{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZKY56IMOBJE2ZZVRA3GFZJOIFA","short_pith_number":"pith:ZKY56IMO","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"},"canonical_sha256":"cab1df218e0a49ace6b106cc5ca5c8283c3877d90c4790f78c4c46c2ee6e5eb8","source":{"kind":"arxiv","id":"2605.18561","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18561","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18561v1","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18561","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"ZKY56IMOBJE2","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZKY56IMOBJE2ZZVR","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZKY56IMO","created_at":"2026-05-20T00:06:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZKY56IMOBJE2ZZVRA3GFZJOIFA","target":"record","payload":{"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"},"canonical_sha256":"cab1df218e0a49ace6b106cc5ca5c8283c3877d90c4790f78c4c46c2ee6e5eb8","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"},"source_kind":"arxiv","source_id":"2605.18561","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:06:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wM2QLm2vTNl/lJ4CbXg9vqA+7ssKJQAriB7ChgGeFY4Vik6yXOSPNgxLC3fXJCS6FY3lXy77M074kfr8oiARAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T14:22:22.066926Z"},"content_sha256":"5879f228ae6bbfec5ccc3666922327c6b3b4f75b94fa316d664071716df219b9","schema_version":"1.0","event_id":"sha256:5879f228ae6bbfec5ccc3666922327c6b3b4f75b94fa316d664071716df219b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZKY56IMOBJE2ZZVRA3GFZJOIFA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:06:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sjOEqOs2J8mXjDR0Hj+INmg4GFs3wmePeDjU8z4Aple/GDn0ZBR2rEK/2gthIgIg4pPH8usD33OXZ9s24+SoAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T14:22:22.067345Z"},"content_sha256":"5fcf66a18591db3884b8b90622e39b6d3f0f4f9d68b62a023ab445624fd672d0","schema_version":"1.0","event_id":"sha256:5fcf66a18591db3884b8b90622e39b6d3f0f4f9d68b62a023ab445624fd672d0"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:ZKY56IMOBJE2ZZVRA3GFZJOIFA","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.2310.11248.URLhttps://openreview.net/forum?id=wgDcbBMSfh.Eric) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"doi: 10.48550/arXiv.2310. 11248. URLhttps://openreview.net/forum?id=wgDcbBMSfh. Eric Enslen, Emily Hill, Lori Pollock, and K. Vijay-Shanker. Mining source code to automatically split identifiers for software analysis. In6th IEEE Internation","arxiv_id":"2605.18561","detector":"doi_compliance","evidence":{"ref_index":4,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"doi: 10.48550/arXiv.2310. 11248. URLhttps://openreview.net/forum?id=wgDcbBMSfh. Eric Enslen, Emily Hill, Lori Pollock, and K. Vijay-Shanker. Mining source code to automatically split identifiers for software analysis. In6th IEEE Internation","reconstructed_doi":"10.48550/arXiv.2310.11248.URLhttps://openreview.net/forum?id=wgDcbBMSfh.Eric"},"severity":"advisory","ref_index":4,"audited_at":"2026-05-20T08:21:36.846637Z","event_type":"pith.integrity.v1","detected_doi":"10.48550/arXiv.2310.11248.URLhttps://openreview.net/forum?id=wgDcbBMSfh.Eric","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"abc8a152cf71b5bba337abcb61e260b56a961b3a1f00eab72adf7b354c3a3949","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":4919,"payload_sha256":"273d6204d16ee08004e5dcb36e7a308bf9ae2df66d6524aca9aebd08a4b6b338","signature_b64":"ORvA4rTohIt3oy+cPy27LUkUEo3eYTGzUEdGenRSiB81AVfGTerT5idJof/76ZhrZAxKsh2tXeazyO4Rog67Bg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T08:22:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q0JxdosHVhAY6N/7FFQ7BA9mqsDROxAFov62/aJ1+4xzAYl/F5DH+MXtpWE5iCDQwugE1LjtMRVtkHVFrQ2nDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T14:22:22.068412Z"},"content_sha256":"df2e1d204fb56490fae482282356edd17025bd998173234dc417a227b0f2c179","schema_version":"1.0","event_id":"sha256:df2e1d204fb56