{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KIQL3NVURF6TW3GMUTOL4YOJA5","short_pith_number":"pith:KIQL3NVU","schema_version":"1.0","canonical_sha256":"5220bdb6b4897d3b6ccca4dcbe61c90771981b41a4160ef8f15a4efb49ef1607","source":{"kind":"arxiv","id":"2505.12306","version":1},"attestation_state":"computed","paper":{"title":"Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gaowen Liu, Jayanth Srinivasa, Jingbo Shang, Letian Peng, Shangbin Feng, Wenhao Yu, Yifan Zhu, Yuwei Zhang","submitted_at":"2025-05-18T08:39:05Z","abstract_excerpt":"Despite significant advances in large language models (LLMs), their knowledge memorization capabilities remain underexplored, due to the lack of standardized and high-quality test ground. In this paper, we introduce a novel, real-world and large-scale knowledge injection benchmark that evolves continuously over time without requiring human intervention. Specifically, we propose WikiDYK, which leverages recently-added and human-written facts from Wikipedia's \"Did You Know...\" entries. These entries are carefully selected by expert Wikipedia editors based on criteria such as verifiability and cl"},"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":"2505.12306","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T08:39:05Z","cross_cats_sorted":[],"title_canon_sha256":"114011a32d615885c7fbab59d64790a1c95552bf3d56b6ec843ab56dbab97306","abstract_canon_sha256":"3b6f55af76390ddbf196258de3a5bb1db3945147ae7a9616762181efa2fc4264"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:01.945896Z","signature_b64":"cLKy5Blwwj917fnXnXKaDJCDRb65wz655jwS8TecSx0N+A9xoqzBGZtm1485l3rWYWUDcGr6GkVzmUZUZ7THCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5220bdb6b4897d3b6ccca4dcbe61c90771981b41a4160ef8f15a4efb49ef1607","last_reissued_at":"2026-07-05T11:05:01.945356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:01.945356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gaowen Liu, Jayanth Srinivasa, Jingbo Shang, Letian Peng, Shangbin Feng, Wenhao Yu, Yifan Zhu, Yuwei Zhang","submitted_at":"2025-05-18T08:39:05Z","abstract_excerpt":"Despite significant advances in large language models (LLMs), their knowledge memorization capabilities remain underexplored, due to the lack of standardized and high-quality test ground. In this paper, we introduce a novel, real-world and large-scale knowledge injection benchmark that evolves continuously over time without requiring human intervention. Specifically, we propose WikiDYK, which leverages recently-added and human-written facts from Wikipedia's \"Did You Know...\" entries. These entries are carefully selected by expert Wikipedia editors based on criteria such as verifiability and cl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12306","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/2505.12306/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":"2505.12306","created_at":"2026-07-05T11:05:01.945419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12306v1","created_at":"2026-07-05T11:05:01.945419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12306","created_at":"2026-07-05T11:05:01.945419+00:00"},{"alias_kind":"pith_short_12","alias_value":"KIQL3NVURF6T","created_at":"2026-07-05T11:05:01.945419+00:00"},{"alias_kind":"pith_short_16","alias_value":"KIQL3NVURF6TW3GM","created_at":"2026-07-05T11:05:01.945419+00:00"},{"alias_kind":"pith_short_8","alias_value":"KIQL3NVU","created_at":"2026-07-05T11:05:01.945419+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07812","citing_title":"Scaling Participation in Modular AI Systems","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21257","citing_title":"MoCo: A One-Stop Shop for Model Collaboration Research","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KIQL3NVURF6TW3GMUTOL4YOJA5","json":"https://pith.science/pith/KIQL3NVURF6TW3GMUTOL4YOJA5.json","graph_json":"https://pith.science/api/pith-number/KIQL3NVURF6TW3GMUTOL4YOJA5/graph.json","events_json":"https://pith.science/api/pith-number/KIQL3NVURF6TW3GMUTOL4YOJA5/events.json","paper":"https://pith.science/paper/KIQL3NVU"},"agent_actions":{"view_html":"https://pith.science/pith/KIQL3NVURF6TW3GMUTOL4YOJA5","download_json":"https://pith.science/pith/KIQL3NVURF6TW3GMUTOL4YOJA5.json","view_paper":"https://pith.science/paper/KIQL3NVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12306&json=true","fetch_graph":"https://pith.science/api/pith-number/KIQL3NVURF6TW3GMUTOL4YOJA5/graph.json","fetch_events":"https://pith.science/api/pith-number/KIQL3NVURF6TW3GMUTOL4YOJA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KIQL3NVURF6TW3GMUTOL4YOJA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KIQL3NVURF6TW3GMUTOL4YOJA5/action/storage_attestation","attest_author":"https://pith.science/pith/KIQL3NVURF6TW3GMUTOL4YOJA5/action/author_attestation","sign_citation":"https://pith.science/pith/KIQL3NVURF6TW3GMUTOL4YOJA5/action/citation_signature","submit_replication":"https://pith.science/pith/KIQL3NVURF6TW3GMUTOL4YOJA5/action/replication_record"}},"created_at":"2026-07-05T11:05:01.945419+00:00","updated_at":"2026-07-05T11:05:01.945419+00:00"}