{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IQRVI5KDMJ46Q46E5CHMGFB2IU","short_pith_number":"pith:IQRVI5KD","schema_version":"1.0","canonical_sha256":"44235475436279e873c4e88ec3143a45341cb01c2559b31cdd3ebf38e298cd69","source":{"kind":"arxiv","id":"2402.12352","version":1},"attestation_state":"computed","paper":{"title":"Graph-Based Retriever Captures the Long Tail of Biomedical Knowledge","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Anton Van Pamel, Julien Delile, Leonid Zhukov, Srayanta Mukherjee","submitted_at":"2024-02-19T18:31:11Z","abstract_excerpt":"Large language models (LLMs) are transforming the way information is retrieved with vast amounts of knowledge being summarized and presented via natural language conversations. Yet, LLMs are prone to highlight the most frequently seen pieces of information from the training set and to neglect the rare ones. In the field of biomedical research, latest discoveries are key to academic and industrial actors and are obscured by the abundance of an ever-increasing literature corpus (the information overload problem). Surfacing new associations between biomedical entities, e.g., drugs, genes, disease"},"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":"2402.12352","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T18:31:11Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"abb454479175f02582fde5589822ce399fa47c27d78ba023379bb1f80e647835","abstract_canon_sha256":"384a6d97b3cf9eca25468ccb99ea0f7a1f1dc48e4a1b018647e68ba379aa76ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:52.265708Z","signature_b64":"mp2oSmPnEOpgpq95plk51mWuRNXJ+SJi8IZsFuO4Ljm7EhKMpgOI6/Mbndzk0e+Kc+pCCa+eE4yDvcRRvtLIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44235475436279e873c4e88ec3143a45341cb01c2559b31cdd3ebf38e298cd69","last_reissued_at":"2026-07-05T07:46:52.265297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:52.265297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph-Based Retriever Captures the Long Tail of Biomedical Knowledge","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Anton Van Pamel, Julien Delile, Leonid Zhukov, Srayanta Mukherjee","submitted_at":"2024-02-19T18:31:11Z","abstract_excerpt":"Large language models (LLMs) are transforming the way information is retrieved with vast amounts of knowledge being summarized and presented via natural language conversations. Yet, LLMs are prone to highlight the most frequently seen pieces of information from the training set and to neglect the rare ones. In the field of biomedical research, latest discoveries are key to academic and industrial actors and are obscured by the abundance of an ever-increasing literature corpus (the information overload problem). Surfacing new associations between biomedical entities, e.g., drugs, genes, disease"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12352","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/2402.12352/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":"2402.12352","created_at":"2026-07-05T07:46:52.265371+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12352v1","created_at":"2026-07-05T07:46:52.265371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12352","created_at":"2026-07-05T07:46:52.265371+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQRVI5KDMJ46","created_at":"2026-07-05T07:46:52.265371+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQRVI5KDMJ46Q46E","created_at":"2026-07-05T07:46:52.265371+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQRVI5KD","created_at":"2026-07-05T07:46:52.265371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":78,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IQRVI5KDMJ46Q46E5CHMGFB2IU","json":"https://pith.science/pith/IQRVI5KDMJ46Q46E5CHMGFB2IU.json","graph_json":"https://pith.science/api/pith-number/IQRVI5KDMJ46Q46E5CHMGFB2IU/graph.json","events_json":"https://pith.science/api/pith-number/IQRVI5KDMJ46Q46E5CHMGFB2IU/events.json","paper":"https://pith.science/paper/IQRVI5KD"},"agent_actions":{"view_html":"https://pith.science/pith/IQRVI5KDMJ46Q46E5CHMGFB2IU","download_json":"https://pith.science/pith/IQRVI5KDMJ46Q46E5CHMGFB2IU.json","view_paper":"https://pith.science/paper/IQRVI5KD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12352&json=true","fetch_graph":"https://pith.science/api/pith-number/IQRVI5KDMJ46Q46E5CHMGFB2IU/graph.json","fetch_events":"https://pith.science/api/pith-number/IQRVI5KDMJ46Q46E5CHMGFB2IU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQRVI5KDMJ46Q46E5CHMGFB2IU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQRVI5KDMJ46Q46E5CHMGFB2IU/action/storage_attestation","attest_author":"https://pith.science/pith/IQRVI5KDMJ46Q46E5CHMGFB2IU/action/author_attestation","sign_citation":"https://pith.science/pith/IQRVI5KDMJ46Q46E5CHMGFB2IU/action/citation_signature","submit_replication":"https://pith.science/pith/IQRVI5KDMJ46Q46E5CHMGFB2IU/action/replication_record"}},"created_at":"2026-07-05T07:46:52.265371+00:00","updated_at":"2026-07-05T07:46:52.265371+00:00"}