{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V22OPBHBGOFDKXJWIZBRV6RHYL","short_pith_number":"pith:V22OPBHB","schema_version":"1.0","canonical_sha256":"aeb4e784e1338a355d3646431afa27c2e53110e1b01347245600add22888d1e4","source":{"kind":"arxiv","id":"2603.26667","version":2},"attestation_state":"computed","paper":{"title":"M-RAG: Semantic Key-Value Indexing for Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Baiheng Xie, Kunpeng Zhang, Li Huang, Qiang Gao, Tongkai Xu, Xu Sun","submitted_at":"2026-01-06T15:14:54Z","abstract_excerpt":"Retrieval-augmented generation (RAG) turns external documents into evidence for large language models. In practice, this is also a data access problem: a system must decide what to index, what to retrieve, and what evidence to place in the context under a token budget. Most RAG pipelines use text chunks for both lookup and generation. This couples two different objectives. Retrieval benefits from compact and discriminative records, while generation needs contextual and faithful evidence. As a result, small chunks may fragment answer-bearing information, whereas large chunks may introduce noise"},"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":"2603.26667","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-01-06T15:14:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e9501fbbbc023925681d4e6c39cf4b554e3d29884f5b4123681377536fd3060f","abstract_canon_sha256":"c346d615208f75e6007aba5ab5fd5b9aba02718ca143d4c882b93f525a0d0374"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:23:55.561722Z","signature_b64":"0sORVMacvLZ4Zg7cLDPHDU6dYqkYubX5yhNotPgaaZdiJoIItDPDuV0SmSHG7QYAMM3weQNA9be1CpNt5c1ZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aeb4e784e1338a355d3646431afa27c2e53110e1b01347245600add22888d1e4","last_reissued_at":"2026-07-22T01:23:55.560814Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:23:55.560814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M-RAG: Semantic Key-Value Indexing for Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Baiheng Xie, Kunpeng Zhang, Li Huang, Qiang Gao, Tongkai Xu, Xu Sun","submitted_at":"2026-01-06T15:14:54Z","abstract_excerpt":"Retrieval-augmented generation (RAG) turns external documents into evidence for large language models. In practice, this is also a data access problem: a system must decide what to index, what to retrieve, and what evidence to place in the context under a token budget. Most RAG pipelines use text chunks for both lookup and generation. This couples two different objectives. Retrieval benefits from compact and discriminative records, while generation needs contextual and faithful evidence. As a result, small chunks may fragment answer-bearing information, whereas large chunks may introduce noise"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.26667","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/2603.26667/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":"2603.26667","created_at":"2026-07-22T01:23:55.561240+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.26667v2","created_at":"2026-07-22T01:23:55.561240+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.26667","created_at":"2026-07-22T01:23:55.561240+00:00"},{"alias_kind":"pith_short_12","alias_value":"V22OPBHBGOFD","created_at":"2026-07-22T01:23:55.561240+00:00"},{"alias_kind":"pith_short_16","alias_value":"V22OPBHBGOFDKXJW","created_at":"2026-07-22T01:23:55.561240+00:00"},{"alias_kind":"pith_short_8","alias_value":"V22OPBHB","created_at":"2026-07-22T01:23:55.561240+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/V22OPBHBGOFDKXJWIZBRV6RHYL","json":"https://pith.science/pith/V22OPBHBGOFDKXJWIZBRV6RHYL.json","graph_json":"https://pith.science/api/pith-number/V22OPBHBGOFDKXJWIZBRV6RHYL/graph.json","events_json":"https://pith.science/api/pith-number/V22OPBHBGOFDKXJWIZBRV6RHYL/events.json","paper":"https://pith.science/paper/V22OPBHB"},"agent_actions":{"view_html":"https://pith.science/pith/V22OPBHBGOFDKXJWIZBRV6RHYL","download_json":"https://pith.science/pith/V22OPBHBGOFDKXJWIZBRV6RHYL.json","view_paper":"https://pith.science/paper/V22OPBHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.26667&json=true","fetch_graph":"https://pith.science/api/pith-number/V22OPBHBGOFDKXJWIZBRV6RHYL/graph.json","fetch_events":"https://pith.science/api/pith-number/V22OPBHBGOFDKXJWIZBRV6RHYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V22OPBHBGOFDKXJWIZBRV6RHYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V22OPBHBGOFDKXJWIZBRV6RHYL/action/storage_attestation","attest_author":"https://pith.science/pith/V22OPBHBGOFDKXJWIZBRV6RHYL/action/author_attestation","sign_citation":"https://pith.science/pith/V22OPBHBGOFDKXJWIZBRV6RHYL/action/citation_signature","submit_replication":"https://pith.science/pith/V22OPBHBGOFDKXJWIZBRV6RHYL/action/replication_record"}},"created_at":"2026-07-22T01:23:55.561240+00:00","updated_at":"2026-07-22T01:23:55.561240+00:00"}