{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MVUCTBKB3AE3S5CCSMUAFBND45","short_pith_number":"pith:MVUCTBKB","schema_version":"1.0","canonical_sha256":"6568298541d809b9744293280285a3e774c936e95022c17f34e3e5bc404476e7","source":{"kind":"arxiv","id":"2307.01924","version":1},"attestation_state":"computed","paper":{"title":"ProtoDiffusion: Classifier-Free Diffusion Guidance with Prototype Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Gozde Unal, Gulcin Baykal, Halil Faruk Karagoz, Taha Binhuraib","submitted_at":"2023-07-04T21:18:39Z","abstract_excerpt":"Diffusion models are generative models that have shown significant advantages compared to other generative models in terms of higher generation quality and more stable training. However, the computational need for training diffusion models is considerably increased. In this work, we incorporate prototype learning into diffusion models to achieve high generation quality faster than the original diffusion model. Instead of randomly initialized class embeddings, we use separately learned class prototypes as the conditioning information to guide the diffusion process. We observe that our method, c"},"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":"2307.01924","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-04T21:18:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"33a8b4c127ed7052ad00a136cb8b8b5c28d4da3f82de9fdb5fff915267aacd1c","abstract_canon_sha256":"baad62289f4606f8d3d1807ed171deb77f57ebc02d02d7267c78da2920b10d3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:02.508541Z","signature_b64":"cEISpdnKAnZKI/uXKV79yfkds81IG3jjCxfenJkQjTVxPULjj94eQTyaMX+r7UbC0fUQ8OufTgHPlUNmHcK8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6568298541d809b9744293280285a3e774c936e95022c17f34e3e5bc404476e7","last_reissued_at":"2026-07-05T06:28:02.508117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:02.508117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProtoDiffusion: Classifier-Free Diffusion Guidance with Prototype Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Gozde Unal, Gulcin Baykal, Halil Faruk Karagoz, Taha Binhuraib","submitted_at":"2023-07-04T21:18:39Z","abstract_excerpt":"Diffusion models are generative models that have shown significant advantages compared to other generative models in terms of higher generation quality and more stable training. However, the computational need for training diffusion models is considerably increased. In this work, we incorporate prototype learning into diffusion models to achieve high generation quality faster than the original diffusion model. Instead of randomly initialized class embeddings, we use separately learned class prototypes as the conditioning information to guide the diffusion process. We observe that our method, c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01924","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/2307.01924/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":"2307.01924","created_at":"2026-07-05T06:28:02.508172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.01924v1","created_at":"2026-07-05T06:28:02.508172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01924","created_at":"2026-07-05T06:28:02.508172+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVUCTBKB3AE3","created_at":"2026-07-05T06:28:02.508172+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVUCTBKB3AE3S5CC","created_at":"2026-07-05T06:28:02.508172+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVUCTBKB","created_at":"2026-07-05T06:28:02.508172+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.14908","citing_title":"CODA: Algorithm-Hardware Co-design for Edge Video Diffusion via NMP-Enabled Compute-Cache Operator Disaggregation","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVUCTBKB3AE3S5CCSMUAFBND45","json":"https://pith.science/pith/MVUCTBKB3AE3S5CCSMUAFBND45.json","graph_json":"https://pith.science/api/pith-number/MVUCTBKB3AE3S5CCSMUAFBND45/graph.json","events_json":"https://pith.science/api/pith-number/MVUCTBKB3AE3S5CCSMUAFBND45/events.json","paper":"https://pith.science/paper/MVUCTBKB"},"agent_actions":{"view_html":"https://pith.science/pith/MVUCTBKB3AE3S5CCSMUAFBND45","download_json":"https://pith.science/pith/MVUCTBKB3AE3S5CCSMUAFBND45.json","view_paper":"https://pith.science/paper/MVUCTBKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.01924&json=true","fetch_graph":"https://pith.science/api/pith-number/MVUCTBKB3AE3S5CCSMUAFBND45/graph.json","fetch_events":"https://pith.science/api/pith-number/MVUCTBKB3AE3S5CCSMUAFBND45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVUCTBKB3AE3S5CCSMUAFBND45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVUCTBKB3AE3S5CCSMUAFBND45/action/storage_attestation","attest_author":"https://pith.science/pith/MVUCTBKB3AE3S5CCSMUAFBND45/action/author_attestation","sign_citation":"https://pith.science/pith/MVUCTBKB3AE3S5CCSMUAFBND45/action/citation_signature","submit_replication":"https://pith.science/pith/MVUCTBKB3AE3S5CCSMUAFBND45/action/replication_record"}},"created_at":"2026-07-05T06:28:02.508172+00:00","updated_at":"2026-07-05T06:28:02.508172+00:00"}