{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SKFHYOF3YVWXU4OIEMVP4FXY46","short_pith_number":"pith:SKFHYOF3","canonical_record":{"source":{"id":"2504.11381","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-15T16:53:31Z","cross_cats_sorted":[],"title_canon_sha256":"3af2aac69d9ab91126637a7065af0b21e07d0f50896f054285c21b531d50ce74","abstract_canon_sha256":"59caf28f72dd293f1219e77ef366d0ca121b4d67f29e974df430ed1980b2a380"},"schema_version":"1.0"},"canonical_sha256":"928a7c38bbc56d7a71c8232afe16f8e7b7a17cca81db804eedcbe0776da1e26c","source":{"kind":"arxiv","id":"2504.11381","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.11381","created_at":"2026-07-05T12:03:26Z"},{"alias_kind":"arxiv_version","alias_value":"2504.11381v2","created_at":"2026-07-05T12:03:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11381","created_at":"2026-07-05T12:03:26Z"},{"alias_kind":"pith_short_12","alias_value":"SKFHYOF3YVWX","created_at":"2026-07-05T12:03:26Z"},{"alias_kind":"pith_short_16","alias_value":"SKFHYOF3YVWXU4OI","created_at":"2026-07-05T12:03:26Z"},{"alias_kind":"pith_short_8","alias_value":"SKFHYOF3","created_at":"2026-07-05T12:03:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SKFHYOF3YVWXU4OIEMVP4FXY46","target":"record","payload":{"canonical_record":{"source":{"id":"2504.11381","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-15T16:53:31Z","cross_cats_sorted":[],"title_canon_sha256":"3af2aac69d9ab91126637a7065af0b21e07d0f50896f054285c21b531d50ce74","abstract_canon_sha256":"59caf28f72dd293f1219e77ef366d0ca121b4d67f29e974df430ed1980b2a380"},"schema_version":"1.0"},"canonical_sha256":"928a7c38bbc56d7a71c8232afe16f8e7b7a17cca81db804eedcbe0776da1e26c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:26.202077Z","signature_b64":"r8YvG2kSFVdKvUMpEbOmUU76UCIk/NJQ3GwtcEhgZOvxBFEiGfm3mNEUPQ6s8dJm9vcAXWje7M5V6JWvMdrGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"928a7c38bbc56d7a71c8232afe16f8e7b7a17cca81db804eedcbe0776da1e26c","last_reissued_at":"2026-07-05T12:03:26.201564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:26.201564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.11381","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":"2026-07-05T12:03:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+UqmKUTa+yN0a+EbL9vcW39kN0HFQyrYfMtP5b5gkx1AKqmcdpa5qqgoVxzWikkB0kFnf99ItoEVXt8x5ybcCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:04:54.141431Z"},"content_sha256":"1c4f26b66dfb00603d24505fb3ebf6f2811ddc0d6a12b0a4689b8d0433f1fada","schema_version":"1.0","event_id":"sha256:1c4f26b66dfb00603d24505fb3ebf6f2811ddc0d6a12b0a4689b8d0433f1fada"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SKFHYOF3YVWXU4OIEMVP4FXY46","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RankAlign: A Ranking View of the Generator-Validator Gap in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Greg Durrett, Juan Diego Rodriguez, Katrin Erk, Wenxuan Ding","submitted_at":"2025-04-15T16:53:31Z","abstract_excerpt":"Although large language models (LLMs) have become more capable and accurate across many tasks, some fundamental sources of unreliability remain in their behavior. One key limitation is their inconsistency at reporting the same information when prompts are changed. In this paper, we consider the discrepancy between a model's generated answer and their own verification of that answer, the generator-validator gap. We define this gap in a more stringent way than prior work: we expect correlation of scores from a generator and a validator over the entire set of candidate answers, i.e., candidate co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11381","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/2504.11381/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":"2026-07-05T12:03:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pjAFBqU4ppVFZ5eVYpEgrIl7KdYp/AuY1W8Gzj0FC1V2L560DuyHMJC8KhNsf3BWscuxrDiWgw3VrDIDrI89Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:04:54.143569Z"},"content_sha256":"5aad89c8c193e5c77ee78f847ee8d627e82df03fbf8066755a635e4e9c2e2e89","schema_version":"1.0","event_id":"sha256:5aad89c8c193e5c77ee78f847ee8d627e82df03fbf8066755a635e4e9c2e2e89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SKFHYOF3YVWXU4OIEMVP4FXY46/bundle.json","state_url":"https://pith.science