{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OXEKTXIBSJLUUTXPRPBWUE4OHH","short_pith_number":"pith:OXEKTXIB","canonical_record":{"source":{"id":"2503.13335","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T16:15:02Z","cross_cats_sorted":["cs.AI","cs.LG","stat.AP"],"title_canon_sha256":"af0cf2fbd448034b04844e7f13adb4aa3180700a3186c237b7a5fb76defe550c","abstract_canon_sha256":"2ef3137a434c6f5f7a703eafd1cf158874d9e8b4fb96b2a15a4267d175bfc461"},"schema_version":"1.0"},"canonical_sha256":"75c8a9dd0192574a4eef8bc36a138e39f5622e72188f94fa79bbb1844f795402","source":{"kind":"arxiv","id":"2503.13335","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13335","created_at":"2026-07-05T10:32:58Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13335v1","created_at":"2026-07-05T10:32:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13335","created_at":"2026-07-05T10:32:58Z"},{"alias_kind":"pith_short_12","alias_value":"OXEKTXIBSJLU","created_at":"2026-07-05T10:32:58Z"},{"alias_kind":"pith_short_16","alias_value":"OXEKTXIBSJLUUTXP","created_at":"2026-07-05T10:32:58Z"},{"alias_kind":"pith_short_8","alias_value":"OXEKTXIB","created_at":"2026-07-05T10:32:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OXEKTXIBSJLUUTXPRPBWUE4OHH","target":"record","payload":{"canonical_record":{"source":{"id":"2503.13335","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T16:15:02Z","cross_cats_sorted":["cs.AI","cs.LG","stat.AP"],"title_canon_sha256":"af0cf2fbd448034b04844e7f13adb4aa3180700a3186c237b7a5fb76defe550c","abstract_canon_sha256":"2ef3137a434c6f5f7a703eafd1cf158874d9e8b4fb96b2a15a4267d175bfc461"},"schema_version":"1.0"},"canonical_sha256":"75c8a9dd0192574a4eef8bc36a138e39f5622e72188f94fa79bbb1844f795402","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:58.539112Z","signature_b64":"gmboxXcuA4qRa7JGJa6FB6EjcyuMDzYvbRzn6nVtQU33s1Jl+fH5hkX6jSGiUk8xQDWu4f0IoYmlnVWg4TW9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75c8a9dd0192574a4eef8bc36a138e39f5622e72188f94fa79bbb1844f795402","last_reissued_at":"2026-07-05T10:32:58.538259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:58.538259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.13335","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":"2026-07-05T10:32:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ejYWeIrUBEf2wm8q5il8NDpdikt4bUlNUF5jLaVXRNiPxewfHlTZmEaHJuwPl3nIEoUWl1+syOtwG2hPrG+DCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:53:31.210077Z"},"content_sha256":"b324a08d35e96228a350c2eba3661d272043ca7f9b96582a0ef496609b249076","schema_version":"1.0","event_id":"sha256:b324a08d35e96228a350c2eba3661d272043ca7f9b96582a0ef496609b249076"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OXEKTXIBSJLUUTXPRPBWUE4OHH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reliable and Efficient Amortized Model-based Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.AP"],"primary_cat":"cs.CL","authors_text":"Bo Li, Percy Liang, Sang Truong, Sanmi Koyejo, Yuheng Tu","submitted_at":"2025-03-17T16:15:02Z","abstract_excerpt":"Comprehensive evaluations of language models (LM) during both development and deployment phases are necessary because these models possess numerous capabilities (e.g., mathematical reasoning, legal support, or medical diagnostic) as well as safety risks (e.g., racial bias, toxicity, or misinformation). The average score across a wide range of benchmarks provides a signal that helps guide the use of these LMs in practice. Currently, holistic evaluations are costly due to the large volume of benchmark questions, making frequent evaluations impractical. A popular attempt to lower the cost is to c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13335","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/2503.13335/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":"2026-07-05T10:32:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y+gRwr6gcj4zEJ5clq4G0Zv3lnCJRknhXvjnetlzJgdxDG2c90KpJoNhx7zqTmSTt8oA9dG0b51d8GOhk4mdDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:53:31.210669Z"},"content_sha256":"23de08cc69b3c7675136fcb0ec27b25fba913db5f9ee04491a9b91f76c233b2e","schema_version":"1.0","event_id":"sha256:23de08cc69b3c7675136fcb0ec27b25fba913db5f9ee04491a9b91f76c233b2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OXEKTXIBSJLUUTXPRPBWUE4OHH/bundle.json","state_url":"https://pith.science/pith/OXEKTXIBSJLUUTXPRPBWUE4OHH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OXEKTXIBSJLUUTXPRPBWUE4OHH/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":"2026-08-06T01:53:31Z","links":{"resolver":"https://pith.science/pith/OXEKTXIBSJLUUTXPRPBWUE4OHH","bundle":"https://pith.science/pith/OXEKTXIBSJLUUTXPRPBWUE4OHH/bundle.json","state":"https://pith.science/pith/OXEKTXIBSJLUUTXPRPBWUE4OHH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OXEKTXIBSJLUUTXPRPBWUE4OHH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OXEKTXIBSJLUUTXPRPBWUE4OHH","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":"2ef3137a434c6f5f7a703eafd1cf158874d9e8b4fb96b2a15a4267d175bfc461","cross_cats_sorted":["cs.AI","cs.LG","stat.AP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T16:15:02Z","title_canon_sha256":"af0cf2fbd448034b04844e7f13adb4aa3180700a3186c237b7a5fb76defe550c"},"schema_version":"1.0","source":{"id":"2503.13335","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13335","created_at":"2026-07-05T10:32:58Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13335v1","created_at":"2026-07-05T10:32:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13335","created_at":"2026-07-05T10:32:58Z"},{"alias_kind":"pith_short_12","alias_value":"OXEKTXIBSJLU","created_at":"2026-07-05T10:32:58Z"},{"alias_kind":"pith_short_16","alias_value":"OXEKTXIBSJLUUTXP","created_at":"2026-07-05T10:32:58Z"},{"alias_kind":"pith_short_8","alias_value":"OXEKTXIB","created_at":"2026-07-05T10:32:58Z"}],"graph_snapshots":[{"event_id":"sha256:23de08cc69b3c7675136fcb0ec27b25fba913db5f9ee04491a9b91f76c233b2e","target":"graph","created_at":"2026-07-05T10:32:58Z","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/2503.13335/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Comprehensive evaluations of language models (LM) during both development and deployment phases are necessary because these models possess numerous capabilities (e.g., mathematical reasoning, legal support, or medical diagnostic) as well as safety risks (e.g., racial bias, toxicity, or misinformation). The average score across a wide range of benchmarks provides a signal that helps guide the use of these LMs in practice. Currently, holistic evaluations are costly due to the large volume of benchmark questions, making frequent evaluations impractical. A popular attempt to lower the cost is to c","authors_text":"Bo Li, Percy Liang, Sang Truong, Sanmi Koyejo, Yuheng Tu","cross_cats":["cs.AI","cs.LG","stat.AP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T16:15:02Z","title":"Reliable and Efficient Amortized Model-based Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13335","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:b324a08d35e96228a350c2eba3661d272043ca7f9b96582a0ef496609b249076","target":"record","created_at":"2026-07-05T10:32:58Z","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":"2ef3137a434c6f5f7a703eafd1cf158874d9e8b4fb96b2a15a4267d175bfc461","cross_cats_sorted":["cs.AI","cs.LG","stat.AP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T16:15:02Z","title_canon_sha256":"af0cf2fbd448034b04844e7f13adb4aa3180700a3186c237b7a5fb76defe550c"},"schema_version":"1.0","source":{"id":"2503.13335","kind":"arxiv","version":1}},"canonical_sha256":"75c8a9dd0192574a4eef8bc36a138e39f5622e72188f94fa79bbb1844f795402","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75c8a9dd0192574a4eef8bc36a138e39f5622e72188f94fa79bbb1844f795402","first_computed_at":"2026-07-05T10:32:58.538259Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:32:58.538259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gmboxXcuA4qRa7JGJa6FB6EjcyuMDzYvbRzn6nVtQU33s1Jl+fH5hkX6jSGiUk8xQDWu4f0IoYmlnVWg4TW9Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:32:58.539112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.13335","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b324a08d35e96228a350c2eba3661d272043ca7f9b96582a0ef496609b249076","sha256:23de08cc69b3c7675136fcb0ec27b25fba913db5f9ee04491a9b91f76c233b2e"],"state_sha256":"83811ce144241ebc2ea1b9ef9f2ea4814f5a65cd5177667d9972c848b180bb50"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fwV0xGNiRpoYcnJAKR/pK8wnf1YsC/a7+LNpRZATCpFN+3GoRw8IAgp+xhv0b9Ukms/1MaenqeHpLZAprKB7DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:53:31.216034Z","bundle_sha256":"418db1611a989f774ba0cc469b05ca54742c3c8c9606e432b431d5d1977c246e"}}