{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WKHV2PSYHOSITMNGVLMSAHF2QN","short_pith_number":"pith:WKHV2PSY","schema_version":"1.0","canonical_sha256":"b28f5d3e583ba489b1a6aad9201cba83640cdba9007a6a1adaa5d8dc6d49ed10","source":{"kind":"arxiv","id":"2410.20050","version":2},"attestation_state":"computed","paper":{"title":"AutoMIR: Effective Zero-Shot Medical Information Retrieval without Relevance Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Lei Li, Xiangxu Zhang, Xiao Zhou, Zheng Liu","submitted_at":"2024-10-26T02:53:20Z","abstract_excerpt":"Medical information retrieval (MIR) is essential for retrieving relevant medical knowledge from diverse sources, including electronic health records, scientific literature, and medical databases. However, achieving effective zero-shot dense retrieval in the medical domain poses substantial challenges due to the lack of relevance-labeled data. In this paper, we introduce a novel approach called \\textbf{S}elf-\\textbf{L}earning \\textbf{Hy}pothetical \\textbf{D}ocument \\textbf{E}mbeddings (\\textbf{SL-HyDE}) to tackle this issue. SL-HyDE leverages large language models (LLMs) as generators to genera"},"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":"2410.20050","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-10-26T02:53:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"32e13200598ca1a6936562028e171ae5560ee30f58117b7453168921f3c66bc8","abstract_canon_sha256":"bdf735886de71e995a650b26ca53798001d6c605118fbf03b0c67811830fc5b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:43.693076Z","signature_b64":"fi++Q2y5p13Fv7RUM56f34xXFcDkEQC0W7ypKXMNYgQ8TPkkHIAp/WTO3QT1GHdsxcnLvtqAMJqHJxrEd0+pCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b28f5d3e583ba489b1a6aad9201cba83640cdba9007a6a1adaa5d8dc6d49ed10","last_reissued_at":"2026-07-05T11:09:43.692588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:43.692588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoMIR: Effective Zero-Shot Medical Information Retrieval without Relevance Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Lei Li, Xiangxu Zhang, Xiao Zhou, Zheng Liu","submitted_at":"2024-10-26T02:53:20Z","abstract_excerpt":"Medical information retrieval (MIR) is essential for retrieving relevant medical knowledge from diverse sources, including electronic health records, scientific literature, and medical databases. However, achieving effective zero-shot dense retrieval in the medical domain poses substantial challenges due to the lack of relevance-labeled data. In this paper, we introduce a novel approach called \\textbf{S}elf-\\textbf{L}earning \\textbf{Hy}pothetical \\textbf{D}ocument \\textbf{E}mbeddings (\\textbf{SL-HyDE}) to tackle this issue. SL-HyDE leverages large language models (LLMs) as generators to genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20050","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/2410.20050/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":"2410.20050","created_at":"2026-07-05T11:09:43.692647+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20050v2","created_at":"2026-07-05T11:09:43.692647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20050","created_at":"2026-07-05T11:09:43.692647+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKHV2PSYHOSI","created_at":"2026-07-05T11:09:43.692647+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKHV2PSYHOSITMNG","created_at":"2026-07-05T11:09:43.692647+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKHV2PSY","created_at":"2026-07-05T11:09:43.692647+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.14558","citing_title":"R2MED: A Benchmark for Reasoning-Driven Medical Retrieval","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WKHV2PSYHOSITMNGVLMSAHF2QN","json":"https://pith.science/pith/WKHV2PSYHOSITMNGVLMSAHF2QN.json","graph_json":"https://pith.science/api/pith-number/WKHV2PSYHOSITMNGVLMSAHF2QN/graph.json","events_json":"https://pith.science/api/pith-number/WKHV2PSYHOSITMNGVLMSAHF2QN/events.json","paper":"https://pith.science/paper/WKHV2PSY"},"agent_actions":{"view_html":"https://pith.science/pith/WKHV2PSYHOSITMNGVLMSAHF2QN","download_json":"https://pith.science/pith/WKHV2PSYHOSITMNGVLMSAHF2QN.json","view_paper":"https://pith.science/paper/WKHV2PSY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20050&json=true","fetch_graph":"https://pith.science/api/pith-number/WKHV2PSYHOSITMNGVLMSAHF2QN/graph.json","fetch_events":"https://pith.science/api/pith-number/WKHV2PSYHOSITMNGVLMSAHF2QN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKHV2PSYHOSITMNGVLMSAHF2QN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKHV2PSYHOSITMNGVLMSAHF2QN/action/storage_attestation","attest_author":"https://pith.science/pith/WKHV2PSYHOSITMNGVLMSAHF2QN/action/author_attestation","sign_citation":"https://pith.science/pith/WKHV2PSYHOSITMNGVLMSAHF2QN/action/citation_signature","submit_replication":"https://pith.science/pith/WKHV2PSYHOSITMNGVLMSAHF2QN/action/replication_record"}},"created_at":"2026-07-05T11:09:43.692647+00:00","updated_at":"2026-07-05T11:09:43.692647+00:00"}