{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OE3BD6IUOFUDME4D6X4GF7Y3XI","short_pith_number":"pith:OE3BD6IU","schema_version":"1.0","canonical_sha256":"713611f9147168361383f5f862ff1bba279c7635b34a4e8e0a0c87bad09f2ea5","source":{"kind":"arxiv","id":"2605.15856","version":1},"attestation_state":"computed","paper":{"title":"crossfit: A Graph-Based Cross-Fitting Engine in R","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The crossfit R package provides a general-purpose cross-fitting engine using user-specified DAGs of nuisance models with custom fold allocations.","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Etienne Peyrot, Fran\\c{c}ois Petit","submitted_at":"2026-05-15T11:14:55Z","abstract_excerpt":"Cross-fitting is a key ingredient in many semiparametric estimation procedures, such as double/debiased machine learning (DML), enabling valid estimation of low-dimensional targets in the presence of high-dimensional nuisance functions by enforcing out-of-sample use of nuisance predictions. crossfit is an R package that provides a general-purpose, estimator-agnostic cross-fitting engine. Users specify (i) a target functional and (ii) a directed acyclic graph (DAG) of nuisance models, with node-specific training fold widths and target-specific evaluation windows. The engine executes a reproduci"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.15856","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2026-05-15T11:14:55Z","cross_cats_sorted":[],"title_canon_sha256":"ef6b457f1509f259716dd98a2fedfc400d203fa9d93b087bf80252c96b310670","abstract_canon_sha256":"e7928e7de4ac86834cdb4cea464111014de9704c5fc55b941bbeb9b3bab16d58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:22.188041Z","signature_b64":"OU5U9+n7EIcMeXF6UtVWHe/QWj9RVwT7sBkSmUe+TxN6W+1/x9AJrcvCbfcDKW80vqqRGMqJuXiieb/tCUZ8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"713611f9147168361383f5f862ff1bba279c7635b34a4e8e0a0c87bad09f2ea5","last_reissued_at":"2026-05-20T00:01:22.187183Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:22.187183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"crossfit: A Graph-Based Cross-Fitting Engine in R","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The crossfit R package provides a general-purpose cross-fitting engine using user-specified DAGs of nuisance models with custom fold allocations.","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Etienne Peyrot, Fran\\c{c}ois Petit","submitted_at":"2026-05-15T11:14:55Z","abstract_excerpt":"Cross-fitting is a key ingredient in many semiparametric estimation procedures, such as double/debiased machine learning (DML), enabling valid estimation of low-dimensional targets in the presence of high-dimensional nuisance functions by enforcing out-of-sample use of nuisance predictions. crossfit is an R package that provides a general-purpose, estimator-agnostic cross-fitting engine. Users specify (i) a target functional and (ii) a directed acyclic graph (DAG) of nuisance models, with node-specific training fold widths and target-specific evaluation windows. The engine executes a reproduci"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"crossfit is an R package that provides a general-purpose, estimator-agnostic cross-fitting engine. Users specify (i) a target functional and (ii) a directed acyclic graph (DAG) of nuisance models, with node-specific training fold widths and target-specific evaluation windows.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The package's internal scheduler and caching logic correctly execute the user-specified DAG and fold-allocation rules without introducing unintended data leakage or dependence between nuisance branches, as stated in the description of disjoint and independence-enforcing modes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"crossfit is an R package that supplies a general-purpose cross-fitting engine driven by user-specified DAGs of nuisance models with configurable fold allocations and reproducibility features.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The crossfit R package provides a general-purpose cross-fitting engine using user-specified DAGs of nuisance models with custom fold allocations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c304fec5a643e53050b0bdf1ec2e782b72c891685f913ac54be714a7ce525bd1"},"source":{"id":"2605.15856","kind":"arxiv","version":1},"verdict":{"id":"fa9a1620-11ba-46b8-ad00-3dcee3c132ed","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T18:03:16.118805Z","strongest_claim":"crossfit is an R package that provides a general-purpose, estimator-agnostic cross-fitting engine. Users specify (i) a target functional and (ii) a directed acyclic graph (DAG) of nuisance models, with node-specific training fold widths and target-specific evaluation windows.","one_line_summary":"crossfit is an R package that supplies a general-purpose cross-fitting engine driven by user-specified DAGs of nuisance models with configurable fold allocations and reproducibility features.