{"schema":"sb.node.v1","id":"sb:e/1c0dd4a73306c2c95b02c696","kind":"entity","label":{"text":"retrieval-augmented generation","locale":"en"},"identity":{"anchor":"label:en:retrieval-augmented generation","strength":"label"},"asOf":{"knowledgeCutoff":"2026-10-29T14:53:26.735970+00:00","releaseId":"sb-fd825c512c1b","snapshot":"deploy 3d25c8f1c2aeeac45bf645bc693e7d469cfddd99"},"lens":{"kind":"public"},"build":{"plane":"projected","builtFrom":["entity_graph.slim.json","entity_receipts (deploy asset)","event_graph.json","truth_records (deploy asset)","corroborated_record.json"],"rule":"node-projection.entity@v1"},"standing":{"evidence":{"supporting":103,"separatePublishers":41,"basis":"documents that mention the subject and the outlets that carried them; a mention is evidence the referent is in use, not evidence about any claim","receiptsOnTopic":{"state":"partial","share":0.204,"named":21,"of":103,"basis":"documents whose own title or summary lead names the subject, over every counted document that mentions it anywhere (the entity graph's measurement); receipts are drawn only from rows whose own title or URL names the subject (the entity graph's subject gate)","blind":["only 20% of the 103 documents measured name the subject in their own text; the rest mention it in passing, so standing.evidence.supporting overstates coverage about it"]}},"admission":{"state":"provisional","kind":"observed","kindBasis":"no-vocabulary-row","policy":"promotion (observed tier; not promoted)","reason":"seen recurring in the corpus and kept in the graph at the observation bar; not promoted into the vocabulary"},"disposition":{"state":"served","reason":"public record"},"validity":{"from":"2026-03-17","to":"2026-10-27","basis":"first and last day we saw it mentioned; not the subject's own lifetime"},"measurement":{"state":"partial","blind":["assertion coverage 0: about 100% of mentions carry no typed assertion"]}},"dimensions":{"domains":["ai_investing"],"activeDays":45,"assertions":{}},"up":[],"upNote":"An entity is a root: it is contained by nothing. Pan out by following R.","children":{"count":7,"byKind":{"observation":7},"items":[{"id":"sb:o/ffa43cdea1825d74bb68f2bb","kind":"observation","label":"arxiv.org · 2026-09-17 · When Is Graph Structure Worth Its Cost? The Case for Structure Pricing in Retrieval-Augmented Generation","url":"https://arxiv.org/abs/2609.18099","match":{"surface":"title","basis":"admitted by the entity graph's subject gate (title or URL); the headline names the subject as whole words (the door's on-topic test)"}},{"id":"sb:o/51f2c309a52e1240e8bf38ea","kind":"observation","label":"arxiv.org · 2026-09-16 · Query-Aware Source-Risk Triage for Retrieval-Augmented Generation","url":"https://arxiv.org/abs/2609.16564","match":{"surface":"title","basis":"admitted by the entity graph's subject gate (title or URL); the headline names the subject as whole words (the door's on-topic test)"}},{"id":"sb:o/26f52e52fa06fb527b1bd730","kind":"observation","label":"arxiv.org · 2026-09-16 · ORDER: Task-Conditioned Routing for Retrieval-Augmented Generation","url":"https://arxiv.org/abs/2609.17012","match":{"surface":"title","basis":"admitted by the entity graph's subject gate (title or URL); the headline names the subject as whole words (the door's on-topic test)"}},{"id":"sb:o/170e23f660cdd2cfab5481d4","kind":"observation","label":"arxiv.org · 2026-09-11 · In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning","url":"https://arxiv.org/abs/2609.09243","match":{"surface":"title","basis":"admitted by the entity graph's subject gate (title or URL); the headline names the subject as whole words (the door's on-topic test)"}},{"id":"sb:o/0e268906c34b6f9a835f46af","kind":"observation","label":"arxiv.org · 2026-09-10 · A Hierarchical Consistency Framework for Auditing Retrieval-Augmented Generation Systems","url":"https://arxiv.org/abs/2609.07075","match":{"surface":"title","basis":"admitted by the entity graph's subject gate (title or URL); the headline names the subject as whole words (the door's on-topic test)"}},{"id":"sb:o/9bfa3292aa31cfbd472741a1","kind":"observation","label":"arxiv.org · 2026-09-03 · PRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented Generation","url":"https://arxiv.org/abs/2609.01658","match":{"surface":"title","basis":"admitted by the entity graph's subject gate (title or URL); the headline names the subject as whole words (the door's on-topic test)"}},{"id":"sb:o/a51b9e1b50473976b6d0bf9a","kind":"observation","label":"arxiv.org · 2026-09-03 · Hybrid Retrieval-Augmented Generation with Knowledge Graph Expansion, RRF Fusion, and Per-Chunk Grounded Evaluation for Enterprise Document Search","url":"https://arxiv.org/abs/2609.01617","match":{"surface":"title","basis":"admitted by the entity graph's subject gate (title