{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UU2NEEQ5ZWQ3BRVRTN7CNTXQQB","short_pith_number":"pith:UU2NEEQ5","schema_version":"1.0","canonical_sha256":"a534d2121dcda1b0c6b19b7e26cef08063044aafd4f8a1631fa03d0809fce363","source":{"kind":"arxiv","id":"1903.08689","version":6},"attestation_state":"computed","paper":{"title":"Implicit Generation and Generalization in Energy-Based Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Igor Mordatch, Yilun Du","submitted_at":"2019-03-20T18:34:29Z","abstract_excerpt":"Energy based models (EBMs) are appealing due to their generality and simplicity in likelihood modeling, but have been traditionally difficult to train. We present techniques to scale MCMC based EBM training on continuous neural networks, and we show its success on the high-dimensional data domains of ImageNet32x32, ImageNet128x128, CIFAR-10, and robotic hand trajectories, achieving better samples than other likelihood models and nearing the performance of contemporary GAN approaches, while covering all modes of the data. We highlight some unique capabilities of implicit generation such as comp"},"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":"1903.08689","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-20T18:34:29Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"bdf852576fc141254d520867ffef804beed4301a073d49c0665e76ba6b3cc1bb","abstract_canon_sha256":"995ad292d9f2f52faa535348a327c713618f4d39055adabd82103bd615210408"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:14:23.890910Z","signature_b64":"UPN++PSX1/fgZBHTctBD+scdobuNGBicip672mariPhJU1KYPrTYMriyU1dVFGYG9ui+zepqaGu5As7wf5x7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a534d2121dcda1b0c6b19b7e26cef08063044aafd4f8a1631fa03d0809fce363","last_reissued_at":"2026-07-05T01:14:23.890472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:14:23.890472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Implicit Generation and Generalization in Energy-Based Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Igor Mordatch, Yilun Du","submitted_at":"2019-03-20T18:34:29Z","abstract_excerpt":"Energy based models (EBMs) are appealing due to their generality and simplicity in likelihood modeling, but have been traditionally difficult to train. We present techniques to scale MCMC based EBM training on continuous neural networks, and we show its success on the high-dimensional data domains of ImageNet32x32, ImageNet128x128, CIFAR-10, and robotic hand trajectories, achieving better samples than other likelihood models and nearing the performance of contemporary GAN approaches, while covering all modes of the data. We highlight some unique capabilities of implicit generation such as comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.08689","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/1903.08689/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":"1903.08689","created_at":"2026-07-05T01:14:23.890532+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.08689v6","created_at":"2026-07-05T01:14:23.890532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.08689","created_at":"2026-07-05T01:14:23.890532+00:00"},{"alias_kind":"pith_short_12","alias_value":"UU2NEEQ5ZWQ3","created_at":"2026-07-05T01:14:23.890532+00:00"},{"alias_kind":"pith_short_16","alias_value":"UU2NEEQ5ZWQ3BRVR","created_at":"2026-07-05T01:14:23.890532+00:00"},{"alias_kind":"pith_short_8","alias_value":"UU2NEEQ5","created_at":"2026-07-05T01:14:23.890532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.02549","citing_title":"DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2405.16730","citing_title":"\"Noisier\" Noise Contrastive Eestimation is (Almost) Maximum Likelihood","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2308.08089","citing_title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","ref_index":207,"is_internal_anchor":false},{"citing_arxiv_id":"1907.05600","citing_title":"Generative Modeling by Estimating Gradients of the Data Distribution","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2105.05233","citing_title":"Diffusion Models Beat GANs on Image Synthesis","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2108.01073","citing_title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","ref_index":4,"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":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UU2NEEQ5ZWQ3BRVRTN7CNTXQQB","json":"https://pith.science/pith/UU2NEEQ5ZWQ3BRVRTN7CNTXQQB.json","graph_json":"https://pith.science/api/pith-number/UU2NEEQ5ZWQ3BRVRTN7CNTXQQB/graph.json","events_json":"https://pith.science/api/pith-number/UU2NEEQ5ZWQ3BRVRTN7CNTXQQB/events.json","paper":"https://pith.science/paper/UU2NEEQ5"},"agent_actions":{"view_html":"https://pith.science/pith/UU2NEEQ5ZWQ3BRVRTN7CNTXQQB","download_json":"https://pith.science/pith/UU2NEEQ5ZWQ3BRVRTN7CNTXQQB.json","view_paper":"https://pith.science/paper/UU2NEEQ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.08689&json=true","fetch_graph":"https://pith.science/api/pith-number/UU2NEEQ5ZWQ3BRVRTN7CNTXQQB/graph.json","fetch_events":"https://pith.science/api/pith-number/UU2NEEQ5ZWQ3BRVRTN7CNTXQQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UU2NEEQ5ZWQ3BRVRTN7CNTXQQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UU2NEEQ5ZWQ3BRVRTN7CNTXQQB/action/storage_attestation","attest_author":"https://pith.science/pith/UU2NEEQ5ZWQ3BRVRTN7CNTXQQB/action/author_attestation","sign_citation":"https://pith.science/pith/UU2NEEQ5ZWQ3BRVRTN7CNTXQQB/action/citation_signature","submit_replication":"https://pith.science/pith/UU2NEEQ5ZWQ3BRVRTN7CNTXQQB/action/replication_record"}},"created_at":"2026-07-05T01:14:23.890532+00:00","updated_at":"2026-07-05T01:14:23.890532+00:00"}