{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZKY56IMOBJE2ZZVRA3GFZJOIFA","short_pith_number":"pith:ZKY56IMO","schema_version":"1.0","canonical_sha256":"cab1df218e0a49ace6b106cc5ca5c8283c3877d90c4790f78c4c46c2ee6e5eb8","source":{"kind":"arxiv","id":"2605.18561","version":1},"attestation_state":"computed","paper":{"title":"Improving BM25 Code Retrieval Under Fixed Generic Tokenization: Adaptive q-Log Odds as a Drop-In BM25 Fix","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.IR","authors_text":"Oktay Goktas, Santosh Kumar Radha","submitted_at":"2026-05-18T15:41:01Z","abstract_excerpt":"In retrieval-augmented coding, failures often begin when the relevant file is absent from the retrieved context. Under frozen generic tokenization, where a BM25 index has been built by a search system whose analyzer the practitioner does not control, this failure is routine: BM25's logarithmic RSJ-odds IDF under-separates the identifier tail that distinguishes one function from another. We replace the outer logarithm of the Robertson-Sp\\\"arck-Jones odds with a q-logarithm. At q=1 the transform recovers BM25 exactly by L'H\\^opital's rule, and for q<1 it is a Box-Cox transform of the RSJ odds wi"},"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":"2605.18561","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-18T15:41:01Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"90bd19f6efa11a0571d3f97f9b364f2ce8b3cd40bc8647d2f3c14553ba98792b","abstract_canon_sha256":"f28eaeb9dc6ee3454d4c82b53c7c39d1ec687dd690477dd7190f013c5bd3a4c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:07.789138Z","signature_b64":"iiPFA/r8HUrOqbpm7k1pWRzDV3nNakNZlffE9NkTHTt6jEwoAzTu/4Tvo5liuhauMcM5nXmi2Zbq0Vm7NkIMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cab1df218e0a49ace6b106cc5ca5c8283c3877d90c4790f78c4c46c2ee6e5eb8","last_reissued_at":"2026-05-20T00:06:07.788358Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:07.788358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving BM25 Code Retrieval Under Fixed Generic Tokenization: Adaptive q-Log Odds as a Drop-In BM25 Fix","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.IR","authors_text":"Oktay Goktas, Santosh Kumar Radha","submitted_at":"2026-05-18T15:41:01Z","abstract_excerpt":"In retrieval-augmented coding, failures often begin when the relevant file is absent from the retrieved context. Under frozen generic tokenization, where a BM25 index has been built by a search system whose analyzer the practitioner does not control, this failure is routine: BM25's logarithmic RSJ-odds IDF under-separates the identifier tail that distinguishes one function from another. We replace the outer logarithm of the Robertson-Sp\\\"arck-Jones odds with a q-logarithm. At q=1 the transform recovers BM25 exactly by L'H\\^opital's rule, and for q<1 it is a Box-Cox transform of the RSJ odds wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18561","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/2605.18561/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.359180Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"c87bfbe4c7c1a3ee4fc8499e9c4d55290d0a4eef6973df98e88f055085887fe8"},"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":"2605.18561","created_at":"2026-05-20T00:06:07.788472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18561v1","created_at":"2026-05-20T00:06:07.788472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18561","created_at":"2026-05-20T00:06:07.788472+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKY56IMOBJE2","created_at":"2026-05-20T00:06:07.788472+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKY56IMOBJE2ZZVR","created_at":"2026-05-20T00:06:07.788472+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKY56IMO","created_at":"2026-05-20T00:06:07.788472+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZKY56IMOBJE2ZZVRA3GFZJOIFA","json":"https://pith.science/pith/ZKY56IMOBJE2ZZVRA3GFZJOIFA.json","graph_json":"https://pith.science/api/pith-number/ZKY56IMOBJE2ZZVRA3GFZJOIFA/graph.json","events_json":"https://pith.science/api/pith-number/ZKY56IMOBJE2ZZVRA3GFZJOIFA/events.json","paper":"https://pith.science/paper/ZKY56IMO"},"agent_actions":{"view_html":"https://pith.science/pith/ZKY56IMOBJE2ZZVRA3GFZJOIFA","download_json":"https://pith.science/pith/ZKY56IMOBJE2ZZVRA3GFZJOIFA.json","view_paper":"https://pith.science/paper/ZKY56IMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18561&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKY56IMOBJE2ZZVRA3GFZJOIFA/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKY56IMOBJE2ZZVRA3GFZJOIFA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKY56IMOBJE2ZZVRA3GFZJOIFA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKY56IMOBJE2ZZVRA3GFZJOIFA/action/storage_attestation","attest_author":"https://pith.science/pith/ZKY56IMOBJE2ZZVRA3GFZJOIFA/action/author_attestation","sign_citation":"https://pith.science/pith/ZKY56IMOBJE2ZZVRA3GFZJOIFA/action/citation_signature","submit_replication":"https://pith.science/pith/ZKY56IMOBJE2ZZVRA3GFZJOIFA/action/replication_record"}},"created_at":"2026-05-20T00:06:07.788472+00:00","updated_at":"2026-05-20T00:06:07.788472+00:00"}