{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G3SKPAV6VCLH5RAJYPQKH7KOYI","short_pith_number":"pith:G3SKPAV6","schema_version":"1.0","canonical_sha256":"36e4a782bea8967ec409c3e0a3fd4ec23559030799fbe1b454cd80250607c4a6","source":{"kind":"arxiv","id":"2606.26016","version":1},"attestation_state":"computed","paper":{"title":"MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Limin Wang, Qiushi Guo, Shuai Wang, Tiezheng Ge, Xiaowei Xu, Xinwen Zhang, Yang Chen","submitted_at":"2026-06-24T16:37:10Z","abstract_excerpt":"Normalizing Flows (NFs) are powerful generative models capable of exact density estimation and sampling. However, their strict invertibility often forces the model to exhaust its capacity on low-level pixel details, hindering the capture of high-level semantic structures. While Masked Image Modeling (MIM) has excelled in representation learning, its integration into generative pipelines has remained largely modular and disjointed. In this paper, we propose MIMFlow, a unified end-to-end framework that jointly optimizes latent semantics, pixel reconstruction, and generative flow. By employing a "},"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":"2606.26016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-24T16:37:10Z","cross_cats_sorted":[],"title_canon_sha256":"1dda3d01c334e6109cdd97714ad8df1ca7d554123d914a5c66d67fcececafd0b","abstract_canon_sha256":"6f65dc07467e2ffde1470144821824f0340ac2b925933bc1cb427bb3f56e6f45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:45.962753Z","signature_b64":"aabeuQgTUMwd0Bo5EVnAtnWbeRzptrRuta0/EXruwkij1esPaSeH26mkazMLE0aGz6kdeBaO7qK4JYkb8O9hDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36e4a782bea8967ec409c3e0a3fd4ec23559030799fbe1b454cd80250607c4a6","last_reissued_at":"2026-06-25T01:18:45.962345Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:45.962345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Limin Wang, Qiushi Guo, Shuai Wang, Tiezheng Ge, Xiaowei Xu, Xinwen Zhang, Yang Chen","submitted_at":"2026-06-24T16:37:10Z","abstract_excerpt":"Normalizing Flows (NFs) are powerful generative models capable of exact density estimation and sampling. However, their strict invertibility often forces the model to exhaust its capacity on low-level pixel details, hindering the capture of high-level semantic structures. While Masked Image Modeling (MIM) has excelled in representation learning, its integration into generative pipelines has remained largely modular and disjointed. In this paper, we propose MIMFlow, a unified end-to-end framework that jointly optimizes latent semantics, pixel reconstruction, and generative flow. By employing a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26016","kind":"arxiv","version":1},"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/2606.26016/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":"2606.26016","created_at":"2026-06-25T01:18:45.962410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26016v1","created_at":"2026-06-25T01:18:45.962410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26016","created_at":"2026-06-25T01:18:45.962410+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3SKPAV6VCLH","created_at":"2026-06-25T01:18:45.962410+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3SKPAV6VCLH5RAJ","created_at":"2026-06-25T01:18:45.962410+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3SKPAV6","created_at":"2026-06-25T01:18:45.962410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G3SKPAV6VCLH5RAJYPQKH7KOYI","json":"https://pith.science/pith/G3SKPAV6VCLH5RAJYPQKH7KOYI.json","graph_json":"https://pith.science/api/pith-number/G3SKPAV6VCLH5RAJYPQKH7KOYI/graph.json","events_json":"https://pith.science/api/pith-number/G3SKPAV6VCLH5RAJYPQKH7KOYI/events.json","paper":"https://pith.science/paper/G3SKPAV6"},"agent_actions":{"view_html":"https://pith.science/pith/G3SKPAV6VCLH5RAJYPQKH7KOYI","download_json":"https://pith.science/pith/G3SKPAV6VCLH5RAJYPQKH7KOYI.json","view_paper":"https://pith.science/paper/G3SKPAV6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26016&json=true","fetch_graph":"https://pith.science/api/pith-number/G3SKPAV6VCLH5RAJYPQKH7KOYI/graph.json","fetch_events":"https://pith.science/api/pith-number/G3SKPAV6VCLH5RAJYPQKH7KOYI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3SKPAV6VCLH5RAJYPQKH7KOYI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3SKPAV6VCLH5RAJYPQKH7KOYI/action/storage_attestation","attest_author":"https://pith.science/pith/G3SKPAV6VCLH5RAJYPQKH7KOYI/action/author_attestation","sign_citation":"https://pith.science/pith/G3SKPAV6VCLH5RAJYPQKH7KOYI/action/citation_signature","submit_replication":"https://pith.science/pith/G3SKPAV6VCLH5RAJYPQKH7KOYI/action/replication_record"}},"created_at":"2026-06-25T01:18:45.962410+00:00","updated_at":"2026-06-25T01:18:45.962410+00:00"}