{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:D6WWVLL6B57N2DSJEPQJZ25UNT","short_pith_number":"pith:D6WWVLL6","canonical_record":{"source":{"id":"2607.27023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T15:20:39Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a962e81ad91aacab9a8d5ec571d8d05586dc7da32edd3652c64d48177e8442fa","abstract_canon_sha256":"b3e074b47d786a692c7d912152fc577d592ad32c635edfa3e607696b7d97cfec"},"schema_version":"1.0"},"canonical_sha256":"1fad6aad7e0f7edd0e4923e09cebb46ccf8c496b77d286167824c0707bfbed3e","source":{"kind":"arxiv","id":"2607.27023","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27023","created_at":"2026-07-30T01:23:22Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27023v1","created_at":"2026-07-30T01:23:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27023","created_at":"2026-07-30T01:23:22Z"},{"alias_kind":"pith_short_12","alias_value":"D6WWVLL6B57N","created_at":"2026-07-30T01:23:22Z"},{"alias_kind":"pith_short_16","alias_value":"D6WWVLL6B57N2DSJ","created_at":"2026-07-30T01:23:22Z"},{"alias_kind":"pith_short_8","alias_value":"D6WWVLL6","created_at":"2026-07-30T01:23:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:D6WWVLL6B57N2DSJEPQJZ25UNT","target":"record","payload":{"canonical_record":{"source":{"id":"2607.27023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T15:20:39Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a962e81ad91aacab9a8d5ec571d8d05586dc7da32edd3652c64d48177e8442fa","abstract_canon_sha256":"b3e074b47d786a692c7d912152fc577d592ad32c635edfa3e607696b7d97cfec"},"schema_version":"1.0"},"canonical_sha256":"1fad6aad7e0f7edd0e4923e09cebb46ccf8c496b77d286167824c0707bfbed3e","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fad6aad7e0f7edd0e4923e09cebb46ccf8c496b77d286167824c0707bfbed3e","last_reissued_at":"2026-07-30T01:23:22.328225Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:23:22.328225Z"},"source_kind":"arxiv","source_id":"2607.27023","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":"2026-07-30T01:23:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DS97HaB5XGMfsqMJ0oW6wjuRWsdDf21PP349ParxmY04HBAiKEfbv1fDpoTi+OXOAej+9f/Kr9HQovDLkj9eCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:02:06.379871Z"},"content_sha256":"296b584bce6d2e265e6d152907c2b67b4200018f392a8e3d83b5b3119dd988a3","schema_version":"1.0","event_id":"sha256:296b584bce6d2e265e6d152907c2b67b4200018f392a8e3d83b5b3119dd988a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:D6WWVLL6B57N2DSJEPQJZ25UNT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BayesAME: Bayesian Active Model Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arnaud Doucet, Paula Cordero Encinar, Silvia Chiappa, Taylan Cemgil, Virginia Aglietti","submitted_at":"2026-07-29T15:20:39Z","abstract_excerpt":"Evaluating large generative models across benchmarks is time-consuming and computationally expensive. This drives the need for methods that can estimate full benchmark performance by evaluating models on only a subset of items, known as a coreset. Current literature mostly requires the practitioner to input a coreset size. However, when reliable performance estimation takes priority over efficiency, an evaluation method should also be capable of automatically determining a coreset size that reflects this priority. We introduce BayesAME, a sequential Bayesian framework specifically targeting au"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27023","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/2607.27023/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":"2026-07-30T01:23:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G6to/JBpqxqkq6AAvA7f1gCqDpBqtre3cfecgkqg9v8ELt814PgTGOoh+l1YVQnxb6pY9rUdzsyy4UoPrdziBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:02:06.380540Z"},"content_sha256":"cbc089a5791c9f9d78f2fa0c794b8c1e442f4113b4ca2110aad24e21e12da4d0","schema_version":"1.0","event_id":"sha256:cbc089a5791c9f9d78f2fa0c794b8c1e442f4113b4ca2110aad24e21e12da4d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D6WWVLL6B57N2DSJEPQJZ25UNT/bundle.json","state_url":"