{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JJEZSPBZMHOFENTYXJ73W2X6HP","short_pith_number":"pith:JJEZSPBZ","canonical_record":{"source":{"id":"2502.14855","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-20T18:58:07Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"afb313a8b3bdf4091fe7b76dd9e42958c60704dff947817a1068ec72b2557e27","abstract_canon_sha256":"8db5ed68a50c0b1bb63358c9efb947eac840e2951aa9cf19d54bea470a342550"},"schema_version":"1.0"},"canonical_sha256":"4a49993c3961dc523678ba7fbb6afe3bfb3c35c6ecd933d013f729e29ea7908d","source":{"kind":"arxiv","id":"2502.14855","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14855","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14855v2","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14855","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"pith_short_12","alias_value":"JJEZSPBZMHOF","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"pith_short_16","alias_value":"JJEZSPBZMHOFENTY","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"pith_short_8","alias_value":"JJEZSPBZ","created_at":"2026-07-05T10:27:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JJEZSPBZMHOFENTYXJ73W2X6HP","target":"record","payload":{"canonical_record":{"source":{"id":"2502.14855","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-20T18:58:07Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"afb313a8b3bdf4091fe7b76dd9e42958c60704dff947817a1068ec72b2557e27","abstract_canon_sha256":"8db5ed68a50c0b1bb63358c9efb947eac840e2951aa9cf19d54bea470a342550"},"schema_version":"1.0"},"canonical_sha256":"4a49993c3961dc523678ba7fbb6afe3bfb3c35c6ecd933d013f729e29ea7908d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:25.857514Z","signature_b64":"gxTJciNfNt/L1Twft6kQC8SI9eMNuhthbjnv5KuXpOYIEtDnvknDFVQn14X6d2IQ5VYSGqW97+y+P92+Tr0ABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a49993c3961dc523678ba7fbb6afe3bfb3c35c6ecd933d013f729e29ea7908d","last_reissued_at":"2026-07-05T10:27:25.857007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:25.857007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.14855","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:27:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1pAgrMwq9zzE+31DNLOGceMnCz5A5A54j8V8V51fSvfGCUQBEXiBtRMIPsn5KLSXSv6M3r9GoPj4jwzlWSyYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:34:18.815240Z"},"content_sha256":"6e8cc5f4bd0a5c3287525f959d900c4dea8ae36630cfaf892737c0a133701844","schema_version":"1.0","event_id":"sha256:6e8cc5f4bd0a5c3287525f959d900c4dea8ae36630cfaf892737c0a133701844"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JJEZSPBZMHOFENTYXJ73W2X6HP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prompt-to-Leaderboard","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Anastasios N. Angelopoulos, Connor Chen, Evan Frick, Ion Stoica, Joseph Tennyson, Tianle Li, Wei-Lin Chiang","submitted_at":"2025-02-20T18:58:07Z","abstract_excerpt":"Large language model (LLM) evaluations typically rely on aggregated metrics like accuracy or human preference, averaging across users and prompts. This averaging obscures user- and prompt-specific variations in model performance. To address this, we propose Prompt-to-Leaderboard (P2L), a method that produces leaderboards specific to a prompt. The core idea is to train an LLM taking natural language prompts as input to output a vector of Bradley-Terry coefficients which are then used to predict the human preference vote. The resulting prompt-dependent leaderboards allow for unsupervised task-sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14855","kind":"arxiv","version":2},"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/2502.14855/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":"2026-07-05T10:27:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hT7n0plX32506AwwsulmeZWGVoFovyDTTWAo+ZC7GFBGZk7ifP7aYFoC4D+vecQvZWizpZxaLabbbm/xb2G5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:34:18.815738Z"},"content_sha256":"4f5c792aaef76ef93eed161de47519af30066883b9ff0d3f2688441f5309d29c","schema_version":"1.0","event_id":"sha256:4f5c792aaef76ef93eed161de47519af30066883b9ff0d3f2688441f5309d29c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JJEZSPBZMHOFENTYXJ73W2X6HP/bundle.json","state_url":"https://