{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q5BTZPWDQNGJGPX7NZZWK5EXOJ","short_pith_number":"pith:Q5BTZPWD","schema_version":"1.0","canonical_sha256":"87433cbec3834c933eff6e73657497724ebaef3d3f18a604846bdfb61a93ca73","source":{"kind":"arxiv","id":"2401.12689","version":3},"attestation_state":"computed","paper":{"title":"Energy-based Automated Model Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Haobo Wang, Heming Zou, Junbo Zhao, Ru Peng, Yawen Zeng, Zenan Huang","submitted_at":"2024-01-23T11:54:09Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.12689","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-23T11:54:09Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"6f604c437e7dd292ccb0b8f304979d272814250b6d220c59885f0f237847f431","abstract_canon_sha256":"b7ddcbf1d5febd1b4d868122820ab6e7f6da7d495a07f8a3dd8f1f5337d835a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:20.555873Z","signature_b64":"X1OVAL3emti/PvX0bQ67kX66x5o7A5S3qbSA1tVURlTWHShXlX3Tj5uo6w9fhjzU91atp1G01OQdK0xTgqazAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87433cbec3834c933eff6e73657497724ebaef3d3f18a604846bdfb61a93ca73","last_reissued_at":"2026-07-05T07:56:20.555360Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:20.555360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Energy-based Automated Model Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Haobo Wang, Heming Zou, Junbo Zhao, Ru Peng, Yawen Zeng, Zenan Huang","submitted_at":"2024-01-23T11:54:09Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12689","kind":"arxiv","version":3},"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/2401.12689/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.12689","created_at":"2026-07-05T07:56:20.555424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.12689v3","created_at":"2026-07-05T07:56:20.555424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12689","created_at":"2026-07-05T07:56:20.555424+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5BTZPWDQNGJ","created_at":"2026-07-05T07:56:20.555424+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5BTZPWDQNGJGPX7","created_at":"2026-07-05T07:56:20.555424+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5BTZPWD","created_at":"2026-07-05T07:56:20.555424+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07023","citing_title":"Online Data Selection Is Implicit Alignment","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08192","citing_title":"Inside-Out: Measuring Generalization in Vision Transformers Through Inner Workings","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q5BTZPWDQNGJGPX7NZZWK5EXOJ","json":"https://pith.science/pith/Q5BTZPWDQNGJGPX7NZZWK5EXOJ.json","graph_json":"https://pith.science/api/pith-number/Q5BTZPWDQNGJGPX7NZZWK5EXOJ/graph.json","events_json":"https://pith.science/api/pith-number/Q5BTZPWDQNGJGPX7NZZWK5EXOJ/events.json","paper":"https://pith.science/paper/Q5BTZPWD"},"agent_actions":{"view_html":"https://pith.science/pith/Q5BTZPWDQNGJGPX7NZZWK5EXOJ","download_json":"https://pith.science/pith/Q5BTZPWDQNGJGPX7NZZWK5EXOJ.json","view_paper":"https://pith.science/paper/Q5BTZPWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.12689&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5BTZPWDQNGJGPX7NZZWK5EXOJ/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5BTZPWDQNGJGPX7NZZWK5EXOJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5BTZPWDQNGJGPX7NZZWK5EXOJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5BTZPWDQNGJGPX7NZZWK5EXOJ/action/storage_attestation","attest_author":"https://pith.science/pith/Q5BTZPWDQNGJGPX7NZZWK5EXOJ/action/author_attestation","sign_citation":"https://pith.science/pith/Q5BTZPWDQNGJGPX7NZZWK5EXOJ/action/citation_signature","submit_replication":"https://pith.science/pith/Q5BTZPWDQNGJGPX7NZZWK5EXOJ/action/replication_record"}},"created_at":"2026-07-05T07:56:20.555424+00:00","updated_at":"2026-07-05T07:56:20.555424+00:00"}