/pith/SKFHYOF3YVWXU4OIEMVP4FXY46/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SKFHYOF3YVWXU4OIEMVP4FXY46/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":"2026-08-03T21:04:54Z","links":{"resolver":"https://pith.science/pith/SKFHYOF3YVWXU4OIEMVP4FXY46","bundle":"https://pith.science/pith/SKFHYOF3YVWXU4OIEMVP4FXY46/bundle.json","state":"https://pith.science/pith/SKFHYOF3YVWXU4OIEMVP4FXY46/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SKFHYOF3YVWXU4OIEMVP4FXY46/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SKFHYOF3YVWXU4OIEMVP4FXY46","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":"59caf28f72dd293f1219e77ef366d0ca121b4d67f29e974df430ed1980b2a380","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-15T16:53:31Z","title_canon_sha256":"3af2aac69d9ab91126637a7065af0b21e07d0f50896f054285c21b531d50ce74"},"schema_version":"1.0","source":{"id":"2504.11381","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.11381","created_at":"2026-07-05T12:03:26Z"},{"alias_kind":"arxiv_version","alias_value":"2504.11381v2","created_at":"2026-07-05T12:03:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11381","created_at":"2026-07-05T12:03:26Z"},{"alias_kind":"pith_short_12","alias_value":"SKFHYOF3YVWX","created_at":"2026-07-05T12:03:26Z"},{"alias_kind":"pith_short_16","alias_value":"SKFHYOF3YVWXU4OI","created_at":"2026-07-05T12:03:26Z"},{"alias_kind":"pith_short_8","alias_value":"SKFHYOF3","created_at":"2026-07-05T12:03:26Z"}],"graph_snapshots":[{"event_id":"sha256:5aad89c8c193e5c77ee78f847ee8d627e82df03fbf8066755a635e4e9c2e2e89","target":"graph","created_at":"2026-07-05T12:03:26Z","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/2504.11381/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although large language models (LLMs) have become more capable and accurate across many tasks, some fundamental sources of unreliability remain in their behavior. One key limitation is their inconsistency at reporting the same information when prompts are changed. In this paper, we consider the discrepancy between a model's generated answer and their own verification of that answer, the generator-validator gap. We define this gap in a more stringent way than prior work: we expect correlation of scores from a generator and a validator over the entire set of candidate answers, i.e., candidate co","authors_text":"Greg Durrett, Juan Diego Rodriguez, Katrin Erk, Wenxuan Ding","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-15T16:53:31Z","title":"RankAlign: A Ranking View of the Generator-Validator Gap in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11381","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":"sha256:1c4f26b66dfb00603d24505fb3ebf6f2811ddc0d6a12b0a4689b8d0433f1fada","target":"record","created_at":"2026-07-05T12:03:26Z","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":"59caf28f72dd293f1219e77ef366d0ca121b4d67f29e974df430ed1980b2a380","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-15T16:53:31Z","title_canon_sha256":"3af2aac69d9ab91126637a7065af0b21e07d0f50896f054285c21b531d50ce74"},"schema_version":"1.0","source":{"id":"2504.11381","kind":"arxiv","version":2}},"canonical_sha256":"928a7c38bbc56d7a71c8232afe16f8e7b7a17cca81db804eedcbe0776da1e26c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"928a7c38bbc56d7a71c8232afe16f8e7b7a17cca81db804eedcbe0776da1e26c","first_computed_at":"2026-07-05T12:03:26.201564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:26.201564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r8YvG2kSFVdKvUMpEbOmUU76UCIk/NJQ3GwtcEhgZOvxBFEiGfm3mNEUPQ6s8dJm9vcAXWje7M5V6JWvMdrGCw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:26.202077Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.11381","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c4f26b66dfb00603d24505fb3ebf6f2811ddc0d6a12b0a4689b8d0433f1fada","sha256:5aad89c8c193e5c77ee78f847ee8d627e82df03fbf8066755a635e4e9c2e2e89"],"state_sha256":"e644a61c6b633f37ed0276e2d14ad2f07aba5a1aec10fc00798e20f441b4809f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4IJH469McpZIih0Lr/Q471uC2W3OcnWBdr9JPwQWSfKBSl4JAfrN+4itXoTHKSMagBMsH2NKrobFslEjgA+pAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:04:54.184256Z","bundle_sha256":"4f2b6381d01778f4051a666f72c13457d4284f9a50adc0bb46a59a2b3bae73cc"}}