{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KTDK3K3D2LXYZR3AFIEO4BM2LX","short_pith_number":"pith:KTDK3K3D","schema_version":"1.0","canonical_sha256":"54c6adab63d2ef8cc7602a08ee059a5dc5ff13155cdcd9151c2c7d2e56ed26b5","source":{"kind":"arxiv","id":"2004.06030","version":3},"attestation_state":"computed","paper":{"title":"Compositional Visual Generation and Inference with Energy Based Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Igor Mordatch, Shuang Li, Yilun Du","submitted_at":"2020-04-13T16:01:40Z","abstract_excerpt":"A vital aspect of human intelligence is the ability to compose increasingly complex concepts out of simpler ideas, enabling both rapid learning and adaptation of knowledge. In this paper we show that energy-based models can exhibit this ability by directly combining probability distributions. Samples from the combined distribution correspond to compositions of concepts. For example, given a distribution for smiling faces, and another for male faces, we can combine them to generate smiling male faces. This allows us to generate natural images that simultaneously satisfy conjunctions, disjunctio"},"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":"2004.06030","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-13T16:01:40Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"0175c94a7169ccdd385dc3230933be2d1b2aaf4e8294657ff2e460a6717d08d7","abstract_canon_sha256":"315baff3b7c6ff4a6ce7e34e6c1335c44de25ca7634499db5896f009a4be2f2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:10.422598Z","signature_b64":"bdaukTSUBrPp8MI1A9J+IoTjmKaPgeN2hYbvwDHsLNuqajoEekU3JK4wHtldFN/12fZGft4NcKoCBttIyfSLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54c6adab63d2ef8cc7602a08ee059a5dc5ff13155cdcd9151c2c7d2e56ed26b5","last_reissued_at":"2026-07-05T02:00:10.422152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:10.422152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compositional Visual Generation and Inference with Energy Based Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Igor Mordatch, Shuang Li, Yilun Du","submitted_at":"2020-04-13T16:01:40Z","abstract_excerpt":"A vital aspect of human intelligence is the ability to compose increasingly complex concepts out of simpler ideas, enabling both rapid learning and adaptation of knowledge. In this paper we show that energy-based models can exhibit this ability by directly combining probability distributions. Samples from the combined distribution correspond to compositions of concepts. For example, given a distribution for smiling faces, and another for male faces, we can combine them to generate smiling male faces. This allows us to generate natural images that simultaneously satisfy conjunctions, disjunctio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.06030","kind":"arxiv","version":3},"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/2004.06030/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":"2004.06030","created_at":"2026-07-05T02:00:10.422213+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.06030v3","created_at":"2026-07-05T02:00:10.422213+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.06030","created_at":"2026-07-05T02:00:10.422213+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTDK3K3D2LXY","created_at":"2026-07-05T02:00:10.422213+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTDK3K3D2LXYZR3A","created_at":"2026-07-05T02:00:10.422213+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTDK3K3D","created_at":"2026-07-05T02:00:10.422213+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14988","citing_title":"Compositional Video Generation via Inference-Time Guidance","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16520","citing_title":"Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08645","citing_title":"Energy-based models for diagnostic reconstruction and analysis in a laboratory plasma device","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KTDK3K3D2LXYZR3AFIEO4BM2LX","json":"https://pith.science/pith/KTDK3K3D2LXYZR3AFIEO4BM2LX.json","graph_json":"https://pith.science/api/pith-number/KTDK3K3D2LXYZR3AFIEO4BM2LX/graph.json","events_json":"https://pith.science/api/pith-number/KTDK3K3D2LXYZR3AFIEO4BM2LX/events.json","paper":"https://pith.science/paper/KTDK3K3D"},"agent_actions":{"view_html":"https://pith.science/pith/KTDK3K3D2LXYZR3AFIEO4BM2LX","download_json":"https://pith.science/pith/KTDK3K3D2LXYZR3AFIEO4BM2LX.json","view_paper":"https://pith.science/paper/KTDK3K3D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.06030&json=true","fetch_graph":"https://pith.science/api/pith-number/KTDK3K3D2LXYZR3AFIEO4BM2LX/graph.json","fetch_events":"https://pith.science/api/pith-number/KTDK3K3D2LXYZR3AFIEO4BM2LX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTDK3K3D2LXYZR3AFIEO4BM2LX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTDK3K3D2LXYZR3AFIEO4BM2LX/action/storage_attestation","attest_author":"https://pith.science/pith/KTDK3K3D2LXYZR3AFIEO4BM2LX/action/author_attestation","sign_citation":"https://pith.science/pith/KTDK3K3D2LXYZR3AFIEO4BM2LX/action/citation_signature","submit_replication":"https://pith.science/pith/KTDK3K3D2LXYZR3AFIEO4BM2LX/action/replication_record"}},"created_at":"2026-07-05T02:00:10.422213+00:00","updated_at":"2026-07-05T02:00:10.422213+00:00"}