{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LSMLM6YVAA54UHPKVWSY5UIMFG","short_pith_number":"pith:LSMLM6YV","canonical_record":{"source":{"id":"2410.05952","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T12:08:46Z","cross_cats_sorted":[],"title_canon_sha256":"3bdb10fbd1412b30a21140c6eaf24847e415b3f35f549ed311e7e5b0f11ed890","abstract_canon_sha256":"80aa9be01533a1bc4ddb1877efa31c838329b3b5a99ff4ae6aa5e0b4b4e5f5d4"},"schema_version":"1.0"},"canonical_sha256":"5c98b67b15003bca1deaada58ed10c29a658f19609462251cb91c2986f0fc7e7","source":{"kind":"arxiv","id":"2410.05952","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.05952","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"arxiv_version","alias_value":"2410.05952v1","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05952","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"pith_short_12","alias_value":"LSMLM6YVAA54","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"pith_short_16","alias_value":"LSMLM6YVAA54UHPK","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"pith_short_8","alias_value":"LSMLM6YV","created_at":"2026-07-05T09:17:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LSMLM6YVAA54UHPKVWSY5UIMFG","target":"record","payload":{"canonical_record":{"source":{"id":"2410.05952","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T12:08:46Z","cross_cats_sorted":[],"title_canon_sha256":"3bdb10fbd1412b30a21140c6eaf24847e415b3f35f549ed311e7e5b0f11ed890","abstract_canon_sha256":"80aa9be01533a1bc4ddb1877efa31c838329b3b5a99ff4ae6aa5e0b4b4e5f5d4"},"schema_version":"1.0"},"canonical_sha256":"5c98b67b15003bca1deaada58ed10c29a658f19609462251cb91c2986f0fc7e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:53.651385Z","signature_b64":"7Yt/AI1Yv64Ybbuw9nO0B/tJjctioGwBQ9LbrUvGTeD3bJDTh01efXd7AF/lpE9XT8ei64SCITpv+OVH7fIlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c98b67b15003bca1deaada58ed10c29a658f19609462251cb91c2986f0fc7e7","last_reissued_at":"2026-07-05T09:17:53.650935Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:53.650935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.05952","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":"2026-07-05T09:17:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wuyf1cEFm38601Fijt0UaUEr8xgB/fwlYD7eYRB99kg59OApmu0OJsAQketnS3JH/bzyA7NMfIPagb9x5GgFBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T15:32:18.049285Z"},"content_sha256":"1e7d5f2a639c2cfa54692700895742097351c1c7123452768284159617d0298b","schema_version":"1.0","event_id":"sha256:1e7d5f2a639c2cfa54692700895742097351c1c7123452768284159617d0298b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LSMLM6YVAA54UHPKVWSY5UIMFG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Active Evaluation Acquisition for Efficient LLM Benchmarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Graham Horwood, Jie Ma, Miguel Ballesteros, Yang Li, Yassine Benajiba","submitted_at":"2024-10-08T12:08:46Z","abstract_excerpt":"As large language models (LLMs) become increasingly versatile, numerous large scale benchmarks have been developed to thoroughly assess their capabilities. These benchmarks typically consist of diverse datasets and prompts to evaluate different aspects of LLM performance. However, comprehensive evaluations on hundreds or thousands of prompts incur tremendous costs in terms of computation, money, and time. In this work, we investigate strategies to improve evaluation efficiency by selecting a subset of examples from each benchmark using a learned policy. Our approach models the dependencies acr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05952","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/2410.05952/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":"2026-07-05T09:17:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aC3GA+PHeXjzudA7OqlP9jX1yR2LE8AQTRspF4OpJKOtx/fhDQV3PQSbc37vGeaIKzmnQvpPwnARjLRP319cBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T15:32:18.049675Z"},"content_sha256":"9207ee5b80f37332577e5a3e008b4bf82589e994b25077b230a81d73a245b123","schema_version":"1.0","event_id":"sha256:9207ee5b80f37332577e5a3e008b4bf82589e994b25077b230a81d73a245b123"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LSMLM6YVAA54UHPKVWSY5UIMFG/bundle.json","state_url