{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NA3GQARVTYUEWURULHY7T272CM","short_pith_number":"pith:NA3GQARV","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"},"canonical_sha256":"68366802359e284b523459f1f9ebfa132c1349a2524cf4442749f2586e0c79dd","source":{"kind":"arxiv","id":"2408.06643","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06643","created_at":"2026-07-05T08:55:10Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06643v2","created_at":"2026-07-05T08:55:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06643","created_at":"2026-07-05T08:55:10Z"},{"alias_kind":"pith_short_12","alias_value":"NA3GQARVTYUE","created_at":"2026-07-05T08:55:10Z"},{"alias_kind":"pith_short_16","alias_value":"NA3GQARVTYUEWURU","created_at":"2026-07-05T08:55:10Z"},{"alias_kind":"pith_short_8","alias_value":"NA3GQARV","created_at":"2026-07-05T08:55:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NA3GQARVTYUEWURULHY7T272CM","target":"record","payload":{"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"},"canonical_sha256":"68366802359e284b523459f1f9ebfa132c1349a2524cf4442749f2586e0c79dd","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"},"source_kind":"arxiv","source_id":"2408.06643","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:55:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yDz1T1JRQgccCPBq5GcyQ0sTeK39rKXmSjQu/VRFKEf2vPV7DhgWg2mxlDJQ81iiBvTGIOnz6lt5RZOjd7IWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:23:15.740476Z"},"content_sha256":"af88667ca4d1d61fb98e556d6793e44061c21b64581d50181242d7758d4d8a85","schema_version":"1.0","event_id":"sha256:af88667ca4d1d61fb98e556d6793e44061c21b64581d50181242d7758d4d8a85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NA3GQARVTYUEWURULHY7T272CM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:55:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hl6zrmiuhx9cq0ph7+wyVvaLXb/h0zfu/EtC80hfGt0Vj1WZe9nAksme9El/VMvnWYNj5pbJIl27I2hRM9pdDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:23:15.741017Z"},"content_sha256":"e4381ecba59701f4222dec87fb0072aa038b9a3e95f37a65c07a05ece988f194","schema_version":"1.0","event_id":"sha256:e4381ecba59701f4222dec87fb0072aa038b9a3e95f37a65c07a05ece988f194"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NA3GQARVTYUEWURULHY7T272CM/bundle.json","state_url":"https://pith.science/pith/NA3GQARVTYUEWURULHY7T272CM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NA3GQARVTYUEWURULHY7T272CM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T18:23:15Z","links":{"resolver":"https://pith.science/pith/NA3GQARVTYUEWURULHY7T272CM","bundle":"https://pith.science/pith/NA3GQARVTYUEWURULHY7T272CM/bundle.json","state":"https://pith.science/pith/NA3GQARVTYUEWURULHY7T272CM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NA3GQARVTYUEWURULHY7T272CM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NA3GQARVTYUEWURULHY7T272CM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"061b267b48efcf52250580ac8ce2a0dc2a9d674b938265b3c3a772e08bba75cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-13T05:27:22Z","title_canon_sha256":"fc1461a228957135f415d5bfdcca23cc6b3dd5548261e97fbe62e656fa4edcca"},"schema_version":"1.0","source":{"id":"2408.06643","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06643","created_at":"2026-07-05T08:55:10Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06643v2","created_at":"2026-07-05T08:55:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06643","created_at":"2026-07-05T08:55:10Z"},{"alias_kind":"pith_short_12","alias_value":"NA3GQARVTYUE","created_at":"2026-07-05T08:55:10Z"},{"alias_kind":"pith_short_16","alias_value":"NA3GQARVTYUEWURU","created_at":"2026-07-05T08:55:10Z"},{"alias_kind":"pith_short_8","alias_value":"NA3GQARV","created_at":"2026-07-05T08:55:10Z"}],"graph_snapshots":[{"event_id":"sha256:e4381ecba59701f4222dec87fb0072aa038b9a3e95f37a65c07a05ece988f194","target":"graph","created_at":"2026-07-05T08:55:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2408.06643/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aamir Shakir, Jing Li, Julius Lipp, Rui Huang, Xianming Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-13T05:27:22Z","title":"BMX: Entropy-weighted Similarity and Semantic-enhanced Lexical Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06643","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:af88667ca4d1d61fb98e556d6793e44061c21b64581d50181242d7758d4d8a85","target":"record","created_at":"2026-07-05T08:55:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"061b267b48efcf52250580ac8ce2a0dc2a9d674b938265b3c3a772e08bba75cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-13T05:27:22Z","title_canon_sha256":"fc1461a228957135f415d5bfdcca23cc6b3dd5548261e97fbe62e656fa4edcca"},"schema_version":"1.0","source":{"id":"2408.06643","kind":"arxiv","version":2}},"canonical_sha256":"68366802359e284b523459f1f9ebfa132c1349a2524cf4442749f2586e0c79dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68366802359e284b523459f1f9ebfa132c1349a2524cf4442749f2586e0c79dd","first_computed_at":"2026-07-05T08:55:10.232243Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:10.232243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oXIqVL1QmYsB323vjBrGvGQ2Tsy6zhQ8HobL9bdYFIDpV+pKZ/LYOd78ibT3/s6yagjSIEOWbyfbQeObuDs7Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:10.232712Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.06643","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af88667ca4d1d61fb98e556d6793e44061c21b64581d50181242d7758d4d8a85","sha256:e4381ecba59701f4222dec87fb0072aa038b9a3e95f37a65c07a05ece988f194"],"state_sha256":"8ff8ac4ba546c15c6edc7ac4de1f8852eec13dcd6ed874a1a329be07ccab8d22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZtH3q8cs5RfGdC4vOSIHTZtM3KQLUMXzVkcS7eoS+jSjEe9LKhJyM5QHzlPg8gNCUbva40n4gWQsRXYZSWLJDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T18:23:15.745793Z","bundle_sha256":"1e70eeebe536f49a9e849b496d20f81cb890ee87c9260196f59b16c7a31c1018"}}