{"paper":{"title":"Localize, Then Reason: Visual Latent Structural Reasoning for Molecular Properties and Edits","arxiv_id":"2608.13244","primary_cat":"cs.CL","submitted_at":"2026-08-13T13:50:26+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":1.0,"id":"s0","own":false,"role":"background","text":"Local chemical perception and property reasoning are both essential for understanding how molecular structure determines properties.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.06,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.02,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.98,"id":"s1","own":false,"role":"background","text":"Current LLM-based chemical reasoning methods either receive SMILES/molecular images together with descriptions of local motifs, or reason directly from molecular images.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.05,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.11,"role_probabilities":{"gap":0.02,"method":0.0,"result":0.0,"background":0.98,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":1.0,"id":"s2","own":false,"role":"gap","text":"Neither approach enables the model to focus on chemically meaningful regions before reasoning.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.09,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":1.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":3,"p":0.98,"id":"s3","own":true,"role":"contribution","text":"To address this gap, we propose Visual Latent Structural Reasoning (VLSR), an end-to-end framework that jointly learns localization and reasoning from molecular images.","hedge":{"p":0.97,"label":"asserted"},"own_p":0.87,"main_claim_p":0.16,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.02,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.98,"interpretation":0.0}},{"i":4,"p":0.76,"id":"s4","own":true,"role":"method","text":"Central to our approach is a localize-then-reason strategy.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.65,"main_claim_p":0.08,"quantitative":false,"quantitative_p":0.02,"role_probabilities":{"gap":0.0,"method":0.76,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.24,"interpretation":0.0}},{"i":5,"p":0.98,"id":"s5","own":true,"role":"method","text":"VLSR first learns to locate chemically meaningful regions in a molecular image.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.76,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.02,"role_probabilities":{"gap":0.0,"method":0.98,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.02,"interpretation":0.0}},{"i":6,"p":0.99,"id":"s6","own":true,"role":"method","text":"It then reasons about their property effects in a compact latent workspace before producing the final answer.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.82,"main_claim_p":0.1,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.99,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":7,"p":1.0,"id":"s7","own":true,"role":"result","text":"Under the same inference setup, this design achieves 9.6X higher throughput than a comparable textual-reasoning baseline.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.92,"main_claim_p":0.2,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":0.89,"text":"Under the same inference setup, this design achieves 9.6X higher throughput than a comparable textual-reasoning baseline.","location":"abstract s7","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":6041,"cost_usd_reported":0.0},"compiled_at":"2026-09-23","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.14,"states_limitation":0.08,"human_participants":0.03,"controlled_comparison":0.87,"randomized_assignment":0.01,"states_quantitative_result":0.98,"compares_with_prior_results":0.94,"mentions_code_or_data_availability":0.02},"evidential_basis":{"p":0.43,"value":"observation or experiment","probabilities":{"argument":0.16,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.43,"simulation_or_computation":0.41}},"contribution_type":{"p":1.0,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":1.0,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":1.0,"text":"To address this gap, we propose Visual Latent Structural Reasoning (VLSR), an end-to-end framework that jointly learns localization and reasoning from molecular images.","location":"abstract s3"}},"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":8,"sentences_in_abstract":8},"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"}}}