{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RPEVOBTEJGJYR4N4HBDQIOLHHU","short_pith_number":"pith:RPEVOBTE","schema_version":"1.0","canonical_sha256":"8bc9570664499388f1bc38470439673d031b08133a01c94bf1668f9c867a37dd","source":{"kind":"arxiv","id":"2302.11552","version":6},"attestation_state":"computed","paper":{"title":"Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arnaud Doucet, Conor Durkan, Jascha Sohl-Dickstein, Joshua B. Tenenbaum, Rob Fergus, Robin Strudel, Sander Dieleman, Will Grathwohl, Yilun Du","submitted_at":"2023-02-22T18:48:46Z","abstract_excerpt":"Since their introduction, diffusion models have quickly become the prevailing approach to generative modeling in many domains. They can be interpreted as learning the gradients of a time-varying sequence of log-probability density functions. This interpretation has motivated classifier-based and classifier-free guidance as methods for post-hoc control of diffusion models. In this work, we build upon these ideas using the score-based interpretation of diffusion models, and explore alternative ways to condition, modify, and reuse diffusion models for tasks involving compositional generation and "},"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":"2302.11552","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-22T18:48:46Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"a7c4226e2acda55e3862c08cb99a69c768109be135c06d315864a651bc9e5e6b","abstract_canon_sha256":"134eed1cf8ee5d8558131a41853318ed443a17ca72843e6bed24de85bac465ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:53.303712Z","signature_b64":"dnYBMREceypWsDkDuhXPQ/qk8iZAnvD6VnV9Gpwp2nlt5rxPPN2GyGMK/MQMFwJvbSVmLjT5Ek9wcYmXGI/kCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bc9570664499388f1bc38470439673d031b08133a01c94bf1668f9c867a37dd","last_reissued_at":"2026-07-05T09:06:53.303204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:53.303204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arnaud Doucet, Conor Durkan, Jascha Sohl-Dickstein, Joshua B. Tenenbaum, Rob Fergus, Robin Strudel, Sander Dieleman, Will Grathwohl, Yilun Du","submitted_at":"2023-02-22T18:48:46Z","abstract_excerpt":"Since their introduction, diffusion models have quickly become the prevailing approach to generative modeling in many domains. They can be interpreted as learning the gradients of a time-varying sequence of log-probability density functions. This interpretation has motivated classifier-based and classifier-free guidance as methods for post-hoc control of diffusion models. In this work, we build upon these ideas using the score-based interpretation of diffusion models, and explore alternative ways to condition, modify, and reuse diffusion models for tasks involving compositional generation and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11552","kind":"arxiv","version":6},"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/2302.11552/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":"2302.11552","created_at":"2026-07-05T09:06:53.303300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.11552v6","created_at":"2026-07-05T09:06:53.303300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11552","created_at":"2026-07-05T09:06:53.303300+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPEVOBTEJGJY","created_at":"2026-07-05T09:06:53.303300+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPEVOBTEJGJYR4N4","created_at":"2026-07-05T09:06:53.303300+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPEVOBTE","created_at":"2026-07-05T09:06:53.303300+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07568","citing_title":"A Systematic Study of Behavioral Cloning for Scientific Data Annotation","ref_index":270,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22726","citing_title":"Text Dictates, Music Decorates: Energy-based Attention for Editable Dance Motion Generation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2310.06114","citing_title":"Learning Interactive Real-World Simulators","ref_index":185,"is_internal_anchor":false},{"citing_arxiv_id":"2305.14325","citing_title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2305.13301","citing_title":"Training Diffusion Models with Reinforcement Learning","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RPEVOBTEJGJYR4N4HBDQIOLHHU","json":"https://pith.science/pith/RPEVOBTEJGJYR4N4HBDQIOLHHU.json","graph_json":"https://pith.science/api/pith-number/RPEVOBTEJGJYR4N4HBDQIOLHHU/graph.json","events_json":"https://pith.science/api/pith-number/RPEVOBTEJGJYR4N4HBDQIOLHHU/events.json","paper":"https://pith.science/paper/RPEVOBTE"},"agent_actions":{"view_html":"https://pith.science/pith/RPEVOBTEJGJYR4N4HBDQIOLHHU","download_json":"https://pith.science/pith/RPEVOBTEJGJYR4N4HBDQIOLHHU.json","view_paper":"https://pith.science/paper/RPEVOBTE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.11552&json=true","fetch_graph":"https://pith.science/api/pith-number/RPEVOBTEJGJYR4N4HBDQIOLHHU/graph.json","fetch_events":"https://pith.science/api/pith-number/RPEVOBTEJGJYR4N4HBDQIOLHHU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPEVOBTEJGJYR4N4HBDQIOLHHU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPEVOBTEJGJYR4N4HBDQIOLHHU/action/storage_attestation","attest_author":"https://pith.science/pith/RPEVOBTEJGJYR4N4HBDQIOLHHU/action/author_attestation","sign_citation":"https://pith.science/pith/RPEVOBTEJGJYR4N4HBDQIOLHHU/action/citation_signature","submit_replication":"https://pith.science/pith/RPEVOBTEJGJYR4N4HBDQIOLHHU/action/replication_record"}},"created_at":"2026-07-05T09:06:53.303300+00:00","updated_at":"2026-07-05T09:06:53.303300+00:00"}