.118965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h89Bjf93xbIBiwqEx56YMXohs6itRODm2rTsoRRvDwHFaQAg7dOKelw2X/eEyqAXo5Ha0IbAUM8Zcr4f8SUsCQ==","signature_status":"signed_v1","signed_at":"2026-06-05T00:13:53.119590Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05308","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e02c6cde85486d40b5cfc3c75beacecc795a8eb750c2ff14e69af79e7ef0e36","sha256:b431176c0401bb76da9fc3fb39545c52e30a0989d3c22f3618b7239372f10c7e"],"state_sha256":"3f95d339aca6fb9d38670944bce1f136b04633db9d7dc2be5684e6a3bd25f1b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VQmT8E9YJaNqGSZyJS89aCPc0Fb/K6jp3aDO/tIO2S3DJwLarZDdFL6OMFoIq6atCdhoKCDEupqFsMa8JmS+BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T22:11:25.615824Z","bundle_sha256":"c464b81a0b5cf4541a74380bb035073d66cbd0fdbfb106ad62b7307c7ba00e28"}}