{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KM5YXNLUJQS6RSOQUTPU2ZFG6U","short_pith_number":"pith:KM5YXNLU","schema_version":"1.0","canonical_sha256":"533b8bb5744c25e8c9d0a4df4d64a6f5333a4ec43dae3732a8bb6c28dc9ff6ea","source":{"kind":"arxiv","id":"2606.22783","version":1},"attestation_state":"computed","paper":{"title":"Breaking the Evaluation Paradox: Evaluating High-Entropy Search with Computationally Irreducible Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Juntao Wu, Ke Wang, Ruizhi Qiao, Shuai Pang, Wei Wen, Xianting Huang, Xing Sun","submitted_at":"2026-06-22T02:45:01Z","abstract_excerpt":"Evaluating the exhaustive search capabilities of large language models (LLMs) is plagued by a fundamental paradox: verifying completeness requires complete ground truth, yet high-entropy enumeration tasks make such ground truth impossible for humans to create. This causes benchmarks to systematically penalize models for outperforming their human annotators. Despite rapid progress in web-search and deep research agents -- which now issue hundreds of queries, traverse diverse sites, and synthesize long reports -- evaluation still largely relies on partially annotated answer sets, LLM-based judge"},"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":"2606.22783","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-22T02:45:01Z","cross_cats_sorted":[],"title_canon_sha256":"e64ac311b02bbdf7bc294909a039d632a62f2971ad6583cb92efc16b30a8e29a","abstract_canon_sha256":"ba5769e8625109101590cd839b78154c2bb8a90d017253a686310e8f107267e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:54.425907Z","signature_b64":"HbkRCDWBRkzGItS4KDkBB8x2b9/LTMOcU+62OfIUil2Z+5WaxL/z7STIEgbLkRcie/8peXCm5jdrVEm0hdDzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"533b8bb5744c25e8c9d0a4df4d64a6f5333a4ec43dae3732a8bb6c28dc9ff6ea","last_reissued_at":"2026-06-23T02:13:54.425504Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:54.425504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Breaking the Evaluation Paradox: Evaluating High-Entropy Search with Computationally Irreducible Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Juntao Wu, Ke Wang, Ruizhi Qiao, Shuai Pang, Wei Wen, Xianting Huang, Xing Sun","submitted_at":"2026-06-22T02:45:01Z","abstract_excerpt":"Evaluating the exhaustive search capabilities of large language models (LLMs) is plagued by a fundamental paradox: verifying completeness requires complete ground truth, yet high-entropy enumeration tasks make such ground truth impossible for humans to create. This causes benchmarks to systematically penalize models for outperforming their human annotators. Despite rapid progress in web-search and deep research agents -- which now issue hundreds of queries, traverse diverse sites, and synthesize long reports -- evaluation still largely relies on partially annotated answer sets, LLM-based judge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22783","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/2606.22783/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":"2606.22783","created_at":"2026-06-23T02:13:54.425567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22783v1","created_at":"2026-06-23T02:13:54.425567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22783","created_at":"2026-06-23T02:13:54.425567+00:00"},{"alias_kind":"pith_short_12","alias_value":"KM5YXNLUJQS6","created_at":"2026-06-23T02:13:54.425567+00:00"},{"alias_kind":"pith_short_16","alias_value":"KM5YXNLUJQS6RSOQ","created_at":"2026-06-23T02:13:54.425567+00:00"},{"alias_kind":"pith_short_8","alias_value":"KM5YXNLU","created_at":"2026-06-23T02:13:54.425567+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KM5YXNLUJQS6RSOQUTPU2ZFG6U","json":"https://pith.science/pith/KM5YXNLUJQS6RSOQUTPU2ZFG6U.json","graph_json":"https://pith.science/api/pith-number/KM5YXNLUJQS6RSOQUTPU2ZFG6U/graph.json","events_json":"https://pith.science/api/pith-number/KM5YXNLUJQS6RSOQUTPU2ZFG6U/events.json","paper":"https://pith.science/paper/KM5YXNLU"},"agent_actions":{"view_html":"https://pith.science/pith/KM5YXNLUJQS6RSOQUTPU2ZFG6U","download_json":"https://pith.science/pith/KM5YXNLUJQS6RSOQUTPU2ZFG6U.json","view_paper":"https://pith.science/paper/KM5YXNLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22783&json=true","fetch_graph":"https://pith.science/api/pith-number/KM5YXNLUJQS6RSOQUTPU2ZFG6U/graph.json","fetch_events":"https://pith.science/api/pith-number/KM5YXNLUJQS6RSOQUTPU2ZFG6U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KM5YXNLUJQS6RSOQUTPU2ZFG6U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KM5YXNLUJQS6RSOQUTPU2ZFG6U/action/storage_attestation","attest_author":"https://pith.science/pith/KM5YXNLUJQS6RSOQUTPU2ZFG6U/action/author_attestation","sign_citation":"https://pith.science/pith/KM5YXNLUJQS6RSOQUTPU2ZFG6U/action/citation_signature","submit_replication":"https://pith.science/pith/KM5YXNLUJQS6RSOQUTPU2ZFG6U/action/replication_record"}},"created_at":"2026-06-23T02:13:54.425567+00:00","updated_at":"2026-06-23T02:13:54.425567+00:00"}