{"closest_prior_art":[{"name":"Evidence-Ledger Adjudication for Claim-Evidence Traceability","overlap":"Pairs claims with evidence packets, assigns explicit support, contradiction, missing-evidence, or mixed-evidence relations, and routes problematic claims back to authors while drafting.","remaining_difference":"It addresses AI-assisted factual and scientific writing, not collaborative literary interpretation, and does not reconcile a persistent dependency stock across drafts or track aging, promotion into premises, transfers, capacity, delay, or displacement.","source_ids":["SRC1"]},{"name":"Litreviews Claim Ledger","overlap":"A first-party research-writing product explicitly named Claim Ledger binds claims to passages, pages, and quotations; assigns Supported, Weakened, or Untested states; and surfaces contradictions and evidence gaps within a project.","remaining_difference":"It organizes claims in literature reviews but does not model downstream claim dependencies, time-indexed inflow and clearance, balance residuals, age thresholds, cross-document transfers, or editor-capacity controls.","source_ids":["SRC2"]},{"name":"CATMA collaborative literary annotation","overlap":"Supports team-based literary interpretation, customizable theoretical categories, passage-level annotations, and simultaneous alternative interpretations without prescribing a single theoretical answer.","remaining_difference":"Its first-party description does not treat interpretive propositions as an accumulated debt stock, link premise dependencies to dispositions, reconcile weekly flows, or monitor aging and displacement across manuscript locations.","source_ids":["SRC3"]},{"name":"RELiC: Retrieving Evidence for Literary Claims","overlap":"Directly models the relationship between literary-critical claims and supporting passages; its 78,000-example dataset and expert analysis show that literary evidence linkage is common and interpretively complex.","remaining_difference":"It is an evidence-retrieval benchmark rather than a collaborative editorial workflow and does not track unresolved dependencies, contradictions, draft transitions, clearance, age, or transfers.","source_ids":["SRC4"]}],"contrastive_claim_falsifier":"The contrast is falsified if earlier public work is found that already combines, for a collaborative interpretive manuscript, proposition-level dependency tracking with reconciled time-indexed stock and flows, aging, transfer or displacement monitoring, and explicit protection for conjecture and theoretical disagreement. It is also practically falsified if the proposed pilot cannot produce reliable balances or independent coding, or yields no improvement in dependency age, reviewer rediscovery, or traceability beyond a static claim-evidence ledger or collaborative annotation workflow.","contrastive_claim_remaining":"For a collaborative literary-critical manuscript, the still-distinct testable claim is that managing unresolved interpretive dependencies as a persistent, reconciled stock—with recorded creation, promotion, disposition, aging, and cross-location transfers—can improve longitudinal argument traceability beyond static claim-evidence ledgers, argument maps, or collaborative passage annotations while preserving expressly designated conjecture and disagreement.","experiment_id":"eoa_inverse_innovation_exp13_second_slot_policy60_20260806","gates":{"adequate_source_search":{"rationale":"The bounded search covered the proposal directly, claim-ledger and argumentation terminology, older IBIS/ScholOnto/ClaiMaker concepts, literary-annotation products, TEI and W3C annotation standards, manuscript-review practices, and combinations of claims, evidence, contradictions, status, versioning, and transfers. Exactly four retained sources were opened; they span four publishers and include primary research and first-party products.","source_ids":["SRC1","SRC2","SRC3","SRC4"],"status":"PASS"},"bounded_next_test":{"rationale":"The proposed single-project reconstruction and six-week pilot are bounded and measurable. Two independent coders, balance residuals, dependency ages, reviewer rediscovery, and sampled adjacent stores provide explicit feasibility and falsification criteria. The provisional five-item band should be treated as a pilot parameter rather than a truth threshold.","source_ids":["SRC1","SRC3","SRC4"],"status":"PASS"},"distinct_testable_claim":{"rationale":"The retained art covers claim-evidence ledgers, author routing, collaborative literary annotation, competing readings, and literary passage retrieval, but none reports the combined longitudinal stock-flow reconciliation, aging, dependency conversion, transfer accounting, capacity response, and displacement probe proposed here.","source_ids":["SRC1","SRC2","SRC3","SRC4"],"status":"PASS"},"no_obvious_safety_or_authority_stop":{"rationale":"No obvious stop prevents a consenting, read-only reconstruction and reversible pilot. Human contributors retain substantive claim authority; numerical status cannot determine interpretive truth; conjecture and disagreement are protected; and the stated halt conditions address suppression, category instability, displacement, and administrative burden. CATMA provides adjacent evidence that collaborative tooling can accommodate multiple interpretations.","source_ids":["SRC3"],"status":"PASS"},"supported_problem":{"rationale":"The underlying problem is visible: current research-writing systems explicitly address unsupported, contradicted, mixed, or scattered claims; one primary study says reviewers often encounter such defects late; and RELiC demonstrates that