{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2Z4PJPYOCMT72VPL5Q4Y4KJLOU","short_pith_number":"pith:2Z4PJPYO","schema_version":"1.0","canonical_sha256":"d678f4bf0e1327fd55ebec398e292b753499f0ad0d1ace6b75be345a5d6c3d74","source":{"kind":"arxiv","id":"2606.01542","version":1},"attestation_state":"computed","paper":{"title":"Self-Conditioned Positional HNSW for Overlap-Aware Retrieval in Chunked-Document RAG Systems: Method and Industrial Evidence-Quality Audit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DB","cs.IR"],"primary_cat":"cs.DC","authors_text":"Nataraj Agaram Sundar, Tejas Morabia","submitted_at":"2026-06-01T01:42:55Z","abstract_excerpt":"Chunked-document retrieval is a common component of retrieval-augmented generation (RAG) systems. Documents are split into overlapping chunks, embedded, and indexed with approximate nearest-neighbor search such as hierarchical navigable small world graphs (HNSW). Overlap improves boundary coverage but induces a practical failure mode: top-k retrieval often returns near-adjacent chunks that repeat evidence and waste prompt budget. We propose Self-Conditioned Positional HNSW (SCP-HNSW), a lightweight modification that appends a low-dimensional positional code to chunk embeddings and uses a two-p"},"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":"2606.01542","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-06-01T01:42:55Z","cross_cats_sorted":["cs.AI","cs.CL","cs.DB","cs.IR"],"title_canon_sha256":"6de7074dc42abbfbe2794beaa645067e31ce49c96137796fe06eebda62c05a6d","abstract_canon_sha256":"a3a116d516cd8ac14ea830a9c97eb4951a836282ec028ef2d6ca866acfd02c0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:35.918028Z","signature_b64":"Z4FDw2S/NOtlMbDKKrrW4UcMgsJzkCZXnGZbm5wVxCIukYRW90YjuzQ5f3yaCnF7CcZHwtY4rJabRrb3siZoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d678f4bf0e1327fd55ebec398e292b753499f0ad0d1ace6b75be345a5d6c3d74","last_reissued_at":"2026-06-02T02:04:35.917614Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:35.917614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Conditioned Positional HNSW for Overlap-Aware Retrieval in Chunked-Document RAG Systems: Method and Industrial Evidence-Quality Audit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DB","cs.IR"],"primary_cat":"cs.DC","authors_text":"Nataraj Agaram Sundar, Tejas Morabia","submitted_at":"2026-06-01T01:42:55Z","abstract_excerpt":"Chunked-document retrieval is a common component of retrieval-augmented generation (RAG) systems. Documents are split into overlapping chunks, embedded, and indexed with approximate nearest-neighbor search such as hierarchical navigable small world graphs (HNSW). Overlap improves boundary coverage but induces a practical failure mode: top-k retrieval often returns near-adjacent chunks that repeat evidence and waste prompt budget. We propose Self-Conditioned Positional HNSW (SCP-HNSW), a lightweight modification that appends a low-dimensional positional code to chunk embeddings and uses a two-p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01542","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/2606.01542/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":"2606.01542","created_at":"2026-06-02T02:04:35.917676+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01542v1","created_at":"2026-06-02T02:04:35.917676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01542","created_at":"2026-06-02T02:04:35.917676+00:00"},{"alias_kind":"pith_short_12","alias_value":"2Z4PJPYOCMT7","created_at":"2026-06-02T02:04:35.917676+00:00"},{"alias_kind":"pith_short_16","alias_value":"2Z4PJPYOCMT72VPL","created_at":"2026-06-02T02:04:35.917676+00:00"},{"alias_kind":"pith_short_8","alias_value":"2Z4PJPYO","created_at":"2026-06-02T02:04:35.917676+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/2Z4PJPYOCMT72VPL5Q4Y4KJLOU","json":"https://pith.science/pith/2Z4PJPYOCMT72VPL5Q4Y4KJLOU.json","graph_json":"https://pith.science/api/pith-number/2Z4PJPYOCMT72VPL5Q4Y4KJLOU/graph.json","events_json":"https://pith.science/api/pith-number/2Z4PJPYOCMT72VPL5Q4Y4KJLOU/events.json","paper":"https://pith.science/paper/2Z4PJPYO"},"agent_actions":{"view_html":"https://pith.science/pith/2Z4PJPYOCMT72VPL5Q4Y4KJLOU","download_json":"https://pith.science/pith/2Z4PJPYOCMT72VPL5Q4Y4KJLOU.json","view_paper":"https://pith.science/paper/2Z4PJPYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01542&json=true","fetch_graph":"https://pith.science/api/pith-number/2Z4PJPYOCMT72VPL5Q4Y4KJLOU/graph.json","fetch_events":"https://pith.science/api/pith-number/2Z4PJPYOCMT72VPL5Q4Y4KJLOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2Z4PJPYOCMT72VPL5Q4Y4KJLOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2Z4PJPYOCMT72VPL5Q4Y4KJLOU/action/storage_attestation","attest_author":"https://pith.science/pith/2Z4PJPYOCMT72VPL5Q4Y4KJLOU/action/author_attestation","sign_citation":"https://pith.science/pith/2Z4PJPYOCMT72VPL5Q4Y4KJLOU/action/citation_signature","submit_replication":"https://pith.science/pith/2Z4PJPYOCMT72VPL5Q4Y4KJLOU/action/replication_record"}},"created_at":"2026-06-02T02:04:35.917676+00:00","updated_at":"2026-06-02T02:04:35.917676+00:00"}