{"id":"bdf3b7f6-64a7-4f01-8015-6551643e9d43","arxiv_id":"2611.16492","paper_version":1,"verdict":"CONDITIONAL","confidence":"HIGH","novelty_score":6.0,"correctness_risk":"medium","formal_verification":"none","parameter_count":3,"one_line_summary":"A specification and partial prototype of a context substrate for personal agents that separates event time from ingestion time, preserves ambiguity as data, and requires every answer to be closed over immutable source records.","lead":"This paper argues that personal agents are limited not by model size but by how they represent context. It proposes a spatio-temporal context substrate with formal invariants and operators to make agent memory auditable, temporally aware, and ambiguity-preserving.","discovery_kind":"extension","skeptic_critique":{"model":"deepseek/deepseek-v4-flash","headline":"Ambiguity preservation's product-of-candidates complexity may cap practical utility at low ambiguity levels, and the paper provides no evidence that personal data's ambiguity is within that cap.","rationale":"The reader's weakest assumption focused on the reliability of extraction and entity resolution models. While valid, I believe the more load-bearing internal design concern is the feasibility of ambiguity preservation itself under realistic ambiguity counts. The paper acknowledges the complexity but does not assess whether personal data's typical ambiguity structure fits within the proposed cap. This gap directly threatens the central claim that the substrate enables ambiguity-respecting behavior, because if ambiguity is not tractably preservable (or leads to excessive user disambiguation), the advantage over ingestion-time resolution collapses. The test I propose would directly measure whether the cap assumption holds. The reader's verdict (CONDITIONAL) is appropriate; this concern does not change it, but it sharpens the condition under which the design could be validated.","tokens_in":18662,"tokens_out":1573,"duration_ms":15416,"concrete_test":"Construct a synthetic dataset of 50 personal queries derived from a family history that includes 3–4 ambiguous mentions per query (e.g., multiple 'mom' references from different contexts, a common surname used for two people, and a pronoun with multiple candidates). Implement the answer-consistency test as specified (enumerate all candidate combinations) and measure: (1) the proportion of queries that exceed the two-mention cap, (2) the number of candidate combinations per query (product of set sizes), and (3) the fraction of queries that produce a disambiguation request vs. a definitive answer. Compare against a baseline that resolves at ingestion time by picking the most frequent entity. If more than 20% of queries exceed the cap or produce combinatorial explosion (product > 100), the substrate's utility is severely limited without a cheaper method that has not been demonstrated.","verdict_should_be":"UNCHANGED","load_bearing_attack":"The paper's central claim that the substrate enables ambiguity-respecting agent behavior depends critically on invariant I5 (ambiguity preservation) and the answer-consistency test of Section 5.2. The test assembles the product of candidate-set sizes for each ambiguous mention; the paper acknowledges this cost and caps expansion at two mentions (Section 5.2, 'the prototype therefore caps j at two' and Section 10: 'which is why the prototype caps the expansion at two mentions'). However, personal data may routinely involve more than two ambiguous mentions per query (multiple 'mom', 'he', 'my coworker' references across records). The paper provides no analysis or evidence that real personal queries fall within the cap, nor any validation of the claim that a cheaper version ranking candidates by expected answer change would work (Section 10: 'A cheaper version would rank candidates by the expected change in the answer, and we have not implemented one'). Without such evidence, the feasibility of the substrate for realistic ambiguity is untested. This is a load-bearing gap because the alternative—resolving at ingestion time—is explicitly rejected as error-prone (invariant I5 rationale), yet the proposed alternative may be computationally prohibitive or user-pedantic in practice.","agreement_with_reader":"partial"},"referee_report":{"model":"deepseek/deepseek-v4-flash","summary":"This paper argues that the primary limitation for personal AI agents is not model capacity but the representation of context. It proposes a spatio-temporal context (STC) substrate with six invariants (record primacy, multi-time, provenance totality, open-world validity, ambiguity preservation, scope isolation). The substrate combines a temporal axis (event time, validity intervals, ingestion time) with a spatial axis (relational entity graph). The paper defines operators: a context operator composing temporal intersection and relational expansion, an ambiguity-preserving answer-consistency test, a functional-conflict detector, an evidence-closure rule, and a trigger rule for proactive reminders. It also presents a four-regime consumption taxonomy (query, insight, triage, reminder). The authors describe a local-first prototype of the retrieval layer (SQLite, on-device embeddings, hybrid lexical-dense recall) with measurements on a deployed store of 341 documents and 190,271 vectors. The analytic layer (entity graph, relation extraction, conflict detection, evidence closure) is specified but not implemented. The paper closes with an evaluation protocol with per-invariant metrics, none of which have been run.","tokens_in":20440,"tokens_out":1502,"duration_ms":33966,"significance":"If the proposed representation and invariants prove effective, this work could shift the design focus for personal agents from scaling models to structuring context. The clear formalization of six invariants, the answer-consistency test that preserves ambiguity, and the functional-conflict detector are novel contributions. The retrieval-layer prototype demonstrates that a local-first, privacy-preserving store can achieve reasonable recall latency. The paper is honest about its status as a design proposal with an unimplemented analytic layer, which limits immediate practical impact but provides a rigorous blueprint for future work. The evaluation protocol is thoughtful and addresses key failure modes (unsupported claims, interruption cost).","major_comments":[{"comment":"The ambiguity preservation invariant (I5) and the answer-consistency test are central to the paper's claim of enabling ambiguity-respecting behavior. The test assembles the product of candidate-set sizes for ambiguous mentions, and the authors cap expansion at two mentions (Section 5.2). They acknowledge this is unsolved (Section 10: 'the calibration of when to ask is unsolved') and note that a cheaper ranking alternative has not been implemented. However, the paper provides no analysis or evidence that real personal queries typically involve two or fewer ambiguous mentions, nor that the cap does not exclude many realistic queries. Without such validation, the feasibility of the substrate for actual personal data is untested, which weakens the central claim. The authors should either provide evidence (e.g., analysis of ambiguity patterns in personal data, even from a small pilot) or discuss this limitation more directly in terms of the claim's scope.","section":"§5.2, §10","authors_acknowledge":"Ambiguity preservation pushes work into the answering policy, where it becomes a user-visible question; a user who is asked to disambiguate too often will experience the agent as pedantic, and the calibration of when to ask is unsolved.","authors_acknowledge_p":0.68},{"comment":"The evaluation protocol is specified but not executed. While this is clearly stated, the paper would be significantly strengthened by a small-scale feasibility test of at least one invariant (e.g., evidence closure or temporal accuracy on a minimal constructed set). The absence of any empirical validation for the analytic layer's core mechanisms (conflict detection, evidence closure verification) means the design's effectiveness remains entirely conjectural. I suggest the authors consider a proof-of-concept experiment on a small, carefully annotated dataset to demonstrate the operators in action, even if limited.","section":"§9","authors_acknowledge":"The analytic layer of Section 7.3 is specified, not implemented.","authors_acknowledge_p":0.91}],"minor_comments":[{"comment":"Table 1 is clear and informative. However, the row for 'This framework (proposed)' lists capabilities that are specified but not implemented. The footnote in Section 2.5 acknowledges this, but the table might mislead readers about the current state. Consider adding a visual marker (e.g., asterisk) to indicate that the last row denotes a design rather than an evaluated system.","section":"§2.3, Table 1","authors_acknowledge":null,"authors_acknowledge_p":null},{"comment":"The six invariants are well-defined, but the wording of I4 ('Open-world validity') could be slightly clearer. The current text says 'An open right endpoint means \"still true as far as known\", never \"current\" or \"invalid\".' This is correct, but the sentence might be misinterpreted as 'open right endpoint means the fact is still true', whereas it means 'the system does not know when it stopped being true'. Consider rephrasing to emphasize ignorance rather than truth.","section":"§4.3, Table 2","authors_acknowledge":null,"authors_acknowledge_p":null},{"comment":"The retrieval