{"paper":{"title":"Extracting Published Discussions of 13,616 Galaxies with Language Models","arxiv_id":"2611.13118","primary_cat":"astro-ph.IM","submitted_at":"2026-11-09T19:05:31+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":0.96,"id":"s0","own":false,"role":"background","text":"Astronomers often have difficulty determining whether an object, such as a star or galaxy of interest, has been discussed in the literature.","hedge":{"p":0.96,"label":"asserted"},"own_p":0.04,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.04,"method":0.0,"result":0.0,"background":0.96,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.95,"id":"s1","own":false,"role":"gap","text":"Existing tools enable object identification and linking in papers but do not record whether an object was genuinely discussed in a paper or just appears in a table or catalog.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.04,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.95,"method":0.0,"result":0.0,"background":0.05,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.72,"id":"s2","own":true,"role":"method","text":"We address this by using language model agents to identify galaxies discussed in more than two sentences across a corpus of 156,006 arXiv astro-ph papers and extract those discussions.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.96,"main_claim_p":0.11,"quantitative":true,"quantitative_p":0.98,"role_probabilities":{"gap":0.0,"method":0.72,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.28,"interpretation":0.0}},{"i":3,"p":0.99,"id":"s3","own":true,"role":"result","text":"We extract 44,332 discussions of individual galaxies containing 85,314 quotes from 18,641 papers.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.97,"main_claim_p":0.21,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.99,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":4,"p":0.71,"id":"s4","own":true,"role":"result","text":"With sky coordinates for 98.2% of discussions, we group them into 13,616 galaxies.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.13,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.25,"result":0.71,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.04,"interpretation":0.0}},{"i":5,"p":0.97,"id":"s5","own":true,"role":"contribution","text":"We bring these results together into GalaxyWiki, where users can find literature discussing galaxies, read what was said about them, and follow links to the source papers.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.86,"main_claim_p":0.21,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.03,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.97,"interpretation":0.0}},{"i":6,"p":0.91,"id":"s6","own":true,"role":"contribution","text":"The code, dataset, and webpage are available at https://github.com/NolanKoblischke/galaxywiki-paper","hedge":{"p":0.99,"label":"asserted"},"own_p":0.62,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.03,"background":0.0,"limitation":0.0,"future_work":0.06,"contribution":0.91,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":0.75,"text":"We bring these results together into GalaxyWiki, where users can find literature discussing galaxies, read what was said about them, and follow links to the source papers.","location":"abstract s5","hedge_strength":{"p":1.0,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":5596,"cost_usd_reported":0.0},"compiled_at":"2026-11-11","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.08,"states_limitation":0.19,"human_participants":0.06,"controlled_comparison":0.03,"randomized_assignment":0.01,"states_quantitative_result":0.99,"compares_with_prior_results":0.23,"mentions_code_or_data_availability":0.99},"evidential_basis":{"p":0.75,"value":"analysis of existing data","probabilities":{"argument":0.0,"literature":0.04,"proof_or_derivation":0.0,"analysis_of_existing_data":0.75,"observation_or_experiment":0.0,"simulation_or_computation":0.21}},"contribution_type":{"p":0.9,"value":"dataset or benchmark","probabilities":{"review":0.0,"method_or_tool":0.1,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.9,"position_or_commentary":0.0}},"contribution_statement":{"p":1.0,"text":"We address this by using language model agents to identify galaxies discussed in more than two sentences across a corpus of 156,006 arXiv astro-ph papers and extract those discussions.","location":"abstract s2"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":7,"sentences_in_abstract":7},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}