linking literary claims to textual evidence is a complex interpretive task. However, the retained evidence does not directly establish that unresolved interpretive dependencies accumulate, age, and migrate across successive collaborative literary drafts, so support is partial rather than complete.","source_ids":["SRC1","SRC2","SRC4"],"status":"PASS"}},"prior_art_disposition":"ADJACENT_PRIOR_ART","problem_evidence":{"finding":"Public evidence supports the existence and practical salience of claim-evidence gaps, contradictions, late reviewer discovery, and difficult literary claim-to-passage linkage. It does not directly measure the proposal's narrower longitudinal phenomenon: a separable stock of unresolved interpretive dependencies persisting and migrating across collaborative drafts.","source_ids":["SRC1","SRC2","SRC4"],"status":"PARTLY_SUPPORTED"},"research_id":"eoa_inverse_innovation_exp13_light_screen_20260806","schema_version":1,"screen_id":"E13P120","screen_survival":true,"search_lanes":{"component_combination":{"no_result_note":null,"queries":["claim evidence contradictions status tracking across drafts manuscript review","argument mapping version history unresolved claims editorial workflow","unresolved interpretive claims drafts literary criticism workflow evidence ledger","site:w3.org/TR annotation data model text scholarly annotation provenance"],"source_ids":["SRC1","SRC2","SRC4"]},"direct_problem_and_intervention":{"no_result_note":"No exact literary-critical implementation combining a claim-debt ledger with reconciled stock-flow accounting, aging, capacity bands, and transfer-displacement monitoring surfaced; this phrase-level miss is not treated as evidence of novelty.","queries":["\"interpretive claim\" ledger literary criticism argument dependencies drafts","\"claim ledger\" research writing evidence contradiction","literary argument mapping textual evidence claims collaborative annotation scholarly writing"],"source_ids":["SRC1","SRC2","SRC4"]},"products_practices_and_standards":{"no_result_note":null,"queries":["claim evidence warrant matrix literary analysis writing tool","site:tei-c.org critical apparatus competing readings annotation guidelines","site:w3.org/TR annotation data model text scholarly annotation provenance","literary scholarship collaborative annotation claims evidence CATMA argument"],"source_ids":["SRC2","SRC3"]},"synonyms_and_historical_terms":{"no_result_note":null,"queries":["scholarly argumentation system claim evidence relationships ClaiMaker ScholOnto","IBIS issue based information system unresolved issues version history scholarly writing","argumentation scholarly writing claim lifecycle status unresolved contradiction software","collaborative indeterministic literary annotation competing interpretations"],"source_ids":["SRC3"]}},"sources":[{"claims_supported":["AI-assisted writing can produce claims faster than authors can assess their evidence, and reviewers may encounter unsupported or contradicted claims late.","Evidence-ledger adjudication records a claim, evidence packet, support relation, review route, confidence, and rationale.","A 2,335-row blind benchmark tested routing of supported, contradicted, missing-evidence, and mixed-evidence claims."],"publisher":"arXiv; Gengyu Chen, Yongjie Yu, and Weiling Wang","source_id":"SRC1","source_type":"PRIMARY_RESEARCH","title":"Evidence-Ledger Adjudication for Claim-Evidence Traceability","url":"https://arxiv.org/abs/2607.26512"},{"claims_supported":["The product uses a named Claim Ledger that binds claims to exact evidence, pages, and quotations.","Claims receive Supported, Weakened, or Untested states, and the system surfaces contradictions, unsupported areas, and other coverage gaps.","The workflow is scoped to a research project and intended to expose weaknesses before later review."],"publisher":"Litreviews","source_id":"SRC2","source_type":"FIRST_PARTY_PRODUCT","title":"Litreviews — grounded AI for literature reviews","url":"https://www.litreviews.ai/lp"},{"claims_supported":["CATMA supports collaborative, project-centered literary annotation and customizable interpretive categories.","It permits multiple annotations and alternative interpretations of the same passage and describes its approach as undogmatic.","Its workflow is designed for humanities text analysis by individuals or teams."],"publisher":"CATMA project","source_id":"SRC3","source_type":"FIRST_PARTY_PRODUCT","title":"CATMA — Computer Assisted Text Markup and Analysis","url":"https://catma.de/"},{"claims_supported":["Literary scholars commonly use quotations from primary texts as evidence for interpretive claims.","RELiC contains approximately 78,000 quotations with surrounding critical analysis and was evaluated with human domain experts.","The relationship between literary claims and appropriate textual passages can require complex reasoning involving irony, metaphor, paraphrase, and other contextual phenomena."],"publisher":"Association for Computational Linguistics","source_id":"SRC4","source_type":"PRIMARY_RESEARCH","title":"RELiC: Retrieving Evidence for Literary Claims","url":"https://aclanthology.org/2022.acl-long.517/"}],"world_novelty_boundary":"This bounded screen found adjacent claim-evidence ledgers, manuscript-routing research, collaborative literary annotation, and literary evidence retrieval, but no opened retained source implementing the proposal's full longitudinal stock-flow control. That result establishes only a residual contrast for further testing; it cannot establish world novelty, patentability, market size, expert acceptance, or realized value."}