{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:J32GRNSRQ7USTCWOKQT7MZYWNL","short_pith_number":"pith:J32GRNSR","canonical_record":{"source":{"id":"2606.11350","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T18:26:24Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"43ae7f2414f5fa6fffee7c408b27614e672eff368dcb5048f416cdc81952644e","abstract_canon_sha256":"4790d42614c873d293e897baabd77ca9344e6c57697279d7bbc764acc3dfdcf6"},"schema_version":"1.0"},"canonical_sha256":"4ef468b65187e9298ace5427f667166ae00bd5b3e81604db7b2875bf816bc08c","source":{"kind":"arxiv","id":"2606.11350","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11350","created_at":"2026-06-11T00:08:21Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11350v1","created_at":"2026-06-11T00:08:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11350","created_at":"2026-06-11T00:08:21Z"},{"alias_kind":"pith_short_12","alias_value":"J32GRNSRQ7US","created_at":"2026-06-11T00:08:21Z"},{"alias_kind":"pith_short_16","alias_value":"J32GRNSRQ7USTCWO","created_at":"2026-06-11T00:08:21Z"},{"alias_kind":"pith_short_8","alias_value":"J32GRNSR","created_at":"2026-06-11T00:08:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:J32GRNSRQ7USTCWOKQT7MZYWNL","target":"record","payload":{"canonical_record":{"source":{"id":"2606.11350","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T18:26:24Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"43ae7f2414f5fa6fffee7c408b27614e672eff368dcb5048f416cdc81952644e","abstract_canon_sha256":"4790d42614c873d293e897baabd77ca9344e6c57697279d7bbc764acc3dfdcf6"},"schema_version":"1.0"},"canonical_sha256":"4ef468b65187e9298ace5427f667166ae00bd5b3e81604db7b2875bf816bc08c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T00:08:21.135170Z","signature_b64":"u2f6SPnBMpfNsmMprYEIIfyBcUUi/TfVJkA/nmdHmxGUPSNz23wBcZ3SRJ2QtCEb8P3ZyrRrAo8gb9uLwC4bAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ef468b65187e9298ace5427f667166ae00bd5b3e81604db7b2875bf816bc08c","last_reissued_at":"2026-06-11T00:08:21.134483Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T00:08:21.134483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.11350","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":"2026-06-11T00:08:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pmVKRW1u/bMQF/Hk8EKyRtW7+rp1lsLL9sNYpxdX2BSd+pU4C6odwfSlu4kNqngkANR36dEB8qcz710lvkH2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:06:29.000750Z"},"content_sha256":"6655dfd9c57a351607e50e8caf7b75ea88bdf7dd600b77a3de38e4a022cecceb","schema_version":"1.0","event_id":"sha256:6655dfd9c57a351607e50e8caf7b75ea88bdf7dd600b77a3de38e4a022cecceb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:J32GRNSRQ7USTCWOKQT7MZYWNL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When More Documents Hurt RAG: Mitigating Vector Search Dilution with Domain-Scoped, Model-Agnostic Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Ahmed Abdelaty, Nabaraj Subedi, Shivanand Venkanna Sheshappanavar","submitted_at":"2026-06-09T18:26:24Z","abstract_excerpt":"Retrieval-augmented generation degrades when scaled to large, heterogeneous document collections, where dense similarity loses discriminative power, and top-k retrieval increasingly returns semantically similar but contextually incorrect chunks. We refer to this failure mode as vector search dilution. Even when using hybrid dense+sparse retrieval, we observed this firsthand in a deployed Wyoming Department of Transportation corpus, where scaling from 54 to 1,128 documents (88,907 chunks) reduced accuracy from 75% to below 40%. To address this dilution, we propose MASDR-RAG ( Multi-Agent Scoped"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11350","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/2606.11350/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":"2026-06-11T00:08:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4KQLpX4rJ817HqfhxBKUxUGolyIaum8K7A8nbbMCFk7GE2NDRS7WYssV4DPttxek3T7saCXieyLGlY0Q0qHWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:06:29.001117Z"},"content_sha256":"385af6e04dbbb2ab94afedabd288a3fdfd6a32b31615fc7a77e7653526d3b4ce","schema_version":"1.0","event_id":"sha256:385af6e04dbbb2ab94afedabd288a3fdfd6a32b31615fc7a77e7653526d3b4ce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J32GRNSRQ7USTCWOKQT7MZYWNL/bundle.json","state_url":"https://pith.science/pith/J32GRNSRQ7USTCWOKQT7MZYWNL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J32GRNSRQ7USTCWOKQT7MZYWNL/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":"2026-07-05T09:06:29Z","links":{"resolver":"https://pith.science/pith/J32GRNSRQ7USTCWOKQT7MZYWNL","bundle":"https://pith.science/pith/J32GRNSRQ7USTCWOKQT7MZYWNL/bundle.json","state":"https://pith.science/pith/J32GRNSRQ7USTCWOKQT7MZYWNL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J32GRNSRQ7USTCWOKQT7MZYWNL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:J32GRNSRQ7USTCWOKQT7MZYWNL","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":"4790d42614c873d293e897baabd77ca9344e6c57697279d7bbc764acc3dfdcf6","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T18:26:24Z","title_canon_sha256":"43ae7f2414f5fa6fffee7c408b27614e672eff368dcb5048f416cdc81952644e"},"schema_version":"1.0","source":{"id":"2606.11350","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11350","created_at":"2026-06-11T00:08:21Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11350v1","created_at":"2026-06-11T00:08:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11350","created_at":"2026-06-11T00:08:21Z"},{"alias_kind":"pith_short_12","alias_value":"J32GRNSRQ7US","created_at":"2026-06-11T00:08:21Z"},{"alias_kind":"pith_short_16","alias_value":"J32GRNSRQ7USTCWO","created_at":"2026-06-11T00:08:21Z"},{"alias_kind":"pith_short_8","alias_value":"J32GRNSR","created_at":"2026-06-11T00:08:21Z"}],"graph_snapshots":[{"event_id":"sha256:385af6e04dbbb2ab94afedabd288a3fdfd6a32b31615fc7a77e7653526d3b4ce","target":"graph","created_at":"2026-06-11T00:08:21Z","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/2606.11350/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-augmented generation degrades when scaled to large, heterogeneous document collections, where dense similarity loses discriminative power, and top-k retrieval increasingly returns semantically similar but contextually incorrect chunks. We refer to this failure mode as vector search dilution. Even when using hybrid dense+sparse retrieval, we observed this firsthand in a deployed Wyoming Department of Transportation corpus, where scaling from 54 to 1,128 documents (88,907 chunks) reduced accuracy from 75% to below 40%. To address this dilution, we propose MASDR-RAG ( Multi-Agent Scoped","authors_text":"Ahmed Abdelaty, Nabaraj Subedi, Shivanand Venkanna Sheshappanavar","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T18:26:24Z","title":"When More Documents Hurt RAG: Mitigating Vector Search Dilution with Domain-Scoped, Model-Agnostic Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11350","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":"sha256:6655dfd9c57a351607e50e8caf7b75ea88bdf7dd600b77a3de38e4a022cecceb","target":"record","created_at":"2026-06-11T00:08:21Z","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":"4790d42614c873d293e897baabd77ca9344e6c57697279d7bbc764acc3dfdcf6","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T18:26:24Z","title_canon_sha256":"43ae7f2414f5fa6fffee7c408b27614e672eff368dcb5048f416cdc81952644e"},"schema_version":"1.0","source":{"id":"2606.11350","kind":"arxiv","version":1}},"canonical_sha256":"4ef468b65187e9298ace5427f667166ae00bd5b3e81604db7b2875bf816bc08c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ef468b65187e9298ace5427f667166ae00bd5b3e81604db7b2875bf816bc08c","first_computed_at":"2026-06-11T00:08:21.134483Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T00:08:21.134483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u2f6SPnBMpfNsmMprYEIIfyBcUUi/TfVJkA/nmdHmxGUPSNz23wBcZ3SRJ2QtCEb8P3ZyrRrAo8gb9uLwC4bAA==","signature_status":"signed_v1","signed_at":"2026-06-11T00:08:21.135170Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11350","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6655dfd9c57a351607e50e8caf7b75ea88bdf7dd600b77a3de38e4a022cecceb","sha256:385af6e04dbbb2ab94afedabd288a3fdfd6a32b31615fc7a77e7653526d3b4ce"],"state_sha256":"1ea8c7d45cd7a446317fdca813a04d942b304f224d1490c290ec7729d74aa2d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4BlTIJbKOiWTaDoc4kX4kP1HWA3FCNeUMN9jO6YRGhILpf9T9nKtT3FNowJKIeyE6l+mC26Wcos5mRoOHmJyCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T09:06:29.003126Z","bundle_sha256":"be4b534d6e7e127f981ef51fd507202251714d6507d71384ff1c1c5685f2a66e"}}