https://pith.science/pith/D6WWVLL6B57N2DSJEPQJZ25UNT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D6WWVLL6B57N2DSJEPQJZ25UNT/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":"2026-08-04T21:02:06Z","links":{"resolver":"https://pith.science/pith/D6WWVLL6B57N2DSJEPQJZ25UNT","bundle":"https://pith.science/pith/D6WWVLL6B57N2DSJEPQJZ25UNT/bundle.json","state":"https://pith.science/pith/D6WWVLL6B57N2DSJEPQJZ25UNT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D6WWVLL6B57N2DSJEPQJZ25UNT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:D6WWVLL6B57N2DSJEPQJZ25UNT","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":"b3e074b47d786a692c7d912152fc577d592ad32c635edfa3e607696b7d97cfec","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T15:20:39Z","title_canon_sha256":"a962e81ad91aacab9a8d5ec571d8d05586dc7da32edd3652c64d48177e8442fa"},"schema_version":"1.0","source":{"id":"2607.27023","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27023","created_at":"2026-07-30T01:23:22Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27023v1","created_at":"2026-07-30T01:23:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27023","created_at":"2026-07-30T01:23:22Z"},{"alias_kind":"pith_short_12","alias_value":"D6WWVLL6B57N","created_at":"2026-07-30T01:23:22Z"},{"alias_kind":"pith_short_16","alias_value":"D6WWVLL6B57N2DSJ","created_at":"2026-07-30T01:23:22Z"},{"alias_kind":"pith_short_8","alias_value":"D6WWVLL6","created_at":"2026-07-30T01:23:22Z"}],"graph_snapshots":[{"event_id":"sha256:cbc089a5791c9f9d78f2fa0c794b8c1e442f4113b4ca2110aad24e21e12da4d0","target":"graph","created_at":"2026-07-30T01:23:22Z","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/2607.27023/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating large generative models across benchmarks is time-consuming and computationally expensive. This drives the need for methods that can estimate full benchmark performance by evaluating models on only a subset of items, known as a coreset. Current literature mostly requires the practitioner to input a coreset size. However, when reliable performance estimation takes priority over efficiency, an evaluation method should also be capable of automatically determining a coreset size that reflects this priority. We introduce BayesAME, a sequential Bayesian framework specifically targeting au","authors_text":"Arnaud Doucet, Paula Cordero Encinar, Silvia Chiappa, Taylan Cemgil, Virginia Aglietti","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T15:20:39Z","title":"BayesAME: Bayesian Active Model Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27023","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":"sha256:296b584bce6d2e265e6d152907c2b67b4200018f392a8e3d83b5b3119dd988a3","target":"record","created_at":"2026-07-30T01:23:22Z","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":"b3e074b47d786a692c7d912152fc577d592ad32c635edfa3e607696b7d97cfec","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T15:20:39Z","title_canon_sha256":"a962e81ad91aacab9a8d5ec571d8d05586dc7da32edd3652c64d48177e8442fa"},"schema_version":"1.0","source":{"id":"2607.27023","kind":"arxiv","version":1}},"canonical_sha256":"1fad6aad7e0f7edd0e4923e09cebb46ccf8c496b77d286167824c0707bfbed3e","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fad6aad7e0f7edd0e4923e09cebb46ccf8c496b77d286167824c0707bfbed3e","first_computed_at":"2026-07-30T01:23:22.328225Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:23:22.328225Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.27023","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:296b584bce6d2e265e6d152907c2b67b4200018f392a8e3d83b5b3119dd988a3","sha256:cbc089a5791c9f9d78f2fa0c794b8c1e442f4113b4ca2110aad24e21e12da4d0"],"state_sha256":"9cd6a8fffb76a1a6425d3f4f4cbdbccb537f464ac194fb7ea48e3b6502b323eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fJXCrxY8BL58aKkbynMRGXBsYKX6uI23RD8x9XsbQD6KMEzsfTPBtXm9aawIlZRs62//Khp2eAOKHeYgNjgPDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:02:06.388867Z","bundle_sha256":"b901b1b618214f6275bd9a593a212962be855a4223eeb70e2b514ed06f37d42b"}}