{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4BYA6DQXX7BPBKWO6BDKHUBP3G","short_pith_number":"pith:4BYA6DQX","canonical_record":{"source":{"id":"2502.14445","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T10:52:38Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"13d29f77e35d16e4254a24766fbebbb2bca9ecc6079ed218c944e2f7ee98925a","abstract_canon_sha256":"350e61fced0cb124445bd039f77b92b84f2b111d987c52dc6e6b455ff401ec34"},"schema_version":"1.0"},"canonical_sha256":"e0700f0e17bfc2f0aacef046a3d02fd9acc8c2392de7c18ae120e77c3e3d0507","source":{"kind":"arxiv","id":"2502.14445","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14445","created_at":"2026-07-05T11:22:36Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14445v2","created_at":"2026-07-05T11:22:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14445","created_at":"2026-07-05T11:22:36Z"},{"alias_kind":"pith_short_12","alias_value":"4BYA6DQXX7BP","created_at":"2026-07-05T11:22:36Z"},{"alias_kind":"pith_short_16","alias_value":"4BYA6DQXX7BPBKWO","created_at":"2026-07-05T11:22:36Z"},{"alias_kind":"pith_short_8","alias_value":"4BYA6DQX","created_at":"2026-07-05T11:22:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4BYA6DQXX7BPBKWO6BDKHUBP3G","target":"record","payload":{"canonical_record":{"source":{"id":"2502.14445","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T10:52:38Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"13d29f77e35d16e4254a24766fbebbb2bca9ecc6079ed218c944e2f7ee98925a","abstract_canon_sha256":"350e61fced0cb124445bd039f77b92b84f2b111d987c52dc6e6b455ff401ec34"},"schema_version":"1.0"},"canonical_sha256":"e0700f0e17bfc2f0aacef046a3d02fd9acc8c2392de7c18ae120e77c3e3d0507","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:36.962813Z","signature_b64":"GYs6DjejksaWPXz+ohq/g4EVYwiiyEFYsyRtzFnWG/612kgmjscXteQFFZxNBzmTiuWJQcjiBh3B7S98V7LxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0700f0e17bfc2f0aacef046a3d02fd9acc8c2392de7c18ae120e77c3e3d0507","last_reissued_at":"2026-07-05T11:22:36.962207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:36.962207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.14445","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":"2026-07-05T11:22:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xosyCbFnNZiILGFo5jU2LKqqQGP706PuwFfFep7/7hECVzG892ZuP0N3Tw2Ra9QmXb1wQnck4Jdett1fEc6uAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:36:16.191781Z"},"content_sha256":"5fc6713ac52fdfd77dfb6d179040fea01b4cb829bf1ca04f03147947aa452759","schema_version":"1.0","event_id":"sha256:5fc6713ac52fdfd77dfb6d179040fea01b4cb829bf1ca04f03147947aa452759"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4BYA6DQXX7BPBKWO6BDKHUBP3G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PredictaBoard: Benchmarking LLM Score Predictability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CL","authors_text":"Ben Slater, Fernando Mart\\'inez-Plumed, Jos\\'e Hern\\'andez-Orallo, Konstantinos Voudouris, Lexin Zhou, Lorenzo Pacchiardi, Wout Schellaert","submitted_at":"2025-02-20T10:52:38Z","abstract_excerpt":"Despite possessing impressive skills, Large Language Models (LLMs) often fail unpredictably, demonstrating inconsistent success in even basic common sense reasoning tasks. This unpredictability poses a significant challenge to ensuring their safe deployment, as identifying and operating within a reliable \"safe zone\" is essential for mitigating risks. To address this, we present PredictaBoard, a novel collaborative benchmarking framework designed to evaluate the ability of score predictors (referred to as assessors) to anticipate LLM errors on specific task instances (i.e., prompts) from existi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14445","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/2502.14445/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":"2026-07-05T11:22:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/X7jIk6ddsIm45YFKKfSnirQIzh3xAV6TtTINLVDkC+sE+oYc8Q0gxsLD662MJ1XfpK6RLRJxeEoVEXK8nlCCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:36:16.192610Z"},"content_sha256":"0f779f4cff7bff7c58f7c40b58a3f3f534a20ee7532c0011c38a850c8642cb95","schema_version":"1.0","event_id":"sha256:0f779f4cff7bff7c58f7c40b58a3f3f534a20ee7532c0011c38a850c8642cb95"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4BYA6DQXX7BPBKWO6BDKHUBP3G/bundle.json","state_url":