{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ETCWPJSC5KXLS7FNRB3R7SYJ6J","short_pith_number":"pith:ETCWPJSC","schema_version":"1.0","canonical_sha256":"24c567a642eaaeb97cad88771fcb09f2573af7287269ab5f33b705c5884ea916","source":{"kind":"arxiv","id":"2407.03300","version":1},"attestation_state":"computed","paper":{"title":"DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Arash Vahdat, Gabriele Corso, Karsten Kreis, Tommi Jaakkola, Yilun Xu","submitted_at":"2024-07-03T17:42:46Z","abstract_excerpt":"Diffusion models (DMs) have revolutionized generative learning. They utilize a diffusion process to encode data into a simple Gaussian distribution. However, encoding a complex, potentially multimodal data distribution into a single continuous Gaussian distribution arguably represents an unnecessarily challenging learning problem. We propose Discrete-Continuous Latent Variable Diffusion Models (DisCo-Diff) to simplify this task by introducing complementary discrete latent variables. We augment DMs with learnable discrete latents, inferred with an encoder, and train DM and encoder end-to-end. D"},"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":"2407.03300","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-03T17:42:46Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"c601bade938579b304cf9ba718e052a5f07bcbd91519e2e051c138b91b40b107","abstract_canon_sha256":"26263528ee41879b4a513c0ef9cef211ff198d829e055862bdb85472039d4686"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:48.802557Z","signature_b64":"BaDAlitLEM+1sdXbUJgCAn9qTbjrR3RAaNhhk3nnQu/CgPzjhh7ET5AN5G2Tpq82ypHYNfjnothI7Xe0DvezDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24c567a642eaaeb97cad88771fcb09f2573af7287269ab5f33b705c5884ea916","last_reissued_at":"2026-07-05T08:39:48.802114Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:48.802114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Arash Vahdat, Gabriele Corso, Karsten Kreis, Tommi Jaakkola, Yilun Xu","submitted_at":"2024-07-03T17:42:46Z","abstract_excerpt":"Diffusion models (DMs) have revolutionized generative learning. They utilize a diffusion process to encode data into a simple Gaussian distribution. However, encoding a complex, potentially multimodal data distribution into a single continuous Gaussian distribution arguably represents an unnecessarily challenging learning problem. We propose Discrete-Continuous Latent Variable Diffusion Models (DisCo-Diff) to simplify this task by introducing complementary discrete latent variables. We augment DMs with learnable discrete latents, inferred with an encoder, and train DM and encoder end-to-end. D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03300","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/2407.03300/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":"2407.03300","created_at":"2026-07-05T08:39:48.802172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03300v1","created_at":"2026-07-05T08:39:48.802172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03300","created_at":"2026-07-05T08:39:48.802172+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETCWPJSC5KXL","created_at":"2026-07-05T08:39:48.802172+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETCWPJSC5KXLS7FN","created_at":"2026-07-05T08:39:48.802172+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETCWPJSC","created_at":"2026-07-05T08:39:48.802172+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/ETCWPJSC5KXLS7FNRB3R7SYJ6J","json":"https://pith.science/pith/ETCWPJSC5KXLS7FNRB3R7SYJ6J.json","graph_json":"https://pith.science/api/pith-number/ETCWPJSC5KXLS7FNRB3R7SYJ6J/graph.json","events_json":"https://pith.science/api/pith-number/ETCWPJSC5KXLS7FNRB3R7SYJ6J/events.json","paper":"https://pith.science/paper/ETCWPJSC"},"agent_actions":{"view_html":"https://pith.science/pith/ETCWPJSC5KXLS7FNRB3R7SYJ6J","download_json":"https://pith.science/pith/ETCWPJSC5KXLS7FNRB3R7SYJ6J.json","view_paper":"https://pith.science/paper/ETCWPJSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03300&json=true","fetch_graph":"https://pith.science/api/pith-number/ETCWPJSC5KXLS7FNRB3R7SYJ6J/graph.json","fetch_events":"https://pith.science/api/pith-number/ETCWPJSC5KXLS7FNRB3R7SYJ6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETCWPJSC5KXLS7FNRB3R7SYJ6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETCWPJSC5KXLS7FNRB3R7SYJ6J/action/storage_attestation","attest_author":"https://pith.science/pith/ETCWPJSC5KXLS7FNRB3R7SYJ6J/action/author_attestation","sign_citation":"https://pith.science/pith/ETCWPJSC5KXLS7FNRB3R7SYJ6J/action/citation_signature","submit_replication":"https://pith.science/pith/ETCWPJSC5KXLS7FNRB3R7SYJ6J/action/replication_record"}},"created_at":"2026-07-05T08:39:48.802172+00:00","updated_at":"2026-07-05T08:39:48.802172+00:00"}