{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L2RNAOU4BL324B4WDDZ7QJD77T","short_pith_number":"pith:L2RNAOU4","schema_version":"1.0","canonical_sha256":"5ea2d03a9c0af7ae079618f3f8247ffccecdac1f21848c92eb3cf5fc041631c2","source":{"kind":"arxiv","id":"2603.13421","version":2},"attestation_state":"computed","paper":{"title":"Generalization and Memorization in Rectified Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Daniel Moyer, Mingxing Rao","submitted_at":"2026-03-12T21:10:39Z","abstract_excerpt":"Generative models based on the Flow Matching objective, particularly Rectified Flow, have emerged as a dominant paradigm for efficient, high-fidelity image synthesis. However, while existing research heavily prioritizes generation quality and architectural scaling, the underlying dynamics of how RF models memorize training data remain largely underexplored. In this paper, we systematically investigate the memorization behaviors of RF through the test statistics of Membership Inference Attacks (MIA). We progressively formulate three test statistics, culminating in a complexity-calibrated metric"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2603.13421","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-12T21:10:39Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"50179f2461f828b27912fe7e77f29f9c27fecea037dcb3365adde8be7452a7e5","abstract_canon_sha256":"b0ed202eba6f5bed27c369d858a87477bf60e4aed8749b6bf3e4e3b2ee915772"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T00:21:17.678258Z","signature_b64":"5HylMuvDCgbUNMFZhlBpfPnkaD4GzbeYHU70b1XzwmC3IH5/qkC+cRA6ZFPlGFTk0bWncB297PXQC9VXgqdOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ea2d03a9c0af7ae079618f3f8247ffccecdac1f21848c92eb3cf5fc041631c2","last_reissued_at":"2026-07-15T00:21:17.677351Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T00:21:17.677351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization and Memorization in Rectified Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Daniel Moyer, Mingxing Rao","submitted_at":"2026-03-12T21:10:39Z","abstract_excerpt":"Generative models based on the Flow Matching objective, particularly Rectified Flow, have emerged as a dominant paradigm for efficient, high-fidelity image synthesis. However, while existing research heavily prioritizes generation quality and architectural scaling, the underlying dynamics of how RF models memorize training data remain largely underexplored. In this paper, we systematically investigate the memorization behaviors of RF through the test statistics of Membership Inference Attacks (MIA). We progressively formulate three test statistics, culminating in a complexity-calibrated metric"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.13421","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.13421/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2603.13421","created_at":"2026-07-15T00:21:17.677777+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.13421v2","created_at":"2026-07-15T00:21:17.677777+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.13421","created_at":"2026-07-15T00:21:17.677777+00:00"},{"alias_kind":"pith_short_12","alias_value":"L2RNAOU4BL32","created_at":"2026-07-15T00:21:17.677777+00:00"},{"alias_kind":"pith_short_16","alias_value":"L2RNAOU4BL324B4W","created_at":"2026-07-15T00:21:17.677777+00:00"},{"alias_kind":"pith_short_8","alias_value":"L2RNAOU4","created_at":"2026-07-15T00:21:17.677777+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.08554","citing_title":"A Theoretical Analysis of Memory and Overfitting Phenomena in Stochastic Interpolation Models","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L2RNAOU4BL324B4WDDZ7QJD77T","json":"https://pith.science/pith/L2RNAOU4BL324B4WDDZ7QJD77T.json","graph_json":"https://pith.science/api/pith-number/L2RNAOU4BL324B4WDDZ7QJD77T/graph.json","events_json":"https://pith.science/api/pith-number/L2RNAOU4BL324B4WDDZ7QJD77T/events.json","paper":"https://pith.science/paper/L2RNAOU4"},"agent_actions":{"view_html":"https://pith.science/pith/L2RNAOU4BL324B4WDDZ7QJD77T","download_json":"https://pith.science/pith/L2RNAOU4BL324B4WDDZ7QJD77T.json","view_paper":"https://pith.science/paper/L2RNAOU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.13421&json=true","fetch_graph":"https://pith.science/api/pith-number/L2RNAOU4BL324B4WDDZ7QJD77T/graph.json","fetch_events":"https://pith.science/api/pith-number/L2RNAOU4BL324B4WDDZ7QJD77T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L2RNAOU4BL324B4WDDZ7QJD77T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L2RNAOU4BL324B4WDDZ7QJD77T/action/storage_attestation","attest_author":"https://pith.science/pith/L2RNAOU4BL324B4WDDZ7QJD77T/action/author_attestation","sign_citation":"https://pith.science/pith/L2RNAOU4BL324B4WDDZ7QJD77T/action/citation_signature","submit_replication":"https://pith.science/pith/L2RNAOU4BL324B4WDDZ7QJD77T/action/replication_record"}},"created_at":"2026-07-15T00:21:17.677777+00:00","updated_at":"2026-07-15T00:21:17.677777+00:00"}