ResearchIT / scripts /topic_labels.json
siddhm11
Claude Opus 5.5
fix(ingest): make the arXiv backfill safe to run and re-run
82498e7
Raw History Blame Contribute Delete
5.15 kB
{
"_about": "Primary arXiv code -> the friendly primary_topic label the existing post-2025 rows carry (modal label per code, codes with >= 20 rows). Generated 2026-10-01 from sidecar d241ff1. Codes not listed fall back to 'Other Technical'. Ingest-only: serving derives categories from the categories column, not from this label.",
"labels": {
"astro-ph.CO": "Other Technical",
"astro-ph.EP": "Other Technical",
"astro-ph.GA": "Other Technical",
"astro-ph.HE": "Signal Processing",
"astro-ph.IM": "Other Technical",
"astro-ph.SR": "Signal Processing",
"cond-mat.dis-nn": "Other Technical",
"cond-mat.mes-hall": "Quantum Computing",
"cond-mat.mtrl-sci": "Other Technical",
"cond-mat.other": "Other Technical",
"cond-mat.quant-gas": "Quantum Computing",
"cond-mat.soft": "Other Technical",
"cond-mat.stat-mech": "Other Technical",
"cond-mat.str-el": "Other Technical",
"cond-mat.supr-con": "Other Technical",
"cs.AI": "AI/ML",
"cs.AR": "Other Technical",
"cs.CC": "Other Technical",
"cs.CE": "Other Technical",
"cs.CG": "Algorithms/Data Structures",
"cs.CL": "NLP/Computational Linguistics",
"cs.CR": "Cryptography/Security",
"cs.CV": "Computer Vision",
"cs.CY": "Computer Society/Ethics",
"cs.DB": "Databases",
"cs.DC": "Networks/Distributed Systems",
"cs.DL": "Other Technical",
"cs.DM": "Pure Mathematics",
"cs.DS": "Algorithms/Data Structures",
"cs.ET": "Other Technical",
"cs.FL": "Other Technical",
"cs.GR": "Graphics/Visualization",
"cs.GT": "Game Theory",
"cs.HC": "Human-Computer Interaction",
"cs.IR": "Information Retrieval",
"cs.IT": "Information Theory",
"cs.LG": "AI/ML",
"cs.LO": "Other Technical",
"cs.MA": "Multiagent Systems",
"cs.MM": "Other Technical",
"cs.MS": "Other Technical",
"cs.NE": "AI/ML",
"cs.NI": "Networks/Distributed Systems",
"cs.OH": "Other Technical",
"cs.OS": "Other Technical",
"cs.PF": "Other Technical",
"cs.PL": "Other Technical",
"cs.RO": "Robotics",
"cs.SC": "Other Technical",
"cs.SD": "AI/ML",
"cs.SE": "Software Engineering",
"cs.SI": "AI/ML",
"econ.EM": "Economics",
"econ.GN": "Economics",
"econ.TH": "Game Theory",
"eess.AS": "Signal Processing",
"eess.IV": "Computer Vision",
"eess.SP": "Signal Processing",
"eess.SY": "Systems/Control",
"gr-qc": "Other Technical",
"hep-ex": "Other Technical",
"hep-lat": "Other Technical",
"hep-ph": "Other Technical",
"hep-th": "Quantum Computing",
"math-ph": "Pure Mathematics",
"math.AC": "Pure Mathematics",
"math.AG": "Pure Mathematics",
"math.AP": "Pure Mathematics",
"math.AT": "Pure Mathematics",
"math.CA": "Pure Mathematics",
"math.CO": "Pure Mathematics",
"math.CT": "Pure Mathematics",
"math.CV": "Pure Mathematics",
"math.DG": "Pure Mathematics",
"math.DS": "Pure Mathematics",
"math.FA": "Pure Mathematics",
"math.GM": "Other Technical",
"math.GN": "Pure Mathematics",
"math.GR": "Pure Mathematics",
"math.GT": "Pure Mathematics",
"math.HO": "Pure Mathematics",
"math.KT": "Signal Processing",
"math.LO": "Other Technical",
"math.MG": "Pure Mathematics",
"math.NA": "Signal Processing",
"math.NT": "Pure Mathematics",
"math.OA": "Pure Mathematics",
"math.OC": "Pure Mathematics",
"math.PR": "Pure Mathematics",
"math.QA": "Pure Mathematics",
"math.RA": "Pure Mathematics",
"math.RT": "Pure Mathematics",
"math.SG": "Pure Mathematics",
"math.SP": "Pure Mathematics",
"math.ST": "Statistics",
"nlin.AO": "Other Technical",
"nlin.CD": "Other Technical",
"nlin.PS": "Other Technical",
"nlin.SI": "Signal Processing",
"nucl-ex": "Other Technical",
"nucl-th": "Other Technical",
"physics.acc-ph": "Other Technical",
"physics.ao-ph": "Other Technical",
"physics.app-ph": "Other Technical",
"physics.atm-clus": "Other Technical",
"physics.atom-ph": "Quantum Computing",
"physics.bio-ph": "Other Technical",
"physics.chem-ph": "Other Technical",
"physics.class-ph": "Other Technical",
"physics.comp-ph": "Computational Physics",
"physics.data-an": "Computational Physics",
"physics.ed-ph": "Other Technical",
"physics.flu-dyn": "Other Technical",
"physics.gen-ph": "Other Technical",
"physics.geo-ph": "Other Technical",
"physics.hist-ph": "Quantum Computing",
"physics.ins-det": "Other Technical",
"physics.med-ph": "Other Technical",
"physics.optics": "Other Technical",
"physics.plasm-ph": "Other Technical",
"physics.soc-ph": "Other Technical",
"physics.space-ph": "Other Technical",
"q-bio.BM": "Other Technical",
"q-bio.GN": "Other Technical",
"q-bio.MN": "Other Technical",
"q-bio.NC": "AI/ML",
"q-bio.OT": "Other Technical",
"q-bio.PE": "Other Technical",
"q-bio.QM": "Other Technical",
"q-bio.TO": "Other Technical",
"q-fin.CP": "Finance",
"q-fin.GN": "Finance",
"q-fin.MF": "Finance",
"q-fin.PM": "Finance",
"q-fin.PR": "Finance",
"q-fin.RM": "Finance",
"q-fin.ST": "Finance",
"q-fin.TR": "Finance",
"quant-ph": "Quantum Computing",
"stat.AP": "Statistics",
"stat.CO": "Statistics",
"stat.ME": "Statistics",
"stat.ML": "AI/ML",
"stat.OT": "Other Technical"
}
}