{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q5BTZPWDQNGJGPX7NZZWK5EXOJ","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":"b7ddcbf1d5febd1b4d868122820ab6e7f6da7d495a07f8a3dd8f1f5337d835a8","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-23T11:54:09Z","title_canon_sha256":"6f604c437e7dd292ccb0b8f304979d272814250b6d220c59885f0f237847f431"},"schema_version":"1.0","source":{"id":"2401.12689","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12689","created_at":"2026-07-05T07:56:20Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12689v3","created_at":"2026-07-05T07:56:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12689","created_at":"2026-07-05T07:56:20Z"},{"alias_kind":"pith_short_12","alias_value":"Q5BTZPWDQNGJ","created_at":"2026-07-05T07:56:20Z"},{"alias_kind":"pith_short_16","alias_value":"Q5BTZPWDQNGJGPX7","created_at":"2026-07-05T07:56:20Z"},{"alias_kind":"pith_short_8","alias_value":"Q5BTZPWD","created_at":"2026-07-05T07:56:20Z"}],"graph_snapshots":[{"event_id":"sha256:8e027e09b2f775fdd7823c09e3279d74b3d76d1607fa14083ea09714681de91c","target":"graph","created_at":"2026-07-05T07:56:20Z","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/2401.12689/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The conventional evaluation protocols on machine learning models rely heavily on a labeled, i.i.d-assumed testing dataset, which is not often present in real world applications. The Automated Model Evaluation (AutoEval) shows an alternative to this traditional workflow, by forming a proximal prediction pipeline of the testing performance without the presence of ground-truth labels. Despite its recent successes, the AutoEval frameworks still suffer from an overconfidence issue, substantial storage and computational cost. In that regard, we propose a novel measure -- Meta-Distribution Energy (MD","authors_text":"Haobo Wang, Heming Zou, Junbo Zhao, Ru Peng, Yawen Zeng, Zenan Huang","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-23T11:54:09Z","title":"Energy-based Automated Model Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12689","kind":"arxiv","version":3},"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":"sha256:05a9041389b2cf420c3532148a79bd3549f06fdc295a1c44fc00d257b1d5054a","target":"record","created_at":"2026-07-05T07:56:20Z","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":"b7ddcbf1d5febd1b4d868122820ab6e7f6da7d495a07f8a3dd8f1f5337d835a8","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-23T11:54:09Z","title_canon_sha256":"6f604c437e7dd292ccb0b8f304979d272814250b6d220c59885f0f237847f431"},"schema_version":"1.0","source":{"id":"2401.12689","kind":"arxiv","version":3}},"canonical_sha256":"87433cbec3834c933eff6e73657497724ebaef3d3f18a604846bdfb61a93ca73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87433cbec3834c933eff6e73657497724ebaef3d3f18a604846bdfb61a93ca73","first_computed_at":"2026-07-05T07:56:20.555360Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:20.555360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X1OVAL3emti/PvX0bQ67kX66x5o7A5S3qbSA1tVURlTWHShXlX3Tj5uo6w9fhjzU91atp1G01OQdK0xTgqazAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:20.555873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.12689","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05a9041389b2cf420c3532148a79bd3549f06fdc295a1c44fc00d257b1d5054a","sha256:8e027e09b2f775fdd7823c09e3279d74b3d76d1607fa14083ea09714681de91c"],"state_sha256":"810872545cdcb7af5c3b9060278b1b83b95758e3eb75871d7d07501881b3cb7a"}