"https://pith.science/pith/4BYA6DQXX7BPBKWO6BDKHUBP3G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4BYA6DQXX7BPBKWO6BDKHUBP3G/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":"2026-08-17T18:36:16Z","links":{"resolver":"https://pith.science/pith/4BYA6DQXX7BPBKWO6BDKHUBP3G","bundle":"https://pith.science/pith/4BYA6DQXX7BPBKWO6BDKHUBP3G/bundle.json","state":"https://pith.science/pith/4BYA6DQXX7BPBKWO6BDKHUBP3G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4BYA6DQXX7BPBKWO6BDKHUBP3G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4BYA6DQXX7BPBKWO6BDKHUBP3G","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":"350e61fced0cb124445bd039f77b92b84f2b111d987c52dc6e6b455ff401ec34","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T10:52:38Z","title_canon_sha256":"13d29f77e35d16e4254a24766fbebbb2bca9ecc6079ed218c944e2f7ee98925a"},"schema_version":"1.0","source":{"id":"2502.14445","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14445","created_at":"2026-07-05T11:22:36Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14445v2","created_at":"2026-07-05T11:22:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14445","created_at":"2026-07-05T11:22:36Z"},{"alias_kind":"pith_short_12","alias_value":"4BYA6DQXX7BP","created_at":"2026-07-05T11:22:36Z"},{"alias_kind":"pith_short_16","alias_value":"4BYA6DQXX7BPBKWO","created_at":"2026-07-05T11:22:36Z"},{"alias_kind":"pith_short_8","alias_value":"4BYA6DQX","created_at":"2026-07-05T11:22:36Z"}],"graph_snapshots":[{"event_id":"sha256:0f779f4cff7bff7c58f7c40b58a3f3f534a20ee7532c0011c38a850c8642cb95","target":"graph","created_at":"2026-07-05T11:22:36Z","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/2502.14445/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite possessing impressive skills, Large Language Models (LLMs) often fail unpredictably, demonstrating inconsistent success in even basic common sense reasoning tasks. This unpredictability poses a significant challenge to ensuring their safe deployment, as identifying and operating within a reliable \"safe zone\" is essential for mitigating risks. To address this, we present PredictaBoard, a novel collaborative benchmarking framework designed to evaluate the ability of score predictors (referred to as assessors) to anticipate LLM errors on specific task instances (i.e., prompts) from existi","authors_text":"Ben Slater, Fernando Mart\\'inez-Plumed, Jos\\'e Hern\\'andez-Orallo, Konstantinos Voudouris, Lexin Zhou, Lorenzo Pacchiardi, Wout Schellaert","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T10:52:38Z","title":"PredictaBoard: Benchmarking LLM Score Predictability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14445","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":"sha256:5fc6713ac52fdfd77dfb6d179040fea01b4cb829bf1ca04f03147947aa452759","target":"record","created_at":"2026-07-05T11:22:36Z","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":"350e61fced0cb124445bd039f77b92b84f2b111d987c52dc6e6b455ff401ec34","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T10:52:38Z","title_canon_sha256":"13d29f77e35d16e4254a24766fbebbb2bca9ecc6079ed218c944e2f7ee98925a"},"schema_version":"1.0","source":{"id":"2502.14445","kind":"arxiv","version":2}},"canonical_sha256":"e0700f0e17bfc2f0aacef046a3d02fd9acc8c2392de7c18ae120e77c3e3d0507","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0700f0e17bfc2f0aacef046a3d02fd9acc8c2392de7c18ae120e77c3e3d0507","first_computed_at":"2026-07-05T11:22:36.962207Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:36.962207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GYs6DjejksaWPXz+ohq/g4EVYwiiyEFYsyRtzFnWG/612kgmjscXteQFFZxNBzmTiuWJQcjiBh3B7S98V7LxCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:36.962813Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14445","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fc6713ac52fdfd77dfb6d179040fea01b4cb829bf1ca04f03147947aa452759","sha256:0f779f4cff7bff7c58f7c40b58a3f3f534a20ee7532c0011c38a850c8642cb95"],"state_sha256":"8fa44926e5354c03cdb52dedf67455824b53617a9a42cd218d80e24036d3c46d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I8XLQ08Z6aXunz0xBs3MTY+LI4kF9vsxesvDP5+UmacWM0/2OlhXBnUvmuLAk0LhL0pPYVqbNl9BR9iqyNWIBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T18:36:16.197865Z","bundle_sha256":"f351c1754c8be4493fe1a574fabf7b0cde336b6769d24d089b90a3e55effc49a"}}