490fae482282356edd17025bd998173234dc417a227b0f2c179"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZKY56IMOBJE2ZZVRA3GFZJOIFA/bundle.json","state_url":"https://pith.science/pith/ZKY56IMOBJE2ZZVRA3GFZJOIFA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZKY56IMOBJE2ZZVRA3GFZJOIFA/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":"2026-05-21T14:22:22Z","links":{"resolver":"https://pith.science/pith/ZKY56IMOBJE2ZZVRA3GFZJOIFA","bundle":"https://pith.science/pith/ZKY56IMOBJE2ZZVRA3GFZJOIFA/bundle.json","state":"https://pith.science/pith/ZKY56IMOBJE2ZZVRA3GFZJOIFA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZKY56IMOBJE2ZZVRA3GFZJOIFA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZKY56IMOBJE2ZZVRA3GFZJOIFA","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f28eaeb9dc6ee3454d4c82b53c7c39d1ec687dd690477dd7190f013c5bd3a4c0","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-18T15:41:01Z","title_canon_sha256":"90bd19f6efa11a0571d3f97f9b364f2ce8b3cd40bc8647d2f3c14553ba98792b"},"schema_version":"1.0","source":{"id":"2605.18561","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18561","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18561v1","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18561","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"ZKY56IMOBJE2","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZKY56IMOBJE2ZZVR","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZKY56IMO","created_at":"2026-05-20T00:06:07Z"}],"graph_snapshots":[{"event_id":"sha256:5fcf66a18591db3884b8b90622e39b6d3f0f4f9d68b62a023ab445624fd672d0","target":"graph","created_at":"2026-05-20T00:06:07Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.359180Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18561/integrity.json","findings":[],"snapshot_sha256":"c87bfbe4c7c1a3ee4fc8499e9c4d55290d0a4eef6973df98e88f055085887fe8","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Oktay Goktas, Santosh Kumar Radha","cross_cats":["cs.AI","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-18T15:41:01Z","title":"Improving BM25 Code Retrieval Under Fixed Generic Tokenization: Adaptive q-Log Odds as a Drop-In BM25 Fix"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18561","kind":"arxiv","version":1},"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":"sha256:5879f228ae6bbfec5ccc3666922327c6b3b4f75b94fa316d664071716df219b9","target":"record","created_at":"2026-05-20T00:06:07Z","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":"f28eaeb9dc6ee3454d4c82b53c7c39d1ec687dd690477dd7190f013c5bd3a4c0","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-18T15:41:01Z","title_canon_sha256":"90bd19f6efa11a0571d3f97f9b364f2ce8b3cd40bc8647d2f3c14553ba98792b"},"schema_version":"1.0","source":{"id":"2605.18561","kind":"arxiv","version":1}},"canonical_sha256":"cab1df218e0a49ace6b106cc5ca5c8283c3877d90c4790f78c4c46c2ee6e5eb8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cab1df218e0a49ace6b106cc5ca5c8283c3877d90c4790f78c4c46c2ee6e5eb8","first_computed_at":"2026-05-20T00:06:07.788358Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:07.788358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iiPFA/r8HUrOqbpm7k1pWRzDV3nNakNZlffE9NkTHTt6jEwoAzTu/4Tvo5liuhauMcM5nXmi2Zbq0Vm7NkIMDQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:07.789138Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18561","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5879f228ae6bbfec5ccc3666922327c6b3b4f75b94fa316d664071716df219b9","sha256:5fcf66a18591db3884b8b90622e39b6d3f0f4f9d68b62a023ab445624fd672d0","sha256:df2e1d204fb56490fae482282356edd17025bd998173234dc417a227b0f2c179"],"state_sha256":"78c5449d8eea324f7d63cf5c2293e42253bffedb9ab90387e52d478d2d2d03c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EbHzTQh9d5aiZ/+WQOKwVjFi8ay1G8ac8isrkuzF4qa/CSWu2oLcaJw2EpM6oy4vVANNBmuVG3ZY1kVY3EOWAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T14:22:22.070651Z","bundle_sha256":"0652921bdd9092e2bb8f764fbae6e55b65aac1497c8161bcd6255491352ca4c1"}}