Add literature review protocol, searches and first snowball round

Six seeds snowballed (Semantic Scholar) plus logged keyword searches
(OpenAlex, arXiv): 2,127 unique records, 480 title/abstract screened.
AI first-pass suggestions are in their own column; decisions are pending.

Claude-Session: https://claude.ai/code/session_01S8KN7NuUCm8nXLmy6eDuVv
This commit is contained in:
Cormac Shannon committed 2026-10-28 18:00:06 +00:00
1 parent 4369bcefa8
commit 95b5857189
28 files changed
+5547

No files matched your search

+20
View File
@@ -0,0 +1,20 @@
date,source,action,query_or_seed,filters,total_hits,retrieved,results_file
2026-10-28,Semantic Scholar API,backward snowball (references),2309.14322,,56,56,results/snowball-back-wortsman2024.csv
2026-10-28,Semantic Scholar API,forward snowball (citations),2309.14322,,210,210,results/snowball-fwd-wortsman2024.csv
2026-10-28,Semantic Scholar API,backward snowball (references),2010.04245,,41,41,results/snowball-back-henry2020.csv
2026-10-28,Semantic Scholar API,forward snowball (citations),2010.04245,,351,351,results/snowball-fwd-henry2020.csv
2026-10-28,Semantic Scholar API,backward snowball (references),2602.02522,,22,22,results/snowball-back-imu1.csv
2026-10-28,Semantic Scholar API,forward snowball (citations),2602.02522,,1,1,results/snowball-fwd-imu1.csv
2026-10-28,Semantic Scholar API,backward snowball (references),2410.16682,,21,21,results/snowball-back-stability2024.csv
2026-10-28,Semantic Scholar API,forward snowball (citations),2410.16682,,16,16,results/snowball-fwd-stability2024.csv
2026-10-28,Semantic Scholar API,backward snowball (references),2302.05442,,134,134,results/snowball-back-vit22b.csv
2026-10-28,Semantic Scholar API,forward snowball (citations),2302.05442,,972,972,results/snowball-fwd-vit22b.csv
2026-10-28,Semantic Scholar API,backward snowball (references),2303.06296,,72,72,results/snowball-back-zhai2023.csv
2026-10-28,Semantic Scholar API,forward snowball (citations),2303.06296,,221,221,results/snowball-fwd-zhai2023.csv
2026-10-28,OpenAlex API,search,"""qk-norm""|""qk norm""|""qk-layernorm""|""qk layernorm""|""query-key normalization""|""query key normalization""|""qk normalization""",since=2020-01-01,46,46,results/S1-openalex-qknorm.csv
2026-10-28,OpenAlex API,search,"""attention logit""|""attention logits""|""attention entropy collapse""|""logit growth"" AND ""training instability""|""training stability""|""loss spike""|""divergence""|""learning rate""",since=2020-01-01,11,11,results/S2-openalex-logit-instability.csv
2026-10-28,OpenAlex API,search,"""small language model""|""small language models""|""small-scale proxies""|""small transformer"" AND ""learning rate sensitivity""|""training instability""|""training stability"" AND ""normalization""",since=2020-01-01,1,1,results/S3-openalex-small-scale.csv
2026-10-28,arXiv API,search,"abs:""qk norm"" OR abs:""qk-norm"" OR abs:""query-key normalization"" OR abs:""qk normalization"" OR abs:""qk-layernorm"" OR abs:""qk layernorm""",since=2020-01-01,30,30,results/A1-arxiv-qknorm.csv
2026-10-28,arXiv API,search,"(abs:""attention logit"" OR abs:""attention logits"" OR abs:""entropy collapse"") AND (abs:""training instability"" OR abs:""learning rate"" OR abs:""loss spike"")",since=2020-01-01,9,9,results/A2-arxiv-logit-instability.csv
2026-10-28,OpenAlex API,search,"""large language model""|""large language models""|""LLM""|""ChatGPT""|""GPT-4"" AND ""systematic literature review""|""systematic review""|""literature search""|""literature screening"" AND ""search""|""screening""",since=2023-01-01,3248,200,results/L1-openalex-llm-for-lit-search.csv
