Metadata-Version: 2.4
Name: papertuner
Version: 0.2.22
Summary: A package for creating ML research assistant models through paper dataset creation and model fine-tuning
Author-email: Your Name <your.email@example.com>
Project-URL: Homepage, https://github.com/yourusername/papertuner
Project-URL: Bug Tracker, https://github.com/yourusername/papertuner/issues
Project-URL: Documentation, https://github.com/yourusername/papertuner#readme
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: huggingface_hub==0.29.3
Requires-Dist: tenacity==9.0.0
Requires-Dist: PyMuPDF>=1.22.0
Requires-Dist: arxiv>=1.4.0
Requires-Dist: google-genai==1.7.0
Requires-Dist: tqdm==4.67.1
Requires-Dist: requests==2.32.3
Requires-Dist: datasets==3.4.1
Requires-Dist: sentence-transformers==3.4.1
Requires-Dist: trl==0.16.0
Requires-Dist: vllm>=0.8.1
Requires-Dist: torch==2.6.0
Requires-Dist: unsloth==2025.3.18
Requires-Dist: transformers>=4.36.2
Requires-Dist: peft>=0.8.1

    # Research Methodology QA Dataset

    ## Overview
    - Contains 2528 validated question-answer pairs
    - Derived from 1288 research papers
    - Domains: 92B05, 14-01, 13P25, 12Y05, 97M60, cond-mat.mes-hall, astro-ph.HE, 60J27, 97C42, 37Fxx, cond-mat.mtrl-sci, math.CT, q-fin.EC, physics.comp-ph, nucl-th, G.2.1, 92D15, 92D50, 82C40, 60J25, 60J75, q-bio.SC, 65, 70, 74, 76, 82, 92, 93, 94, cs.CY, cs.CR, q-bio.GN, cs.LO, G.3; I.5.3; J.3; K.8.1, 60, 92, 37N25, 92-10, 92C37, 92C40, math.RA, math.GT, 92-08, cs.MS, physics.ins-det, physics.class-ph, cond-mat.soft, 92Bxx, 92B99, cs.MA, D.2.12, 92D30, J.3, 14QXX, math.AP, cs.OH, physics.pop-ph, 37N25, 34C25, 34F05, 92D25, I.2.1, 37N25 (Primary), 34-04 (Secondary), cs.LG, q-bio.CB, astro-ph.SR, cs.AI, cs.RO, cond-mat.dis-nn, physics.atm-clus, q-fin.PR, 92D25 (Primary), 60J05 (Secondary), 34C05, 80A30, 68W15, A.1; I.2.1, 00-XX, 0-XX, 05c85 92b05, physics.soc-ph, cs.CG, I.6.6, E.1; F.2.2; G.2.1; J.3, cs.SI, 68, cs.DL, stat.AP, stat.CO, 92C42, cs.CL, 92-02, cond-mat.str-el, cs.IR, cs.DS, 92-04, nlin.PS, cs.SY, cs.SC, math.GM, 35Q92, 92-08, 49Q22, 91-10, 92-04, 74-10, 70-10, 35Q92, 37N25, 82C22, stat.ME, q-bio.OT, nlin.CD, 53C43, 53C07, 83C22, physics.ao-ph, math.CA, C.4, 35K25, 35K57, 35R09, 68, 92, cond-mat, J.3;F.4.2, 93A30; J3; 92B05; 65K05; 90C20, eess.IV, cs.IT, 05C10, 57M15, 35J70, 35B65, 42B37, 35B30 (Primary) 35J60, 35K55 (Secondary), 37N25, 37G15, 92-10, 34D20, 76-10 (Primary) 76T30, 76T06, 74A50, 80A22 (Secondary), G.3; J.3, Primary 60J27, 60J28, secondary 92B05, 92E20, 