{"paper":{"title":"Time and Space: A Dual-Axis, Evidence-Grounded Context Substrate for Personal Agents","arxiv_id":"2611.16492","primary_cat":"cs.AI","submitted_at":"2026-11-12T09:01:06+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":0.88,"id":"s0","own":false,"role":"gap","text":"We argue that a binding constraint for personal agents is not model capacity but the form in which context is represented: the agent does not know which entity a phrase denotes, when a fact held, or which source record licenses a claim.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.2,"main_claim_p":0.58,"quantitative":true,"quantitative_p":0.59,"role_probabilities":{"gap":0.88,"method":0.0,"result":0.0,"background":0.12,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.93,"id":"s1","own":true,"role":"contribution","text":"We call the missing representation spatio-temporal context (STC) and define it on two axes.","hedge":{"p":0.92,"label":"asserted"},"own_p":0.84,"main_claim_p":0.12,"quantitative":false,"quantitative_p":0.26,"role_probabilities":{"gap":0.04,"method":0.03,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.93,"interpretation":0.0}},{"i":2,"p":0.62,"id":"s2","own":false,"role":"contribution","text":"The temporal axis carries event time, validity intervals and ingestion time.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.47,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.0,"method":0.38,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.62,"interpretation":0.0}},{"i":3,"p":0.65,"id":"s3","own":false,"role":"contribution","text":"The spatial axis is a relational space in which entities are points, typed relations are edges, and distance is semantic rather than geographic; physical places are one entity type among many.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.43,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.11,"role_probabilities":{"gap":0.0,"method":0.35,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.65,"interpretation":0.0}},{"i":4,"p":0.63,"id":"s4","own":false,"role":"method","text":"Every relation is anchored to immutable source records, and every answer must be closed over those records.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.24,"main_claim_p":0.1,"quantitative":false,"quantitative_p":0.41,"role_probabilities":{"gap":0.0,"method":0.63,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.37,"interpretation":0.0}},{"i":5,"p":0.85,"id":"s5","own":true,"role":"contribution","text":"We formalise the substrate and six invariants, a context operator that composes temporal intersection with relational expansion, an ambiguity-preserving resolution state machine, a conflict detector that converts mutually exclusive facts into user adjudication rather than silent overwrite, and a four-regime consumption taxonomy spanning query, insight, triage and proactive reminder.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.91,"main_claim_p":0.12,"quantitative":true,"quantitative_p":0.91,"role_probabilities":{"gap":0.0,"method":0.15,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.85,"interpretation":0.0}},{"i":6,"p":0.56,"id":"s6","own":true,"role":"method","text":"We describe a local-first prototype of the retrieval layer built on SQLite with on-device embeddings and hybrid lexical-dense recall, report measurements from a deployed store of 341 documents, 340,079 chunks and 190,271 embedded vectors, and specify, but do not yet implement, the analytic layer on which the framework depends.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.04,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.56,"result":0.01,"background":0.0,"limitation":0.02,"future_work":0.0,"contribution":0.41,"interpretation":0.0}},{"i":7,"p":0.49,"id":"s7","own":true,"role":"future_work","text":"We close with an evaluation protocol with per-invariant metrics for evidence coverage, temporal correctness, conflict precision and interruption cost.","hedge":{"p":0.84,"label":"asserted"},"own_p":0.67,"main_claim_p":0.07,"quantitative":false,"quantitative_p":0.13,"role_probabilities":{"gap":0.0,"method":0.15,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.49,"contribution":0.36,"interpretation":0.0}},{"i":8,"p":0.56,"id":"s8","own":false,"role":"contribution","text":"The proposal targets the representation of context rather than the volume of it.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.3,"main_claim_p":0.29,"quantitative":false,"quantitative_p":0.21,"role_probabilities":{"gap":0.01,"method":0.0,"result":0.0,"background":0.05,"limitation":0.07,"future_work":0.0,"contribution":0.56,"interpretation":0.31}}]},"compiled":{"main_claim":{"p":0.91,"text":"We argue that a binding constraint for personal agents is not model capacity but the form in which context is represented: the agent does not know which entity a phrase denotes, when a fact held, or which source record licenses a claim.","location":"abstract s0","hedge_strength":{"p":0.98,"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":7021,"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":0.06,"states_limitation":0.94,"human_participants":0.13,"controlled_comparison":0.03,"randomized_assignment":0.01,"states_quantitative_result":0.9,"compares_with_prior_results":0.07,"mentions_code_or_data_availability":0.15},"evidential_basis":{"p":0.54,"value":"argument","probabilities":{"argument":0.54,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.01,"observation_or_experiment":0.42,"simulation_or_computation":0.03}},"contribution_type":{"p":0.87,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":0.87,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.13}},"contribution_statement":{"p":0.88,"text":"We formalise the substrate and six invariants, a context operator that composes temporal intersection with relational expansion, an ambiguity-preserving resolution state machine, a conflict detector that converts mutually exclusive facts into user adjudication rather than silent overwrite, and a four-regime consumption taxonomy spanning query, insight, triage and proactive reminder.","location":"abstract s5"}},"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":9,"sentences_in_abstract":9},"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"}}}