# Research method and scope

## Research question

How did retrieval-augmented generation evolve, what technical problems drove
each transition, and which technique families define the state of the art as of
2026-08-09?

The phrase “state of the art” is treated as a conditional claim. A system may be
frontier-quality for multi-hop evidence discovery, visual-page retrieval,
global corpus synthesis, citation completeness, or accuracy/cost trade-offs
without dominating the other dimensions.

## Evidence policy

The review uses this source priority:

1. final peer-reviewed paper in official proceedings;
2. accepted-paper page or author manuscript when proceedings are unavailable;
3. original preprint for work not yet formally published;
4. first-party technical report for influential industry systems;
5. official repository or dataset card for implementation details not stated in
   the paper.

Surveys help discover terminology and references but do not support mechanism,
result, or priority claims. Secondary blog posts and vendor comparisons are not
used as independent evidence. The machine-readable
[`sources.json`](sources.json) labels each source as `peer-reviewed`, `preprint`,
`industry-report`, or `benchmark-program`.

The [mathematical primer](mathematical_primer.md) collects the objectives and
systems assumptions that recur across papers so the chronology can focus on
empirical and historical differences.

The [field map](field_map.md) is the scope contract, the
[chronological index](chronological_index.md) lists every registered work by
first-public date, and the [coverage matrix](coverage_matrix.md) maps every
major subject to its detailed chapter, Jupyter lab, reference implementation,
and verification evidence. The six continuous-prose
[`field_notebook`](field_notebook) folios provide the book-length reading path;
the complete Jupyter edition places those expressive folios in front of the
entire technical atlas in
[`notebooks/00_complete_rag_handbook.ipynb`](../notebooks/00_complete_rag_handbook.ipynb).

## Chronology policy

Both **first public date** and **formal publication** matter. For example, FiD
and FiD-KD were public in 2020 but published in 2021; RETRO was public in 2021
and published in 2022; Atlas was a 2022 preprint and a 2023 JMLR article. The
chronology orders first public disclosure and reports the venue separately.

This prevents two common historical errors:

- pretending the term “RAG” created retrieve-then-generate architectures; and
- moving methods by a year or more merely because one cites the conference date
  and another cites the arXiv date.

## Claim policy

Every method entry separates:

- **mechanism:** representation, retrieval, integration, and policy;
- **learning signal:** labels, contrastive loss, marginal likelihood,
  distillation, supervised trajectories, or reinforcement learning;
- **evidence:** corpus, dataset, metric, and the original paper's result;
- **limitations:** threats to validity and deployment constraints;
- **influence:** the architectural idea inherited by later work.

Reported scores are not recomputed in this repository. They are attributed to
their source and are not compared across incompatible settings. Phrases such as
“state of the art” are retained only when scoped to the paper's own benchmark
and setting; the synthesis prefers exact metrics and caveats.

## Reproduction policy

For an experiment to be replayable, record at least:

- corpus source, timestamp, content hash, permissions, and deletion state;
- document parser, chunker, overlap, metadata, embedding and index versions;
- retriever, fusion, reranker, top-\(k\), score calibration, and ANN parameters;
- generator, prompt, context order, context budget, decoding, and random seed;
- every retrieved chunk with score, rank, source ID, and retrieval timestamp;
- answer claims, citation spans, abstention/confidence, latency, token count, and
  cost;
- evaluation set/qrels version, judge prompt/model, human adjudication, and
  uncertainty interval.

Mutable web search and closed model APIs require an immutable trace. A model
name such as “GPT-4” or “Claude” without an exact revision/date is insufficient
for a durable result.

## What the executable code proves—and does not

The code verifies algorithmic ideas at small scale: versioned manifests,
content hashes, exact/near deduplication, ACLs and tombstones; fixed, sentence,
section, and parent–child chunks with exact lineage; postings-list BM25; exact
cosine and IVF search; scalar/product quantization and ANN recall; RRF and
calibrated score fusion; multi-query and graph expansion; adaptive/iterative
routing; interaction reranking; MMR and claim-coverage selection; InfoNCE,
pairwise/listwise/distillation/DPO/REINFORCE objectives; Personalized PageRank,
table retrieval, visual late interaction, and hierarchical selection; memory
write/retrieve/update/consolidate/delete; bitemporal lookup and freshness;
authorization, active-content/injection signals, provenance signatures,
poison-cluster/canary diagnostics; citations, abstention, layered metrics,
paired bootstrap intervals, SLOs, budgets, cost, and Pareto selection.

It does not reproduce billion-parameter training runs or paper leaderboards.
The hashed semantic retriever, heuristic reranker, learned-model boundaries,
and security detectors are deliberately labeled teaching proxies. Distributed
ANN engines, neural parsers/encoders/readers, VLMs, private-retrieval protocols,
and certified defenses are documented with substitution and evaluation
contracts rather than misrepresented by trivial demos. Every local decision is
inspectable and every notebook runs without model downloads, credentials, or
mutable external services.