{"paper":{"title":"MaSRead: Content-Addressed Reading of Replicated Latent Stores","arxiv_id":"2608.11218","primary_cat":"cs.AI","submitted_at":"2026-07-21T08:48:06+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":0.98,"id":"s0","own":false,"role":"background","text":"Independent agents that reason in latent space can share computed state as key-value cache fragments rather than text.","hedge":{"p":0.91,"label":"asserted"},"own_p":0.15,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.0,"background":0.98,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":1,"p":0.48,"id":"s1","own":false,"role":"background","text":"Merged by a conflict-free replicated data type, these fragments form a store that converges under any delivery order or duplication.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.37,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.1,"role_probabilities":{"gap":0.0,"method":0.47,"result":0.0,"background":0.48,"limitation":0.0,"future_work":0.0,"contribution":0.05,"interpretation":0.0}},{"i":2,"p":0.85,"id":"s2","own":true,"role":"gap","text":"Yet a later query, unknown at encode time, cannot reliably read the merged cache: colocated fragments interfere, so colocation is not addressability.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.51,"main_claim_p":0.07,"quantitative":false,"quantitative_p":0.09,"role_probabilities":{"gap":0.85,"method":0.0,"result":0.01,"background":0.13,"limitation":0.01,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":3,"p":0.98,"id":"s3","own":true,"role":"contribution","text":"MaSRead addresses the read to content.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.73,"main_claim_p":0.21,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.01,"method":0.01,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.98,"interpretation":0.0}},{"i":4,"p":0.99,"id":"s4","own":true,"role":"method","text":"It routes through opaque keyed tag sets derived from fragment words and decodes each selected fragment under a hard attention mask that hides the rest.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.78,"main_claim_p":0.11,"quantitative":false,"quantitative_p":0.05,"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":"Under lexical connectivity, a graph walk reaches the fragments required by a multi-hop query.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.68,"main_claim_p":0.09,"quantitative":false,"quantitative_p":0.07,"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":"result","text":"Across chain, pipeline, symmetric, hub, and natural-language stores, MaSRead recovers visited fragments in isolation, remains effective as unrelated fragments accumulate, and transfers to another model family.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.87,"main_claim_p":0.15,"quantitative":false,"quantitative_p":0.14,"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":7,"p":0.61,"id":"s7","own":true,"role":"result","text":"After routing, materialized decoding depends on fragment length rather than total store size; end-to-end work still includes store-dependent routing and one read per visited fragment.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.8,"main_claim_p":0.07,"quantitative":true,"quantitative_p":0.86,"role_probabilities":{"gap":0.0,"method":0.04,"result":0.61,"background":0.0,"limitation":0.33,"future_work":0.0,"contribution":0.0,"interpretation":0.02}},{"i":8,"p":1.0,"id":"s8","own":true,"role":"limitation","text":"The limits are explicit: lexical routing can miss disconnected evidence, and answer composition remains bounded by the frozen reader.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.68,"main_claim_p":0.06,"quantitative":true,"quantitative_p":0.6,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":1.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":9,"p":0.84,"id":"s9","own":true,"role":"interpretation","text":"Thus a replicated latent store becomes selectively readable for later queries when the needed fragments connect to the query through content.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.75,"main_claim_p":0.86,"quantitative":false,"quantitative_p":0.08,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.12,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.04,"interpretation":0.84}}]},"compiled":{"main_claim":{"p":1.0,"text":"Thus a replicated latent store becomes selectively readable for later queries when the needed fragments connect to the query through content.","location":"abstract s9","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":7418,"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":0.07,"states_limitation":0.98,"human_participants":0.03,"controlled_comparison":0.09,"randomized_assignment":0.01,"states_quantitative_result":0.08,"compares_with_prior_results":0.26,"mentions_code_or_data_availability":0.04},"evidential_basis":{"p":0.66,"value":"observation or experiment","probabilities":{"argument":0.12,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.66,"simulation_or_computation":0.22}},"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":0.51,"text":"MaSRead addresses the read to content.","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":10,"sentences_in_abstract":10},"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"}}}