{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5G4NWUDDLS6YHDBDEVNAEMJG7D","short_pith_number":"pith:5G4NWUDD","schema_version":"1.0","canonical_sha256":"e9b8db50635cbd838c23255a023126f8c0a85e2e89e22c23aab253ae558529c0","source":{"kind":"arxiv","id":"2310.01236","version":2},"attestation_state":"computed","paper":{"title":"Mirror Diffusion Models for Constrained and Watermarked Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Evangelos A. Theodorou, Guan-Horng Liu, Molei Tao, Tianrong Chen","submitted_at":"2023-10-02T14:26:31Z","abstract_excerpt":"Modern successes of diffusion models in learning complex, high-dimensional data distributions are attributed, in part, to their capability to construct diffusion processes with analytic transition kernels and score functions. The tractability results in a simulation-free framework with stable regression losses, from which reversed, generative processes can be learned at scale. However, when data is confined to a constrained set as opposed to a standard Euclidean space, these desirable characteristics appear to be lost based on prior attempts. In this work, we propose Mirror Diffusion Models (M"},"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":"2310.01236","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-02T14:26:31Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"8307adb37e96b4641a4eb061698e430b72b08c76a5262ba34115d1b337c3e567","abstract_canon_sha256":"86e5a85f081cd4ac6dcc8ecf439fec773802710c0c06f03117652474c10c1f5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:21.029130Z","signature_b64":"Nt+6wzRiwqMjqRoqml4x7WV+nDImfZSvOFY9yIMfu+EW+rpCN2hndsw5E+C4Rz0fWZT+QcOPsOPmnYh8uCqXDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9b8db50635cbd838c23255a023126f8c0a85e2e89e22c23aab253ae558529c0","last_reissued_at":"2026-07-05T07:50:21.028713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:21.028713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mirror Diffusion Models for Constrained and Watermarked Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Evangelos A. Theodorou, Guan-Horng Liu, Molei Tao, Tianrong Chen","submitted_at":"2023-10-02T14:26:31Z","abstract_excerpt":"Modern successes of diffusion models in learning complex, high-dimensional data distributions are attributed, in part, to their capability to construct diffusion processes with analytic transition kernels and score functions. The tractability results in a simulation-free framework with stable regression losses, from which reversed, generative processes can be learned at scale. However, when data is confined to a constrained set as opposed to a standard Euclidean space, these desirable characteristics appear to be lost based on prior attempts. In this work, we propose Mirror Diffusion Models (M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01236","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/2310.01236/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":"2310.01236","created_at":"2026-07-05T07:50:21.028771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01236v2","created_at":"2026-07-05T07:50:21.028771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01236","created_at":"2026-07-05T07:50:21.028771+00:00"},{"alias_kind":"pith_short_12","alias_value":"5G4NWUDDLS6Y","created_at":"2026-07-05T07:50:21.028771+00:00"},{"alias_kind":"pith_short_16","alias_value":"5G4NWUDDLS6YHDBD","created_at":"2026-07-05T07:50:21.028771+00:00"},{"alias_kind":"pith_short_8","alias_value":"5G4NWUDD","created_at":"2026-07-05T07:50:21.028771+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03469","citing_title":"Should the Boundary Term Be Learned in Reflected Diffusion? Conormal Trace and Reflection Masking","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5G4NWUDDLS6YHDBDEVNAEMJG7D","json":"https://pith.science/pith/5G4NWUDDLS6YHDBDEVNAEMJG7D.json","graph_json":"https://pith.science/api/pith-number/5G4NWUDDLS6YHDBDEVNAEMJG7D/graph.json","events_json":"https://pith.science/api/pith-number/5G4NWUDDLS6YHDBDEVNAEMJG7D/events.json","paper":"https://pith.science/paper/5G4NWUDD"},"agent_actions":{"view_html":"https://pith.science/pith/5G4NWUDDLS6YHDBDEVNAEMJG7D","download_json":"https://pith.science/pith/5G4NWUDDLS6YHDBDEVNAEMJG7D.json","view_paper":"https://pith.science/paper/5G4NWUDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01236&json=true","fetch_graph":"https://pith.science/api/pith-number/5G4NWUDDLS6YHDBDEVNAEMJG7D/graph.json","fetch_events":"https://pith.science/api/pith-number/5G4NWUDDLS6YHDBDEVNAEMJG7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5G4NWUDDLS6YHDBDEVNAEMJG7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5G4NWUDDLS6YHDBDEVNAEMJG7D/action/storage_attestation","attest_author":"https://pith.science/pith/5G4NWUDDLS6YHDBDEVNAEMJG7D/action/author_attestation","sign_citation":"https://pith.science/pith/5G4NWUDDLS6YHDBDEVNAEMJG7D/action/citation_signature","submit_replication":"https://pith.science/pith/5G4NWUDDLS6YHDBDEVNAEMJG7D/action/replication_record"}},"created_at":"2026-07-05T07:50:21.028771+00:00","updated_at":"2026-07-05T07:50:21.028771+00:00"}