{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NA3GQARVTYUEWURULHY7T272CM","short_pith_number":"pith:NA3GQARV","schema_version":"1.0","canonical_sha256":"68366802359e284b523459f1f9ebfa132c1349a2524cf4442749f2586e0c79dd","source":{"kind":"arxiv","id":"2408.06643","version":2},"attestation_state":"computed","paper":{"title":"BMX: Entropy-weighted Similarity and Semantic-enhanced Lexical Search","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Aamir Shakir, Jing Li, Julius Lipp, Rui Huang, Xianming Li","submitted_at":"2024-08-13T05:27:22Z","abstract_excerpt":"BM25, a widely-used lexical search algorithm, remains crucial in information retrieval despite the rise of pre-trained and large language models (PLMs/LLMs). However, it neglects query-document similarity and lacks semantic understanding, limiting its performance. We revisit BM25 and introduce BMX, a novel extension of BM25 incorporating entropy-weighted similarity and semantic enhancement techniques. Extensive experiments demonstrate that BMX consistently outperforms traditional BM25 and surpasses PLM/LLM-based dense retrieval in long-context and real-world retrieval benchmarks. This study br"},"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":"2408.06643","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-13T05:27:22Z","cross_cats_sorted":[],"title_canon_sha256":"fc1461a228957135f415d5bfdcca23cc6b3dd5548261e97fbe62e656fa4edcca","abstract_canon_sha256":"061b267b48efcf52250580ac8ce2a0dc2a9d674b938265b3c3a772e08bba75cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:10.232712Z","signature_b64":"oXIqVL1QmYsB323vjBrGvGQ2Tsy6zhQ8HobL9bdYFIDpV+pKZ/LYOd78ibT3/s6yagjSIEOWbyfbQeObuDs7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68366802359e284b523459f1f9ebfa132c1349a2524cf4442749f2586e0c79dd","last_reissued_at":"2026-07-05T08:55:10.232243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:10.232243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BMX: Entropy-weighted Similarity and Semantic-enhanced Lexical Search","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Aamir Shakir, Jing Li, Julius Lipp, Rui Huang, Xianming Li","submitted_at":"2024-08-13T05:27:22Z","abstract_excerpt":"BM25, a widely-used lexical search algorithm, remains crucial in information retrieval despite the rise of pre-trained and large language models (PLMs/LLMs). However, it neglects query-document similarity and lacks semantic understanding, limiting its performance. We revisit BM25 and introduce BMX, a novel extension of BM25 incorporating entropy-weighted similarity and semantic enhancement techniques. Extensive experiments demonstrate that BMX consistently outperforms traditional BM25 and surpasses PLM/LLM-based dense retrieval in long-context and real-world retrieval benchmarks. This study br"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06643","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/2408.06643/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":"2408.06643","created_at":"2026-07-05T08:55:10.232293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.06643v2","created_at":"2026-07-05T08:55:10.232293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06643","created_at":"2026-07-05T08:55:10.232293+00:00"},{"alias_kind":"pith_short_12","alias_value":"NA3GQARVTYUE","created_at":"2026-07-05T08:55:10.232293+00:00"},{"alias_kind":"pith_short_16","alias_value":"NA3GQARVTYUEWURU","created_at":"2026-07-05T08:55:10.232293+00:00"},{"alias_kind":"pith_short_8","alias_value":"NA3GQARV","created_at":"2026-07-05T08:55:10.232293+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.05257","citing_title":"Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NA3GQARVTYUEWURULHY7T272CM","json":"https://pith.science/pith/NA3GQARVTYUEWURULHY7T272CM.json","graph_json":"https://pith.science/api/pith-number/NA3GQARVTYUEWURULHY7T272CM/graph.json","events_json":"https://pith.science/api/pith-number/NA3GQARVTYUEWURULHY7T272CM/events.json","paper":"https://pith.science/paper/NA3GQARV"},"agent_actions":{"view_html":"https://pith.science/pith/NA3GQARVTYUEWURULHY7T272CM","download_json":"https://pith.science/pith/NA3GQARVTYUEWURULHY7T272CM.json","view_paper":"https://pith.science/paper/NA3GQARV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.06643&json=true","fetch_graph":"https://pith.science/api/pith-number/NA3GQARVTYUEWURULHY7T272CM/graph.json","fetch_events":"https://pith.science/api/pith-number/NA3GQARVTYUEWURULHY7T272CM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NA3GQARVTYUEWURULHY7T272CM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NA3GQARVTYUEWURULHY7T272CM/action/storage_attestation","attest_author":"https://pith.science/pith/NA3GQARVTYUEWURULHY7T272CM/action/author_attestation","sign_citation":"https://pith.science/pith/NA3GQARVTYUEWURULHY7T272CM/action/citation_signature","submit_replication":"https://pith.science/pith/NA3GQARVTYUEWURULHY7T272CM/action/replication_record"}},"created_at":"2026-07-05T08:55:10.232293+00:00","updated_at":"2026-07-05T08:55:10.232293+00:00"}