2026-10-28,OpenAlex API,search,"""large language model""|""large language models""|""LLM""|""ChatGPT"" AND ""systematic literature review""|""literature review""|""snowballing"" AND ""software engineering""",since=2023-01-01,210,100,results/L2-openalex-llm-slr-software-eng.csv
1 date source action query_or_seed filters total_hits retrieved results_file
2 2026-10-28 Semantic Scholar API backward snowball (references) 2309.14322 56 56 results/snowball-back-wortsman2024.csv
3 2026-10-28 Semantic Scholar API forward snowball (citations) 2309.14322 210 210 results/snowball-fwd-wortsman2024.csv
4 2026-10-28 Semantic Scholar API backward snowball (references) 2010.04245 41 41 results/snowball-back-henry2020.csv
5 2026-10-28 Semantic Scholar API forward snowball (citations) 2010.04245 351 351 results/snowball-fwd-henry2020.csv
6 2026-10-28 Semantic Scholar API backward snowball (references) 2602.02522 22 22 results/snowball-back-imu1.csv
7 2026-10-28 Semantic Scholar API forward snowball (citations) 2602.02522 1 1 results/snowball-fwd-imu1.csv
8 2026-10-28 Semantic Scholar API backward snowball (references) 2410.16682 21 21 results/snowball-back-stability2024.csv
9 2026-10-28 Semantic Scholar API forward snowball (citations) 2410.16682 16 16 results/snowball-fwd-stability2024.csv
10 2026-10-28 Semantic Scholar API backward snowball (references) 2302.05442 134 134 results/snowball-back-vit22b.csv
11 2026-10-28 Semantic Scholar API forward snowball (citations) 2302.05442 972 972 results/snowball-fwd-vit22b.csv
12 2026-10-28 Semantic Scholar API backward snowball (references) 2303.06296 72 72 results/snowball-back-zhai2023.csv
13 2026-10-28 Semantic Scholar API forward snowball (citations) 2303.06296 221 221 results/snowball-fwd-zhai2023.csv
14 2026-10-28 OpenAlex API search "qk-norm"|"qk norm"|"qk-layernorm"|"qk layernorm"|"query-key normalization"|"query key normalization"|"qk normalization" since=2020-01-01 46 46 results/S1-openalex-qknorm.csv
15 2026-10-28 OpenAlex API search "attention logit"|"attention logits"|"attention entropy collapse"|"logit growth" AND "training instability"|"training stability"|"loss spike"|"divergence"|"learning rate" since=2020-01-01 11 11 results/S2-openalex-logit-instability.csv
16 2026-10-28 OpenAlex API search "small language model"|"small language models"|"small-scale proxies"|"small transformer" AND "learning rate sensitivity"|"training instability"|"training stability" AND "normalization" since=2020-01-01 1 1 results/S3-openalex-small-scale.csv
17 2026-10-28 arXiv API search abs:"qk norm" OR abs:"qk-norm" OR abs:"query-key normalization" OR abs:"qk normalization" OR abs:"qk-layernorm" OR abs:"qk layernorm" since=2020-01-01 30 30 results/A1-arxiv-qknorm.csv
18 2026-10-28 arXiv API search (abs:"attention logit" OR abs:"attention logits" OR abs:"entropy collapse") AND (abs:"training instability" OR abs:"learning rate" OR abs:"loss spike") since=2020-01-01 9 9 results/A2-arxiv-logit-instability.csv
19 2026-10-28 OpenAlex API search "large language model"|"large language models"|"LLM"|"ChatGPT"|"GPT-4" AND "systematic literature review"|"systematic review"|"literature search"|"literature screening" AND "search"|"screening" since=2023-01-01 3248 200 results/L1-openalex-llm-for-lit-search.csv
20 2026-10-28 OpenAlex API search "large language model"|"large language models"|"LLM"|"ChatGPT" AND "systematic literature review"|"literature review"|"snowballing" AND "software engineering" since=2023-01-01 210 100 results/L2-openalex-llm-slr-software-eng.csv