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The package's internal scheduler and caching logic correctly execute the user-specified DAG and fold-allocation rules without introducing unintended data leakage or dependence between nuisance branches, as stated in the description of disjoint and independence-enforcing modes.","pith_extraction_headline":"The crossfit R package provides a general-purpose cross-fitting engine using user-specified DAGs of nuisance models with custom fold allocations."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15856/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T18:31:18.773741Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T18:10:15.757060Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:48.703845Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:01:55.823110Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"53e50145ab7ff487023ce04a3d13a37cd2c094d7c660088fdb244f374ae541b9"},"references":{"count":15,"sample":[{"doi":"10.1214/aos/","year":1982,"title":"doi: 10.1214/aos/ 1176342360","work_id":"5bd55533-e64d-4884-b62b-14c429566078","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1214/aos/1176350055","year":1986,"title":"On Asymptotically Efficient Estimation in Semiparametric Models","work_id":"dec623fd-0fa8-4c67-bc86-16b9e1bc5fd2","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2011,"title":"Cross-Validated Targeted Minimum- Loss-Based Estimation","work_id":"90899aad-2f56-41ca-a394-455d3d3ebae3","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"arXiv preprint arXiv:1801.09138 , year=","work_id":"2a799d79-cace-45bb-98a8-de5ca7ea05f3","ref_index":4,"cited_arxiv_id":"1801.09138","is_internal_anchor":true},{"doi":"10.1111/ectj.12097","year":2018,"title":"Double/debiased machine learning for treatment and structural parameters.The Econometrics Journal, 21(1):C1–C68","work_id":"f1c0cebd-ff53-46ac-aa98-210211b3f171","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":15,"snapshot_sha256":"bbc0bf62988443cf2ed9f038af09d84a144abdcfea75d5ba5eecd318524a7163","internal_anchors":1},"formal_canon":{"evidence_count":1,"snapshot_sha256":"e73a6c647392ac05f4e8ba0795dd1dcc423d488ec9ac93b06ae50c549a15ac92"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.15856","created_at":"2026-05-20T00:01:22.187334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15856v1","created_at":"2026-05-20T00:01:22.187334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15856","created_at":"2026-05-20T00:01:22.187334+00:00"},{"alias_kind":"pith_short_12","alias_value":"OE3BD6IUOFUD","created_at":"2026-05-20T00:01:22.187334+00:00"},{"alias_kind":"pith_short_16","alias_value":"OE3BD6IUOFUDME4D","created_at":"2026-05-20T00:01:22.187334+00:00"},{"alias_kind":"pith_short_8","alias_value":"OE3BD6IU","created_at":"2026-05-20T00:01:22.187334+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OE3BD6IUOFUDME4D6X4GF7Y3XI","json":"https://pith.science/pith/OE3BD6IUOFUDME4D6X4GF7Y3XI.json","graph_json":"https://pith.science/api/pith-number/OE3BD6IUOFUDME4D6X4GF7Y3XI/graph.json","events_json":"https://pith.science/api/pith-number/OE3BD6IUOFUDME4D6X4GF7Y3XI/events.json","paper":"https://pith.science/paper/OE3BD6IU"},"agent_actions":{"view_html":"https://pith.science/pith/OE3BD6IUOFUDME4D6X4GF7Y3XI","download_json":"https://pith.science/pith/OE3BD6IUOFUDME4D6X4GF7Y3XI.json","view_paper":"https://pith.science/paper/OE3BD6IU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15856&json=true","fetch_graph":"https://pith.science/api/pith-number/OE3BD6IUOFUDME4D6X4GF7Y3XI/graph.json","fetch_events":"https://pith.science/api/pith-number/OE3BD6IUOFUDME4D6X4GF7Y3XI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OE3BD6IUOFUDME4D6X4GF7Y3XI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OE3BD6IUOFUDME4D6X4GF7Y3XI/action/storage_attestation","attest_author":"https://pith.science/pith/OE3BD6IUOFUDME4D6X4GF7Y3XI/action/author_attestation","sign_citation":"https://pith.science/pith/OE3BD6IUOFUDME4D6X4GF7Y3XI/action/citation_signature","submit_replication":"https://pith.science/pith/OE3BD6IUOFUDME4D6X4GF7Y3XI/action/replication_record"}},"created_at":"2026-05-20T00:01:22.187334+00:00","updated_at":"2026-05-20T00:01:22.187334+00:00"}