or URL); the headline names the subject as whole words (the door's on-topic test)"}}],"cursor":null,"order":"newest first; we keep the 7 newest receipts for this entity whose own title or URL (the entity graph's subject gate) names it; each says which in match. Its other observations are counted in standing.evidence.supporting but are not addressable in v1"},"relations":{"count":10,"byKind":{"co-mentioned":10},"items":[{"kind":"relation","label":"co-mentioned with ai (97 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/0fc9c42103ff94533f2fcb21"},{"kind":"relation","label":"co-mentioned with ai agents (34 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/860a376ecd96d6f2ea35befa"},{"kind":"relation","label":"co-mentioned with google (30 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/2b439c17a343dc4fb5a715bb"},{"kind":"relation","label":"co-mentioned with citations (29 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/5c9c781736d75ebbb7aa53b4"},{"kind":"relation","label":"co-mentioned with llms (26 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/f70bdda4ab03fd03f837ef0b"},{"kind":"relation","label":"co-mentioned with openai (24 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/e99d66d39c90394feecf2ac7"},{"kind":"relation","label":"co-mentioned with ai models (24 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/8b7ca72dc3219d09bcb73517"},{"kind":"relation","label":"co-mentioned with large language models (24 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/2b29a7c2881ba0b66d6ed2bf"},{"kind":"relation","label":"co-mentioned with agentic ai (23 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/74c71684cdb4d80ad51b84b6"},{"kind":"relation","label":"co-mentioned with finder (23 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/280ee24d3f8312a562706dd4"}],"cursor":null,"order":"situations first, then claims (the subject's own maintained record, then site-wide corroborated clusters; each label ends with its standing), then co-mentions by shared documents, descending. Co-mentions are the ten strongest the entity graph keeps per entity"},"edge":{"state":"continues"},"links":{"rest":"/api/v1/node/e/1c0dd4a73306c2c95b02c696","mcp":"traverse {\"id\":\"sb:e/1c0dd4a73306c2c95b02c696\"}","page":"/entity/retrieval-augmented-generation/"},"limits":{"levelsPerCall":1,"pageSize":10,"maxPageSize":50,"membersMax":50,"statement":"One level per call: depth is 1 and only 1, and there is no whole-graph dump. pageSize 1-50 (default 10); a page limit is a cursor, never an edge. Members are listed up to 50. At most 60 traverse calls a minute per caller (runaway-loop protection, not a meter). One knowledge cutoff is served: the deploy's."},"actions":[{"verb":"unfold","lit":true,"effect":"read","layer":"free-record","call":"traverse {\"id\":\"sb:e/1c0dd4a73306c2c95b02c696\",\"level\":\"children\"}"},{"verb":"fold","lit":true,"effect":"read","layer":"free-record","call":"traverse {\"id\":\"sb:e/1c0dd4a73306c2c95b02c696\"}"},{"verb":"panOut","lit":false,"effect":"read","layer":"free-record","reason":"An entity is a root: it is contained by nothing. Pan out by following R."},{"verb":"follow","lit":true,"effect":"read","layer":"free-record","call":"traverse {\"id\":\"sb:e/1c0dd4a73306c2c95b02c696\",\"level\":\"relations\"}"},{"verb":"receipts","lit":false,"effect":"read","layer":"free-record","reason":"receipts are the observations below this node; unfold to reach them"},{"verb":"edge","lit":true,"effect":"read","layer":"free-record","call":"traverse {\"id\":\"sb:e/1c0dd4a73306c2c95b02c696\"}"},{"verb":"asOf","lit":false,"effect":"read","layer":"free-record","reason":"v1 serves one knowledge cutoff, this deploy's; walking an earlier cutoff needs retained history, which v1 does not keep"},{"verb":"switchObserver","lit":false,"effect":"read","layer":"free-record","reason":"the public record is the same for every observer; traversal through a Watch's lens is not served in v1"},{"verb":"readOriginal","lit":false,"effect":"read","layer":"free-record","reason":"no translation is applied on this node; every label is the source's own text"},{"verb":"save","lit":false,"effect":"watch-declaration","layer":"watch","reason":"saving applies to a configured Watch; configure one around this node first (free), then save it"},{"verb":"deliver","lit":false,"effect":"watch-declaration","layer":"watch","reason":"delivery applies to a saved Watch"},{"verb":"format","lit":false,"effect":"watch-declaration","layer":"watch","reason":"output format applies to a saved Watch"},{"verb":"deltaR","lit":false,"effect":"read","layer":"watch","reason":"Delta R needs a saved Watch with a previous reading"},{"verb":"read","lit":false,"effect":"read","layer":"one-time-read","reason":"one-time Reads are not offered through this door; use ask"}]}