measurements are presented clearly, but the number of queries (24) is very small. While the median and p95 are reported, the small sample size limits generalizability. Please note this constraint explicitly, as has been done for other limitations.","section":"§7.2","authors_acknowledge":null,"authors_acknowledge_p":null},{"comment":"In Definition 1, the field 'w' (scope) appears but is not defined before its use; scope is defined later in Definition 5. Consider moving Definition 5 earlier or adding a forward reference.","section":"§1, §3.1","authors_acknowledge":null,"authors_acknowledge_p":null},{"comment":"Figure 2 is a schematic demonstration of a semantic space. The caption correctly states that positions and probabilities are preset and not from a trained model. However, the relevance of this figure to the paper's argument is unclear. It seems to illustrate a conceptual point about semantic geometry, but it is not referenced in the main text outside Section 4.2, where it is described as an 'explanatory device'. Consider removing or moving to an appendix to avoid confusion.","section":"Figure 2","authors_acknowledge":null,"authors_acknowledge_p":null}],"recommendation":"major_revision"},"author_rebuttal":null,"desk_editor":{"model":"deepseek/deepseek-v4-flash","letter":"This paper is a well-specified design for a spatio-temporal context substrate for personal agents. Its main contribution is a crisp set of six invariants (record primacy, multi-time, provenance totality, open-world validity, ambiguity preservation, scope isolation), a context operator that composes temporal intersection with relational expansion, and a four-regime consumption taxonomy. The literature positioning is careful, and the authors are transparent about what is implemented and what is not: the retrieval layer runs on a real store and has plausible timings, but the analytic layer (entity graph, relation extraction, conflict detection, evidence-closure verification) is only specified. That is the paper's load-bearing limitation, and the authors say so explicitly in the abstract and repeatedly throughout.\n\nThe stress-test concern about ambiguity preservation's product-of-candidates complexity is real, but the paper already acknowledges it (Section 5.2 caps expansion at two mentions, Section 10 notes the calibration is unsolved). The paper does not provide evidence that personal queries stay within that cap, which is a genuine gap. The reader's verdict of CONDITIONAL is fair: the design is coherent and the invariants are interesting, but the central claim that the substrate reduces unsupported answers or improves temporal questions is untested. The evaluation protocol is specified but not run.\n\nWhat the paper does well: it identifies a real problem (context representation for personal agents), defines precise invariants that any solution must satisfy, and provides a clean operator algebra. The walkthrough (Section 8) is instructive, even though invented. The limitation discussion is thorough and honest.\n\nThe soft spots are the ones the authors state: the analytic layer is missing, the cost of ambiguity preservation at scale is unclear, and no user study exists. The paper is a design proposal, not a validated system. For a reader interested in architectures for personal agents, this is a serious, well-reasoned proposal that deserves engagement.\n\nRecommendation: this paper deserves peer review as a design contribution. A responsible editor would send it to reviewers who can evaluate the specification and the feasibility of the design, with the expectation that the authors will need to implement at least one invariant-checking component or run part of the protocol before the paper could appear. The paper is not yet publishable as a systems paper, but as a design statement it is substantive and clearly argued.","headline":"A thoughtful design proposal for personal agent context, but the analytic layer that would validate the core claims is specified, not implemented, and the paper is upfront about this.","tokens_in":19558,"tokens_out":1146,"duration_ms":10965},"pith_extraction":null,"created_at":"2026-11-13T14:46:16.710698+00:00","model_set":{"reader":"deepseek/deepseek-v4-flash"},"pipeline_version":"pith-pipeline@v1.4.1-daily-deepseek-or-medium","input_kind":null,"input_chars":null,"input_total_chars":null,"passes_missing":null,"published_standing":null,"published_confidence":null,"objection_audit":null,"run_record":null,"basis":{"kind":"not_recorded","source":null,"chars_given":null,"chars_total":null},"receipt":null,"falsifier":null,"supporting_citations":[],"lane_accuracy":{"status":"not yet measured","lane":{"model":"deepseek/deepseek-v4-flash","input_kind":null},"url":"https://pith.science/accuracy"},"review_version":1}