{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UETF4ATR2KA53GTMTDZWSTIEU3","short_pith_number":"pith:UETF4ATR","schema_version":"1.0","canonical_sha256":"a1265e0271d281dd9a6c98f3694d04a6e5adbc4d848cac33cbeb3719e70c198f","source":{"kind":"arxiv","id":"2606.26101","version":1},"attestation_state":"computed","paper":{"title":"Know2Guess: A Contamination-Aware Multi-Zone Benchmark for Knowledge-Boundary Evaluation in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bowen Zhang, Haoyi Wu, Jian Wang, Renwei Meng, Shengan Yang, Xican Wang, Xuanyan Qiu","submitted_at":"2026-04-30T05:46:01Z","abstract_excerpt":"Reliable evaluation of large language models should separate supported answering from unsupported guessing without conflating either with data contamination, prompt idiosyncrasy, or generic refusal behavior. We present a contamination-aware, multi-zone benchmark for measuring the transition from answerable knowledge to abstention-expected unknowns under frozen build-time labels. The benchmark contains 1,200 items across five domains, explicit abstention expectations, contamination-risk metadata, and dual parsing with an official strict parser plus a normalized robustness parser. We evaluate FL"},"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":"2606.26101","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-30T05:46:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"800a48d25adb77bf0a20d3c14ce3f8456bb618a0e5d69ec9b914796bec50b559","abstract_canon_sha256":"02477d102694fe73bd8e78efb04d378f252e84a8985c65c2644dd0c3ac71ef4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T00:15:26.301977Z","signature_b64":"o/vIZOrt0Qa52+hD7uInxOFZ5Omm1KoWaY+FKZ6JnBSzopv4ybFucy017MvxPF538NPIjtMze+jqDIFmwwjeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1265e0271d281dd9a6c98f3694d04a6e5adbc4d848cac33cbeb3719e70c198f","last_reissued_at":"2026-06-26T00:15:26.301438Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T00:15:26.301438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Know2Guess: A Contamination-Aware Multi-Zone Benchmark for Knowledge-Boundary Evaluation in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bowen Zhang, Haoyi Wu, Jian Wang, Renwei Meng, Shengan Yang, Xican Wang, Xuanyan Qiu","submitted_at":"2026-04-30T05:46:01Z","abstract_excerpt":"Reliable evaluation of large language models should separate supported answering from unsupported guessing without conflating either with data contamination, prompt idiosyncrasy, or generic refusal behavior. We present a contamination-aware, multi-zone benchmark for measuring the transition from answerable knowledge to abstention-expected unknowns under frozen build-time labels. The benchmark contains 1,200 items across five domains, explicit abstention expectations, contamination-risk metadata, and dual parsing with an official strict parser plus a normalized robustness parser. We evaluate FL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26101","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/2606.26101/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":"2606.26101","created_at":"2026-06-26T00:15:26.301494+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26101v1","created_at":"2026-06-26T00:15:26.301494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26101","created_at":"2026-06-26T00:15:26.301494+00:00"},{"alias_kind":"pith_short_12","alias_value":"UETF4ATR2KA5","created_at":"2026-06-26T00:15:26.301494+00:00"},{"alias_kind":"pith_short_16","alias_value":"UETF4ATR2KA53GTM","created_at":"2026-06-26T00:15:26.301494+00:00"},{"alias_kind":"pith_short_8","alias_value":"UETF4ATR","created_at":"2026-06-26T00:15:26.301494+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/UETF4ATR2KA53GTMTDZWSTIEU3","json":"https://pith.science/pith/UETF4ATR2KA53GTMTDZWSTIEU3.json","graph_json":"https://pith.science/api/pith-number/UETF4ATR2KA53GTMTDZWSTIEU3/graph.json","events_json":"https://pith.science/api/pith-number/UETF4ATR2KA53GTMTDZWSTIEU3/events.json","paper":"https://pith.science/paper/UETF4ATR"},"agent_actions":{"view_html":"https://pith.science/pith/UETF4ATR2KA53GTMTDZWSTIEU3","download_json":"https://pith.science/pith/UETF4ATR2KA53GTMTDZWSTIEU3.json","view_paper":"https://pith.science/paper/UETF4ATR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26101&json=true","fetch_graph":"https://pith.science/api/pith-number/UETF4ATR2KA53GTMTDZWSTIEU3/graph.json","fetch_events":"https://pith.science/api/pith-number/UETF4ATR2KA53GTMTDZWSTIEU3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UETF4ATR2KA53GTMTDZWSTIEU3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UETF4ATR2KA53GTMTDZWSTIEU3/action/storage_attestation","attest_author":"https://pith.science/pith/UETF4ATR2KA53GTMTDZWSTIEU3/action/author_attestation","sign_citation":"https://pith.science/pith/UETF4ATR2KA53GTMTDZWSTIEU3/action/citation_signature","submit_replication":"https://pith.science/pith/UETF4ATR2KA53GTMTDZWSTIEU3/action/replication_record"}},"created_at":"2026-06-26T00:15:26.301494+00:00","updated_at":"2026-06-26T00:15:26.301494+00:00"}