{"paper":{"title":"Gravity and Flight: Learning to Navigate Fine-Grained Remote Sensing Scenes","arxiv_id":"2611.16408","primary_cat":"cs.CV","submitted_at":"2026-11-12T07:17:38+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":0.6,"id":"s0","own":false,"role":"background","text":"Vision-language models are increasingly capable, yet their reasoning in complex remote sensing scenes can remain coarse-grained and insufficiently grounded in task-relevant visual evidence.","hedge":{"p":0.72,"label":"asserted"},"own_p":0.08,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.1,"role_probabilities":{"gap":0.4,"method":0.0,"result":0.0,"background":0.6,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.95,"id":"s1","own":true,"role":"contribution","text":"We propose Gravity and Flight (G&F), a framework for scene specialization with limited supervision that separates visual and reasoning verification while coupling policy updates.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.86,"main_claim_p":0.1,"quantitative":false,"quantitative_p":0.08,"role_probabilities":{"gap":0.0,"method":0.05,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.95,"interpretation":0.0}},{"i":2,"p":0.93,"id":"s2","own":true,"role":"method","text":"It combines Evidence-of-Thought supervised fine-tuning (EoT-SFT) and Relational Transfer Policy Optimization (RTPO).","hedge":{"p":1.0,"label":"asserted"},"own_p":0.66,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.93,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.07,"interpretation":0.0}},{"i":3,"p":0.98,"id":"s3","own":true,"role":"method","text":"EoT-SFT teaches fine-grained observation and faithful reasoning through description, analysis, and supported conclusions.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.55,"main_claim_p":0.04,"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":4,"p":0.99,"id":"s4","own":true,"role":"method","text":"RTPO independently samples responses to scene-matched image pairs with fine-grained visual differences under a shared task.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.86,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.06,"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":5,"p":0.99,"id":"s5","own":true,"role":"method","text":"Its rubric-based verification combines Gravity, which checks visual fidelity and description coverage, and Flight, which takes descriptions as premises to assess evidence use and relations between paired judgments.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.79,"main_claim_p":0.06,"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":6,"p":1.0,"id":"s6","own":true,"role":"method","text":"Their scores and task correctness yield a shared pair-level advantage that couples policy updates from both responses.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.91,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":1.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":7,"p":1.0,"id":"s7","own":true,"role":"result","text":"Using 1,008 demonstrations and 500 training pairs for harbor specialization, G&F achieves a mean score of 69.12 across six evaluation sets, exceeding the backbone and supervised initialization by 9.76 and 4.56 points.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.97,"main_claim_p":0.42,"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}},{"i":8,"p":0.98,"id":"s8","own":true,"role":"result","text":"Matched controls show gains over single-image and joint-input RL, and removing either verification view reduces performance.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.11,"quantitative":true,"quantitative_p":0.87,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.98,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.02}},{"i":9,"p":1.0,"id":"s9","own":true,"role":"result","text":"Applying G&F to urban specialization also improves on the base model and supervised initialization across three evaluation subsets.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.13,"quantitative":true,"quantitative_p":0.85,"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}},{"i":10,"p":0.78,"id":"s10","own":false,"role":"future_work","text":"Project details and updates are available at https://github.com/Z0ngL1ng/Gravity-and-Flight.","hedge":{"p":0.89,"label":"asserted"},"own_p":0.14,"main_claim_p":0.01,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.01,"background":0.09,"limitation":0.0,"future_work":0.78,"contribution":0.11,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":0.89,"text":"Using 1,008 demonstrations and 500 training pairs for harbor specialization, G&F achieves a mean score of 69.12 across six evaluation sets, exceeding the backbone and supervised initialization by 9.76 and 4.56 points.","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":8200,"cost_usd_reported":0.0},"compiled_at":"2026-11-13","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.04,"states_limitation":0.17,"human_participants":0.06,"controlled_comparison":0.98,"randomized_assignment":0.02,"states_quantitative_result":0.99,"compares_with_prior_results":0.98,"mentions_code_or_data_availability":0.89},"evidential_basis":{"p":0.89,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.89,"simulation_or_computation":0.11}},"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":"We propose Gravity and Flight (G&F), a framework for scene specialization with limited supervision that separates visual and reasoning verification while coupling policy updates.","location":"abstract s1"}},"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":11,"sentences_in_abstract":11},"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"}}}