{"paper":{"title":"Neural Representations as New Modes of Interactivity","arxiv_id":"2611.17058","primary_cat":"cs.HC","submitted_at":"2026-11-12T16:36:58+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":0.93,"id":"s0","own":false,"role":"background","text":"Human-AI interaction today runs almost entirely through prompts and outputs, keeping AI systems opaque to general users.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.09,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.36,"role_probabilities":{"gap":0.07,"method":0.0,"result":0.0,"background":0.93,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":1.0,"id":"s1","own":true,"role":"contribution","text":"We introduce Neural Representation Interaction (NRI), a paradigm that treats the internal representations of neural networks as an interaction material people can inspect, steer, and edit.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.89,"main_claim_p":0.2,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":1.0,"interpretation":0.0}},{"i":2,"p":0.46,"id":"s2","own":true,"role":"interpretation","text":"Situating NRI alongside graphical, tangible, and bio-computer interaction, we argue that the concepts and algorithms models encode internally offer representational affordances for richer human-AI interaction.","hedge":{"p":0.8,"label":"asserted"},"own_p":0.51,"main_claim_p":0.3,"quantitative":false,"quantitative_p":0.16,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.0,"background":0.08,"limitation":0.0,"future_work":0.0,"contribution":0.45,"interpretation":0.46}},{"i":3,"p":0.66,"id":"s3","own":true,"role":"method","text":"We synthesize actionable mechanistic interpretability methods and, drawing on General Morphological Analysis, construct a design space spanning Interaction, Target, Referent, and Purpose.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.93,"main_claim_p":0.07,"quantitative":false,"quantitative_p":0.1,"role_probabilities":{"gap":0.0,"method":0.66,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.34,"interpretation":0.0}},{"i":4,"p":0.9,"id":"s4","own":true,"role":"result","text":"Mapping existing interfaces onto this space reveals that most serve expert auditors, while few support lay users.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.78,"main_claim_p":0.09,"quantitative":true,"quantitative_p":0.86,"role_probabilities":{"gap":0.03,"method":0.0,"result":0.9,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.04,"interpretation":0.03}},{"i":5,"p":0.84,"id":"s5","own":true,"role":"contribution","text":"We then present speculative applications in education, personal user modeling, and hiring audits, and discuss design principles, limitations, and sociotechnical risks.","hedge":{"p":0.73,"label":"speculative"},"own_p":0.85,"main_claim_p":0.09,"quantitative":false,"quantitative_p":0.11,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.16,"contribution":0.84,"interpretation":0.0}},{"i":6,"p":0.63,"id":"s6","own":false,"role":"interpretation","text":"NRI offers HCI researchers abstractions for designing interactions that work with AI computation rather than only through its inputs and outputs.","hedge":{"p":0.96,"label":"asserted"},"own_p":0.4,"main_claim_p":0.65,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.07,"contribution":0.3,"interpretation":0.63}}]},"compiled":{"main_claim":{"p":0.76,"text":"NRI offers HCI researchers abstractions for designing interactions that work with AI computation rather than only through its inputs and outputs.","location":"abstract s6","hedge_strength":{"p":0.96,"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":5582,"cost_usd_reported":0.0},"compiled_at":"2026-11-14","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.11,"states_limitation":0.85,"human_participants":0.14,"controlled_comparison":0.03,"randomized_assignment":0.01,"states_quantitative_result":0.04,"compares_with_prior_results":0.42,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":0.98,"value":"argument","probabilities":{"argument":0.98,"literature":0.02,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.0,"simulation_or_computation":0.0}},"contribution_type":{"p":0.92,"value":"position or commentary","probabilities":{"review":0.0,"method_or_tool":0.08,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.92}},"contribution_statement":{"p":0.95,"text":"We introduce Neural Representation Interaction (NRI), a paradigm that treats the internal representations of neural networks as an interaction material people can inspect, steer, and edit.","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":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"}}}