{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MA54ZLBFGJBJINM2D7MANXFACC","short_pith_number":"pith:MA54ZLBF","canonical_record":{"source":{"id":"2505.03814","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-02T17:05:01Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"d877335280172712ff7790e5d7fe40de83cb161a73ea769353dd6a3a0c7610c7","abstract_canon_sha256":"6d07bda39b82f1de0b27a977ce1ff2bc39c6e153bfc605ecc3d1dcbcdf58c5aa"},"schema_version":"1.0"},"canonical_sha256":"603bccac25324294359a1fd806dca01099bdd914de96219866c8dbd9e153d1aa","source":{"kind":"arxiv","id":"2505.03814","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03814","created_at":"2026-07-05T10:59:32Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03814v1","created_at":"2026-07-05T10:59:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03814","created_at":"2026-07-05T10:59:32Z"},{"alias_kind":"pith_short_12","alias_value":"MA54ZLBFGJBJ","created_at":"2026-07-05T10:59:32Z"},{"alias_kind":"pith_short_16","alias_value":"MA54ZLBFGJBJINM2","created_at":"2026-07-05T10:59:32Z"},{"alias_kind":"pith_short_8","alias_value":"MA54ZLBF","created_at":"2026-07-05T10:59:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MA54ZLBFGJBJINM2D7MANXFACC","target":"record","payload":{"canonical_record":{"source":{"id":"2505.03814","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-02T17:05:01Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"d877335280172712ff7790e5d7fe40de83cb161a73ea769353dd6a3a0c7610c7","abstract_canon_sha256":"6d07bda39b82f1de0b27a977ce1ff2bc39c6e153bfc605ecc3d1dcbcdf58c5aa"},"schema_version":"1.0"},"canonical_sha256":"603bccac25324294359a1fd806dca01099bdd914de96219866c8dbd9e153d1aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:32.000836Z","signature_b64":"t5vuFZtIuMU3LLsYYvcSA6uHqFUNW1vxiVQjJ2zsT8DqVlh+LDKowtYNGL1uD0ikjKdfRmRY09a7J4qd3apnDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"603bccac25324294359a1fd806dca01099bdd914de96219866c8dbd9e153d1aa","last_reissued_at":"2026-07-05T10:59:32.000345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:32.000345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.03814","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":"2026-07-05T10:59:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rNAvpx5y47n6SABRmXWh5uw8joD82fQCC4PBXmoZPcTTOABELmSTLYfXhWmxcg6V6UrraHt4QfMM+syy8huqAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:40:21.925083Z"},"content_sha256":"ecc42dd623d0d935e90fb298efc892b538d66f39e60235ba00818be0f0013603","schema_version":"1.0","event_id":"sha256:ecc42dd623d0d935e90fb298efc892b538d66f39e60235ba00818be0f0013603"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MA54ZLBFGJBJINM2D7MANXFACC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cer-Eval: Certifiable and Cost-Efficient Evaluation Framework for LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Bo Li, Ganghua Wang, Haifeng Xu, Zhaorun Chen","submitted_at":"2025-05-02T17:05:01Z","abstract_excerpt":"As foundation models continue to scale, the size of trained models grows exponentially, presenting significant challenges for their evaluation. Current evaluation practices involve curating increasingly large datasets to assess the performance of large language models (LLMs). However, there is a lack of systematic analysis and guidance on determining the sufficiency of test data or selecting informative samples for evaluation. This paper introduces a certifiable and cost-efficient evaluation framework for LLMs. Our framework adapts to different evaluation objectives and outputs confidence inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03814","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/2505.03814/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":"2026-07-05T10:59:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JHQWEGQ4aWnArAKnkveY8LR2ntlYfbfbwbpCcLEsHU+e5LM5c4p84QDxmecsZ8QGQwpQm2DNGm1kdU6hGtxICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:40:21.925767Z"},"content_sha256":"77290ee8a64e8b2855fc53dfb581b7f8582112d728186593bf6834540c0717f6","schema_version":"1.0","event_id":"sha256:77290ee8a64e8b2855fc53dfb581b7f8582112d728186593bf6834540c0717f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MA54ZLBFGJBJINM2D7MANXFACC/bundle.json","state_url":"https://pith.science/pith/MA54ZLBFGJBJINM2D7MANXFACC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MA54ZLBFGJBJINM2D7MANXFACC/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":"2026-08-10T02:40:21Z","links":{"resolver":"https://pith.science/pith/MA54ZLBFGJBJINM2D7MANXFACC","bundle":"https://pith.science/pith/MA54ZLBFGJBJINM2D7MANXFACC/bundle.json","state":"https://pith.science/pith/MA54ZLBFGJBJINM2D7MANXFACC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MA54ZLBFGJBJINM2D7MANXFACC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MA54ZLBFGJBJINM2D7MANXFACC","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":"6d07bda39b82f1de0b27a977ce1ff2bc39c6e153bfc605ecc3d1dcbcdf58c5aa","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-02T17:05:01Z","title_canon_sha256":"d877335280172712ff7790e5d7fe40de83cb161a73ea769353dd6a3a0c7610c7"},"schema_version":"1.0","source":{"id":"2505.03814","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03814","created_at":"2026-07-05T10:59:32Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03814v1","created_at":"2026-07-05T10:59:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03814","created_at":"2026-07-05T10:59:32Z"},{"alias_kind":"pith_short_12","alias_value":"MA54ZLBFGJBJ","created_at":"2026-07-05T10:59:32Z"},{"alias_kind":"pith_short_16","alias_value":"MA54ZLBFGJBJINM2","created_at":"2026-07-05T10:59:32Z"},{"alias_kind":"pith_short_8","alias_value":"MA54ZLBF","created_at":"2026-07-05T10:59:32Z"}],"graph_snapshots":[{"event_id":"sha256:77290ee8a64e8b2855fc53dfb581b7f8582112d728186593bf6834540c0717f6","target":"graph","created_at":"2026-07-05T10:59:32Z","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/2505.03814/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As foundation models continue to scale, the size of trained models grows exponentially, presenting significant challenges for their evaluation. Current evaluation practices involve curating increasingly large datasets to assess the performance of large language models (LLMs). However, there is a lack of systematic analysis and guidance on determining the sufficiency of test data or selecting informative samples for evaluation. This paper introduces a certifiable and cost-efficient evaluation framework for LLMs. Our framework adapts to different evaluation objectives and outputs confidence inte","authors_text":"Bo Li, Ganghua Wang, Haifeng Xu, Zhaorun Chen","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-02T17:05:01Z","title":"Cer-Eval: Certifiable and Cost-Efficient Evaluation Framework for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03814","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:ecc42dd623d0d935e90fb298efc892b538d66f39e60235ba00818be0f0013603","target":"record","created_at":"2026-07-05T10:59:32Z","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":"6d07bda39b82f1de0b27a977ce1ff2bc39c6e153bfc605ecc3d1dcbcdf58c5aa","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-02T17:05:01Z","title_canon_sha256":"d877335280172712ff7790e5d7fe40de83cb161a73ea769353dd6a3a0c7610c7"},"schema_version":"1.0","source":{"id":"2505.03814","kind":"arxiv","version":1}},"canonical_sha256":"603bccac25324294359a1fd806dca01099bdd914de96219866c8dbd9e153d1aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"603bccac25324294359a1fd806dca01099bdd914de96219866c8dbd9e153d1aa","first_computed_at":"2026-07-05T10:59:32.000345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:32.000345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t5vuFZtIuMU3LLsYYvcSA6uHqFUNW1vxiVQjJ2zsT8DqVlh+LDKowtYNGL1uD0ikjKdfRmRY09a7J4qd3apnDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:32.000836Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03814","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecc42dd623d0d935e90fb298efc892b538d66f39e60235ba00818be0f0013603","sha256:77290ee8a64e8b2855fc53dfb581b7f8582112d728186593bf6834540c0717f6"],"state_sha256":"25779ae90f68d1b219875181138db3505859890ed135c494326fa541ae39926d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ls8s/52YRueL7MaLOOpCcMb1Bli0G1oCkjQqWZu7vGOvEGM6V2YPZuq44A0KeHyKXUNpLN8DpW3dzrmBE2IHAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T02:40:21.929885Z","bundle_sha256":"f493204029e2e0866541442e7186340b48e07bffe95ae82e2c679a85b312dfbd"}}