92C42, q-bio.PE, F.2;J.3, nlin.AO, physics.flu-dyn, math-ph, physics.optics, q-bio.TO, math.PR, math.GR, 37N25, 80A30, 92C45, 92E20, 14M25, 11Z05, eess.SP, quant-ph, 68T07, cs.HC, physics.acc-ph, physics.chem-ph, cs.ET, eess.SY, q-bio.NC, 68, 81, 92, cs.NA, 92Exx, 92C42, 14P10, 37N25, 14P05, physics.data-an, nlin.CG, 35R30, 35Q92, 35R11, 35K40, physics.med-ph, 37C10, 80A30, 92C40, 92D25, cs.CE, cs.SE, math.DG, 92E10;20B99, q-bio.BM, 93B52;93D20;35B35, 60H35, 65C99, 92C40, 92C37, math.HO, 92C50, physics.hist-ph, cs.NE, cs.AR, astro-ph, G.1.7; G.1.5, cs.DM, 92C37 92C42, stat.ML, math.LO, cs.CL, G.3 G.2.1, 78A70.82D55.35K25.35E05, adap-org, 93B15, 92B05, 05C85, cond-mat.other, I.2.7, cs.CC, hep-th, 92C42, 90B15, F.4; G.4; I.6; J.3, cs.GL, math.ST, 68Q25, 68Q17, 68R10, 05C85, 68W25, 92C42, 92C40, chao-dyn, q-bio, cs.PL, cs.PF, 92B05, 94A15, 94A17, 94-01, cond-mat.stat-mech, q-fin.CP, astro-ph.CO, math.DS, q-bio.QM, 60J85, 92D15, I.2, math.AG, G.1.6; J.3, 05A15, 06A25, 05C05, 92, J.3; I.2.8, 60J22, 65C05, 65Z05, 82B31, 92E20, econ.GN, 03B80, 92B05, 03B35, 03F07, math.NA, G.3; I.6.5; J.2; J.3, I.2; I.4, stat.TH, 92B05, 92C17, 92C15, 92D15, 34B60, 92B99, 65L05, 92C42 (Primary) 62F15, 97K80 (Secondary), Primary: 60J60 Secondary: 92D10, 92D15, 92D25, 01A75, 60-03, I.2.7; J.3; H.2.8, 92C37 (Primary), 35R35 (Secondary), physics.ed-ph, 92B08, cond-mat.supr-con, 94B 05B, stat.OT, astro-ph.EP, I.2.1; J.3, math.OC, 92B15, 62P10, physics.gen-ph, G.1.7; I.2.0, 92Cxx, math.IT, 92D25, 92B05, 60J85, 92-10, 92D10, 60J20, J.3; K.3; I.3.8, 92C17, 11T99 ; 05C20, cs.DB, cs.FL, 92C42, 62H30, 68T10, 37N25 34C15 37G15 34C26 92C60 92C80, math.CO, 37N25, 92C15, 92C42, comp-gas, 62P10, 92.08, cs.DC, 35K57, 35K55, 92D25, 92D99, math.MP, 92C42, 92C37, 92B05, physics.bio-ph, physics.app-ph, I.6.3;I.6.4;I.6.5, G.3, Comptuational science, math.AC, cs.CV, cs.GR, 82B20 (82B26), q-bio.MN, math.MG, 58J45, 35K57, 41A05, 41A25, 41A30, 41A63, 65D25, 65M20, 65M70,
  46E22, 35B36, I.5.2

    ## Question Categories
    Theoretical Foundations, Architecture & Design, Ethical Considerations, Analysis & Interpretation, Implementation Strategy & Techniques, Comparative Assessment, Handling Specific Challenges, Adaptation & Transfer, Future Directions, Methodology & Approach

    ## Fields
    - `question`: Technical research methodology question
    - `answer`: Detailed methodology answer
    - `category`: Question category/type
    - `paper_id`: Source paper identifier
    - `paper_title`: Title of the source paper
    - `categories`: arXiv categories
    
