{"actions":{"bootstrapAndRun":{"effect":"installs rote if missing, inspects, prepares, and asks before running","href":"https://play.modiqo.ai/install?play=himanshu-jha/cross-split-near-duplicate-leakage@0.1.0","method":"GET","rel":"https://rote.dev/rels/bootstrap-and-run","requiresConsent":true,"responseMediaType":"text/x-shellscript"},"inspect":{"command":"rote play inspect https://play.modiqo.ai/himanshu-jha/cross-split-near-duplicate-leakage@0.1.0","effect":"read-only"},"installCliOnly":{"effect":"installs the rote CLI, nothing else","href":"https://play.modiqo.ai/install","method":"GET","rel":"https://rote.dev/rels/install-cli","requiresConsent":true,"responseMediaType":"text/x-shellscript"},"run":{"command":"rote play run https://play.modiqo.ai/himanshu-jha/cross-split-near-duplicate-leakage@0.1.0","effect":"executes the play locally after consent","headless":{"approvalAssertion":"--yes","approvalRequiredBeforeInvocation":true,"commandTemplate":"rote play run https://play.modiqo.ai/himanshu-jha/cross-split-near-duplicate-leakage@0.1.0 <name=value...> --yes","stdinPolicy":"never pipe input to automate the interactive Ready selector"},"requiresConsent":true}},"description":"Audits dataset contamination across train, validation, and test splits using four distinct evidence layers: exact SHA-256 identity, Unicode/case/URL/number-normalized identity, 64-bit SimHash proximity, and label/group/time conflicts. The join distinguishes proven duplicate leakage from approximate lexical neighbors and emits identifier-and-hash witnesses without exposing record text. JSON, JSONL, labels, grouping keys, timestamps, distance threshold, and record cap are explicit inputs. Custom split names require a complete split_order and chronology remains INDETERMINATE when order or timestamps are missing. It is read-only; SimHash is lexical rather than semantic, and the quadratic near-neighbor pass is deliberately capped so a truncated or oversized audit fails instead of quietly sampling.","distribution":{"digest":"sha256:68c63f45e65263bf1ceb80ce9793af633bdfc57555b9a24ea769a44fa9a77b99","mediaType":"application/vnd.modiqo.rote-flow","size":9885,"verifiedBy":"rote verifies the downloaded archive against this digest before it runs"},"effects":{"credentialsProvidedBy":"runner","credentialsRemainLocal":true,"declaredWrites":[],"publisherReceivesCredentials":false},"id":"https://play.modiqo.ai/himanshu-jha/cross-split-near-duplicate-leakage@0.1.0","inputPolicy":{"optionalWithDefault":"show_default_and_accept_override","optionalWithoutDefault":"omit_unless_supplied","required":"ask","secrets":"collect_locally_outside_conversation"},"license":"MIT","links":{"docs":"https://rote.dev","page":"https://play.modiqo.ai/himanshu-jha/cross-split-near-duplicate-leakage@0.1.0","protocol":"https://play.modiqo.ai/.well-known/rote","self":"https://play.modiqo.ai/himanshu-jha/cross-split-near-duplicate-leakage@0.1.0.json"},"name":"cross-split-near-duplicate-leakage","owner":{"kind":"org","slug":"himanshu-jha"},"parameters":[{"description":"JSON array, object with records, or JSONL containing id, split, text and optional label/group/timestamp. Empty uses the packaged demo.","example":"./labeled-records.jsonl","input":{"allowCustom":true,"choices":[],"label":"Input"},"name":"input","required":false,"type":"string"},{"default":"6","description":"Maximum 64-bit SimHash Hamming distance for a near-duplicate candidate, 0 to 64.","example":"4","input":{"allowCustom":true,"choices":[],"label":"Simhash distance"},"name":"simhash_distance","required":false,"type":"string"},{"default":"5000","description":"Hard record cap for the quadratic cross-split comparison, 2 to 20000. Exceeding it is fatal rather than silently sampling.","example":"10000","input":{"allowCustom":true,"choices":[],"label":"Max records"},"name":"max_records","required":false,"type":"string"}],"preparation":[{"action":{"command":"rote play inspect https://play.modiqo.ai/himanshu-jha/cross-split-near-duplicate-leakage@0.1.0 --json","effect":"read-only"},"step":1,"type":"inspect_local_readiness"},{"references":["/parameters"],"step":2,"type":"collect_parameters"},{"references":["/parameters","/requirements","/effects"],"step":3,"type":"review"},{"consentBoundary":"the user approves the exact play and parameter values","references":["/parameters","/requirements","/effects"],"step":4,"type":"obtain_run_consent"},{"action":{"command":"rote play run https://play.modiqo.ai/himanshu-jha/cross-split-near-duplicate-leakage@0.1.0","headlessCommandTemplate":"rote play run https://play.modiqo.ai/himanshu-jha/cross-split-near-duplicate-leakage@0.1.0 <name=value...> --yes"},"preservesAcquisitionBoundaries":["adapter_selection","oauth_dcr","google_discovery","static_token_setup","runtime_security_checks"],"requiresConsent":true,"step":5,"type":"run"}],"producedBy":{"roteVersion":"0.79.0"},"publishedAt":"2026-09-04T09:06:05.471873+00:00","reference":"himanshu-jha/cross-split-near-duplicate-leakage@0.1.0","requirements":{"adapters":[],"browser":{"dependencies":[],"runtime":false,"signIn":false},"localTools":["python3"],"roteCli":{"minimumVersion":"0.62.0"},"sessions":false},"resolution":"pinned","schema":"rote.play.v1","stats":{"downloads":2,"installs":0},"steps":{"count":5,"names":["assess_cross_split_leakage","compare_normalized_content","detect_label_group_time_conflicts","index_exact_duplicates","search_simhash_neighbors"]},"title":"cross-split-near-duplicate-leakage","type":"play","version":"0.1.0","visibility":"public"}