{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YHRSAPUH3DTFWEOYXT3YBMJDUJ","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fc83f9d340ddfed1c463da7f8109a7b77c50cf28c5a008a4f3c5ccaf797b1cea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T13:22:04Z","title_canon_sha256":"5952761a534a2a0e38aad7bb1d570edf9ad7a3795cdc83520c8da3cae3cddc10"},"schema_version":"1.0","source":{"id":"2607.05046","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05046","created_at":"2026-07-07T02:20:20Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05046v1","created_at":"2026-07-07T02:20:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05046","created_at":"2026-07-07T02:20:20Z"},{"alias_kind":"pith_short_12","alias_value":"YHRSAPUH3DTF","created_at":"2026-07-07T02:20:20Z"},{"alias_kind":"pith_short_16","alias_value":"YHRSAPUH3DTFWEOY","created_at":"2026-07-07T02:20:20Z"},{"alias_kind":"pith_short_8","alias_value":"YHRSAPUH","created_at":"2026-07-07T02:20:20Z"}],"graph_snapshots":[{"event_id":"sha256:8b74c0f77eb75d32e676172031ed9b5d9d8e93c568fb376135a6a313e9af408b","target":"graph","created_at":"2026-07-07T02:20:20Z","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/2607.05046/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating generative AI models is a routine, but resource-intensive, process that is conducted over and over again during the course of model development. In this work, we propose Collaborative Evaluation (CollabEval), a simple, effective, and principled method for exploiting dependencies between historical runs of different models on the same tasks to improve statistical efficiency. Specifically, our approach treats model evaluation as a matrix completion problem over an $M \\times N$ matrix of evaluation scores, where $M$ is the total number of models and $N$ is the total number of evaluatio","authors_text":"Adam Fisch, Alekh Agarwal, Amir Globerson, Daniel Deutsch, Jacob Eisenstein, Jonathan Berant, Joshua Maynez, William Cohen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T13:22:04Z","title":"CollabEval: Statistically Efficient Collaborative Model Evaluation via Matrix Completion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05046","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":"sha256:12a99d804e1ef62f6e3f0d39654be2e17567b6ae820200ffb54140a01bd5e12c","target":"record","created_at":"2026-07-07T02:20:20Z","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":"fc83f9d340ddfed1c463da7f8109a7b77c50cf28c5a008a4f3c5ccaf797b1cea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T13:22:04Z","title_canon_sha256":"5952761a534a2a0e38aad7bb1d570edf9ad7a3795cdc83520c8da3cae3cddc10"},"schema_version":"1.0","source":{"id":"2607.05046","kind":"arxiv","version":1}},"canonical_sha256":"c1e3203e87d8e65b11d8bcf780b123a24e41badd5ecdad56f091b5f2e944f3a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1e3203e87d8e65b11d8bcf780b123a24e41badd5ecdad56f091b5f2e944f3a7","first_computed_at":"2026-07-07T02:20:20.413378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:20:20.413378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"enAd0SUq/FiFmwsBOPwehPEkIOh69n5O3Hc4JSNBoILGitPfoRVFUasJlFGFRA2R5q1umolesbp0Sx6LUoRlDA==","signature_status":"signed_v1","signed_at":"2026-07-07T02:20:20.414234Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.05046","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:3d863d73073d9c86f1779abed7e987d2c8364e4b82d0284a0064f7d29b932d69","sha256:82a3915ad54e6151fd6cd914ef84de22853531380aaba8844519088ca9dfca3e"]}],"invalid_events":[],"applied_event_ids":["sha256:12a99d804e1ef62f6e3f0d39654be2e17567b6ae820200ffb54140a01bd5e12c","sha256:8b74c0f77eb75d32e676172031ed9b5d9d8e93c568fb376135a6a313e9af408b"],"state_sha256":"143a7bd7a75831650a58f5b951ff98673cbaf5b63c9d78d25bb6cb06219ea866"}