{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VNBMUBUPH7TE7REFVFHWYXPSNU","short_pith_number":"pith:VNBMUBUP","schema_version":"1.0","canonical_sha256":"ab42ca068f3fe64fc485a94f6c5df26d0c86ff4cd683fdba082a69fbdd0e6a8c","source":{"kind":"arxiv","id":"2602.14080","version":2},"attestation_state":"computed","paper":{"title":"Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric Factuality","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eran Ofek, Eyal Ben-David, Gal Yona, Nitay Calderon, Zorik Gekhman","submitted_at":"2026-02-15T10:13:30Z","abstract_excerpt":"Standard factuality evaluations of LLMs treat all errors alike, obscuring whether failures arise from missing knowledge (empty shelves) or from limited access to encoded facts (lost keys). We propose a behavioral framework that profiles factual knowledge at the level of facts rather than questions, characterizing each fact by whether it is encoded, and then by how accessible it is: cannot be recalled, can be directly recalled, or can only be recalled with inference-time computation (thinking). To support such profiling, we introduce WikiProfile, a new benchmark constructed via an automated pip"},"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":"2602.14080","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-15T10:13:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"731bf968e5b754e38b9bf93ecb4c54eca0146cc1057de9408281e12813f073e1","abstract_canon_sha256":"11bd1f62fcb2953ec5a3372bd972726df927cdb71a37dddbd4f8e664364daf05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:13:03.697808Z","signature_b64":"bKETBq2ZcaxyRiyt8ZsqWLa+Msc3UP9FLSP9uQkHcTOOqoJPmqpD60PsaD6Q3qSGox5tzqtqgMRy08WsP4akAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab42ca068f3fe64fc485a94f6c5df26d0c86ff4cd683fdba082a69fbdd0e6a8c","last_reissued_at":"2026-06-23T01:13:03.697192Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:13:03.697192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric Factuality","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eran Ofek, Eyal Ben-David, Gal Yona, Nitay Calderon, Zorik Gekhman","submitted_at":"2026-02-15T10:13:30Z","abstract_excerpt":"Standard factuality evaluations of LLMs treat all errors alike, obscuring whether failures arise from missing knowledge (empty shelves) or from limited access to encoded facts (lost keys). We propose a behavioral framework that profiles factual knowledge at the level of facts rather than questions, characterizing each fact by whether it is encoded, and then by how accessible it is: cannot be recalled, can be directly recalled, or can only be recalled with inference-time computation (thinking). To support such profiling, we introduce WikiProfile, a new benchmark constructed via an automated pip"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.14080","kind":"arxiv","version":2},"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/2602.14080/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":"2602.14080","created_at":"2026-06-23T01:13:03.697269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.14080v2","created_at":"2026-06-23T01:13:03.697269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.14080","created_at":"2026-06-23T01:13:03.697269+00:00"},{"alias_kind":"pith_short_12","alias_value":"VNBMUBUPH7TE","created_at":"2026-06-23T01:13:03.697269+00:00"},{"alias_kind":"pith_short_16","alias_value":"VNBMUBUPH7TE7REF","created_at":"2026-06-23T01:13:03.697269+00:00"},{"alias_kind":"pith_short_8","alias_value":"VNBMUBUP","created_at":"2026-06-23T01:13:03.697269+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.22007","citing_title":"Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VNBMUBUPH7TE7REFVFHWYXPSNU","json":"https://pith.science/pith/VNBMUBUPH7TE7REFVFHWYXPSNU.json","graph_json":"https://pith.science/api/pith-number/VNBMUBUPH7TE7REFVFHWYXPSNU/graph.json","events_json":"https://pith.science/api/pith-number/VNBMUBUPH7TE7REFVFHWYXPSNU/events.json","paper":"https://pith.science/paper/VNBMUBUP"},"agent_actions":{"view_html":"https://pith.science/pith/VNBMUBUPH7TE7REFVFHWYXPSNU","download_json":"https://pith.science/pith/VNBMUBUPH7TE7REFVFHWYXPSNU.json","view_paper":"https://pith.science/paper/VNBMUBUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.14080&json=true","fetch_graph":"https://pith.science/api/pith-number/VNBMUBUPH7TE7REFVFHWYXPSNU/graph.json","fetch_events":"https://pith.science/api/pith-number/VNBMUBUPH7TE7REFVFHWYXPSNU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VNBMUBUPH7TE7REFVFHWYXPSNU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VNBMUBUPH7TE7REFVFHWYXPSNU/action/storage_attestation","attest_author":"https://pith.science/pith/VNBMUBUPH7TE7REFVFHWYXPSNU/action/author_attestation","sign_citation":"https://pith.science/pith/VNBMUBUPH7TE7REFVFHWYXPSNU/action/citation_signature","submit_replication":"https://pith.science/pith/VNBMUBUPH7TE7REFVFHWYXPSNU/action/replication_record"}},"created_at":"2026-06-23T01:13:03.697269+00:00","updated_at":"2026-06-23T01:13:03.697269+00:00"}