":"https://pith.science/pith/LSMLM6YVAA54UHPKVWSY5UIMFG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LSMLM6YVAA54UHPKVWSY5UIMFG/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":"2026-07-17T15:32:18Z","links":{"resolver":"https://pith.science/pith/LSMLM6YVAA54UHPKVWSY5UIMFG","bundle":"https://pith.science/pith/LSMLM6YVAA54UHPKVWSY5UIMFG/bundle.json","state":"https://pith.science/pith/LSMLM6YVAA54UHPKVWSY5UIMFG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LSMLM6YVAA54UHPKVWSY5UIMFG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LSMLM6YVAA54UHPKVWSY5UIMFG","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":"80aa9be01533a1bc4ddb1877efa31c838329b3b5a99ff4ae6aa5e0b4b4e5f5d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T12:08:46Z","title_canon_sha256":"3bdb10fbd1412b30a21140c6eaf24847e415b3f35f549ed311e7e5b0f11ed890"},"schema_version":"1.0","source":{"id":"2410.05952","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.05952","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"arxiv_version","alias_value":"2410.05952v1","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05952","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"pith_short_12","alias_value":"LSMLM6YVAA54","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"pith_short_16","alias_value":"LSMLM6YVAA54UHPK","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"pith_short_8","alias_value":"LSMLM6YV","created_at":"2026-07-05T09:17:53Z"}],"graph_snapshots":[{"event_id":"sha256:9207ee5b80f37332577e5a3e008b4bf82589e994b25077b230a81d73a245b123","target":"graph","created_at":"2026-07-05T09:17:53Z","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/2410.05952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) become increasingly versatile, numerous large scale benchmarks have been developed to thoroughly assess their capabilities. These benchmarks typically consist of diverse datasets and prompts to evaluate different aspects of LLM performance. However, comprehensive evaluations on hundreds or thousands of prompts incur tremendous costs in terms of computation, money, and time. In this work, we investigate strategies to improve evaluation efficiency by selecting a subset of examples from each benchmark using a learned policy. Our approach models the dependencies acr","authors_text":"Graham Horwood, Jie Ma, Miguel Ballesteros, Yang Li, Yassine Benajiba","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T12:08:46Z","title":"Active Evaluation Acquisition for Efficient LLM Benchmarking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05952","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":"sha256:1e7d5f2a639c2cfa54692700895742097351c1c7123452768284159617d0298b","target":"record","created_at":"2026-07-05T09:17:53Z","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":"80aa9be01533a1bc4ddb1877efa31c838329b3b5a99ff4ae6aa5e0b4b4e5f5d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T12:08:46Z","title_canon_sha256":"3bdb10fbd1412b30a21140c6eaf24847e415b3f35f549ed311e7e5b0f11ed890"},"schema_version":"1.0","source":{"id":"2410.05952","kind":"arxiv","version":1}},"canonical_sha256":"5c98b67b15003bca1deaada58ed10c29a658f19609462251cb91c2986f0fc7e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c98b67b15003bca1deaada58ed10c29a658f19609462251cb91c2986f0fc7e7","first_computed_at":"2026-07-05T09:17:53.650935Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:53.650935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Yt/AI1Yv64Ybbuw9nO0B/tJjctioGwBQ9LbrUvGTeD3bJDTh01efXd7AF/lpE9XT8ei64SCITpv+OVH7fIlBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:53.651385Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.05952","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e7d5f2a639c2cfa54692700895742097351c1c7123452768284159617d0298b","sha256:9207ee5b80f37332577e5a3e008b4bf82589e994b25077b230a81d73a245b123"],"state_sha256":"ff3561c2f92649cd19f37188e2550bdf1d78eb4a4184ef91123210596746860b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ilbzrj/RTpYAo1d25TWLZ4VeziQV7hhDGb3CCC13dzZ59u9XfcmbItkRytX1fOnmc/jGxxDKKlJVyeoo7+S2CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T15:32:18.051869Z","bundle_sha256":"0c4caec42808e81236f9b4335bbdf5a1d55d35563e98cbefa92646c07863e638"}}