{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SIOTHIFQ33EI6SSDNQTNEG74FT","short_pith_number":"pith:SIOTHIFQ","schema_version":"1.0","canonical_sha256":"921d33a0b0dec88f4a436c26d21bfc2cfc58be977a5707c9f2b89c42931897c1","source":{"kind":"arxiv","id":"2505.11825","version":1},"attestation_state":"computed","paper":{"title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Xudong Ma","submitted_at":"2025-05-17T04:17:48Z","abstract_excerpt":"Training diffusion models requires large datasets. However, acquiring large volumes of high-quality data can be challenging, for example, collecting large numbers of high-resolution images and long videos. On the other hand, there are many complementary data that are usually considered corrupted or partial, such as low-resolution images and short videos. Other examples of corrupted data include videos that contain subtitles, watermarks, and logos. In this study, we investigate the theoretical problem of whether the above partial data can be utilized to train conventional diffusion models. Moti"},"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":"2505.11825","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-17T04:17:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4e072fdfe345e411ae24ab431d89d2341c1ae747a2b5611f9d258733dc7c33db","abstract_canon_sha256":"ad8072b124d83058acf6d4edad24cd48dec3ecd2c70e00fdf8b25d9bae507a72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:27.157923Z","signature_b64":"HIi3M69E94pJJI19C7A/SaKN9oUAJ++3G7hJgb7/cDqETKc0gnf3JqpyBygLw8VwXnva6BiQruOi7Q4mFfL8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"921d33a0b0dec88f4a436c26d21bfc2cfc58be977a5707c9f2b89c42931897c1","last_reissued_at":"2026-07-05T11:04:27.157402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:27.157402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Xudong Ma","submitted_at":"2025-05-17T04:17:48Z","abstract_excerpt":"Training diffusion models requires large datasets. However, acquiring large volumes of high-quality data can be challenging, for example, collecting large numbers of high-resolution images and long videos. On the other hand, there are many complementary data that are usually considered corrupted or partial, such as low-resolution images and short videos. Other examples of corrupted data include videos that contain subtitles, watermarks, and logos. In this study, we investigate the theoretical problem of whether the above partial data can be utilized to train conventional diffusion models. Moti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11825","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/2505.11825/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":"2505.11825","created_at":"2026-07-05T11:04:27.157469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11825v1","created_at":"2026-07-05T11:04:27.157469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11825","created_at":"2026-07-05T11:04:27.157469+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIOTHIFQ33EI","created_at":"2026-07-05T11:04:27.157469+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIOTHIFQ33EI6SSD","created_at":"2026-07-05T11:04:27.157469+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIOTHIFQ","created_at":"2026-07-05T11:04:27.157469+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/SIOTHIFQ33EI6SSDNQTNEG74FT","json":"https://pith.science/pith/SIOTHIFQ33EI6SSDNQTNEG74FT.json","graph_json":"https://pith.science/api/pith-number/SIOTHIFQ33EI6SSDNQTNEG74FT/graph.json","events_json":"https://pith.science/api/pith-number/SIOTHIFQ33EI6SSDNQTNEG74FT/events.json","paper":"https://pith.science/paper/SIOTHIFQ"},"agent_actions":{"view_html":"https://pith.science/pith/SIOTHIFQ33EI6SSDNQTNEG74FT","download_json":"https://pith.science/pith/SIOTHIFQ33EI6SSDNQTNEG74FT.json","view_paper":"https://pith.science/paper/SIOTHIFQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11825&json=true","fetch_graph":"https://pith.science/api/pith-number/SIOTHIFQ33EI6SSDNQTNEG74FT/graph.json","fetch_events":"https://pith.science/api/pith-number/SIOTHIFQ33EI6SSDNQTNEG74FT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIOTHIFQ33EI6SSDNQTNEG74FT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIOTHIFQ33EI6SSDNQTNEG74FT/action/storage_attestation","attest_author":"https://pith.science/pith/SIOTHIFQ33EI6SSDNQTNEG74FT/action/author_attestation","sign_citation":"https://pith.science/pith/SIOTHIFQ33EI6SSDNQTNEG74FT/action/citation_signature","submit_replication":"https://pith.science/pith/SIOTHIFQ33EI6SSDNQTNEG74FT/action/replication_record"}},"created_at":"2026-07-05T11:04:27.157469+00:00","updated_at":"2026-07-05T11:04:27.157469+00:00"}