pith.science/pith/JJEZSPBZMHOFENTYXJ73W2X6HP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JJEZSPBZMHOFENTYXJ73W2X6HP/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":"2026-08-05T08:34:18Z","links":{"resolver":"https://pith.science/pith/JJEZSPBZMHOFENTYXJ73W2X6HP","bundle":"https://pith.science/pith/JJEZSPBZMHOFENTYXJ73W2X6HP/bundle.json","state":"https://pith.science/pith/JJEZSPBZMHOFENTYXJ73W2X6HP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JJEZSPBZMHOFENTYXJ73W2X6HP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JJEZSPBZMHOFENTYXJ73W2X6HP","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":"8db5ed68a50c0b1bb63358c9efb947eac840e2951aa9cf19d54bea470a342550","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-20T18:58:07Z","title_canon_sha256":"afb313a8b3bdf4091fe7b76dd9e42958c60704dff947817a1068ec72b2557e27"},"schema_version":"1.0","source":{"id":"2502.14855","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14855","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14855v2","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14855","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"pith_short_12","alias_value":"JJEZSPBZMHOF","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"pith_short_16","alias_value":"JJEZSPBZMHOFENTY","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"pith_short_8","alias_value":"JJEZSPBZ","created_at":"2026-07-05T10:27:25Z"}],"graph_snapshots":[{"event_id":"sha256:4f5c792aaef76ef93eed161de47519af30066883b9ff0d3f2688441f5309d29c","target":"graph","created_at":"2026-07-05T10:27:25Z","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/2502.14855/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM) evaluations typically rely on aggregated metrics like accuracy or human preference, averaging across users and prompts. This averaging obscures user- and prompt-specific variations in model performance. To address this, we propose Prompt-to-Leaderboard (P2L), a method that produces leaderboards specific to a prompt. The core idea is to train an LLM taking natural language prompts as input to output a vector of Bradley-Terry coefficients which are then used to predict the human preference vote. The resulting prompt-dependent leaderboards allow for unsupervised task-sp","authors_text":"Anastasios N. Angelopoulos, Connor Chen, Evan Frick, Ion Stoica, Joseph Tennyson, Tianle Li, Wei-Lin Chiang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-20T18:58:07Z","title":"Prompt-to-Leaderboard"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14855","kind":"arxiv","version":2},"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":"sha256:6e8cc5f4bd0a5c3287525f959d900c4dea8ae36630cfaf892737c0a133701844","target":"record","created_at":"2026-07-05T10:27:25Z","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":"8db5ed68a50c0b1bb63358c9efb947eac840e2951aa9cf19d54bea470a342550","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-20T18:58:07Z","title_canon_sha256":"afb313a8b3bdf4091fe7b76dd9e42958c60704dff947817a1068ec72b2557e27"},"schema_version":"1.0","source":{"id":"2502.14855","kind":"arxiv","version":2}},"canonical_sha256":"4a49993c3961dc523678ba7fbb6afe3bfb3c35c6ecd933d013f729e29ea7908d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a49993c3961dc523678ba7fbb6afe3bfb3c35c6ecd933d013f729e29ea7908d","first_computed_at":"2026-07-05T10:27:25.857007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:25.857007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gxTJciNfNt/L1Twft6kQC8SI9eMNuhthbjnv5KuXpOYIEtDnvknDFVQn14X6d2IQ5VYSGqW97+y+P92+Tr0ABA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:25.857514Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14855","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e8cc5f4bd0a5c3287525f959d900c4dea8ae36630cfaf892737c0a133701844","sha256:4f5c792aaef76ef93eed161de47519af30066883b9ff0d3f2688441f5309d29c"],"state_sha256":"10ed91bc1d636cd12666da830a5a1071ec0517c61a3611c701028740e3e35255"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KAeDeDWXw9cXVvmKs1YS2s54e/aDNpFXBvlPbunLic3uO9uoqR9zsAgEfMo1l2SP/Z6x6rZdUxvhtiIcxMWDDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:34:18.821452Z","bundle_sha256":"e9aea5a38d5cb327c6d4c9fa12dcb6aef52b84b651447d85715d59d9bb2e39f9"}}