{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:YGZYGKZY3EB4WP37QWFS3MBG5L","short_pith_number":"pith:YGZYGKZY","schema_version":"1.0","canonical_sha256":"c1b3832b38d903cb3f7f858b2db026eac009cae240a4ecf2f22d8bc873bcb484","source":{"kind":"arxiv","id":"1606.03439","version":1},"attestation_state":"computed","paper":{"title":"Deep Directed Generative Models with Energy-Based Probability Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Taesup Kim, Yoshua Bengio","submitted_at":"2016-06-10T19:42:57Z","abstract_excerpt":"Training energy-based probabilistic models is confronted with apparently intractable sums, whose Monte Carlo estimation requires sampling from the estimated probability distribution in the inner loop of training. This can be approximately achieved by Markov chain Monte Carlo methods, but may still face a formidable obstacle that is the difficulty of mixing between modes with sharp concentrations of probability. Whereas an MCMC process is usually derived from a given energy function based on mathematical considerations and requires an arbitrarily long time to obtain good and varied samples, we "},"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":"1606.03439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-06-10T19:42:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c42db24386236f5dad4b734bc6deaccbca69b29fd3bef66cd4830c1a1d1338cb","abstract_canon_sha256":"2fec22309e2ee85ea2cf83c04410d5b891c44866d272d0347640bd8ae892921b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:36.887153Z","signature_b64":"dIQgDZVKm4s2vwqnrhnwo3OGCbHdFtRqSk1pm93cMzbrjEO8bk8g4pGYjc5spvEZzOeJonJib9iH3VApoJ48AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1b3832b38d903cb3f7f858b2db026eac009cae240a4ecf2f22d8bc873bcb484","last_reissued_at":"2026-05-18T01:12:36.886657Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:36.886657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Directed Generative Models with Energy-Based Probability Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Taesup Kim, Yoshua Bengio","submitted_at":"2016-06-10T19:42:57Z","abstract_excerpt":"Training energy-based probabilistic models is confronted with apparently intractable sums, whose Monte Carlo estimation requires sampling from the estimated probability distribution in the inner loop of training. This can be approximately achieved by Markov chain Monte Carlo methods, but may still face a formidable obstacle that is the difficulty of mixing between modes with sharp concentrations of probability. Whereas an MCMC process is usually derived from a given energy function based on mathematical considerations and requires an arbitrarily long time to obtain good and varied samples, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.03439","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":""},"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":"1606.03439","created_at":"2026-05-18T01:12:36.886736+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.03439v1","created_at":"2026-05-18T01:12:36.886736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.03439","created_at":"2026-05-18T01:12:36.886736+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGZYGKZY3EB4","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGZYGKZY3EB4WP37","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGZYGKZY","created_at":"2026-05-18T12:30:53.716459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19607","citing_title":"Contrastive Residual Energy Test-time Adaptation","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YGZYGKZY3EB4WP37QWFS3MBG5L","json":"https://pith.science/pith/YGZYGKZY3EB4WP37QWFS3MBG5L.json","graph_json":"https://pith.science/api/pith-number/YGZYGKZY3EB4WP37QWFS3MBG5L/graph.json","events_json":"https://pith.science/api/pith-number/YGZYGKZY3EB4WP37QWFS3MBG5L/events.json","paper":"https://pith.science/paper/YGZYGKZY"},"agent_actions":{"view_html":"https://pith.science/pith/YGZYGKZY3EB4WP37QWFS3MBG5L","download_json":"https://pith.science/pith/YGZYGKZY3EB4WP37QWFS3MBG5L.json","view_paper":"https://pith.science/paper/YGZYGKZY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.03439&json=true","fetch_graph":"https://pith.science/api/pith-number/YGZYGKZY3EB4WP37QWFS3MBG5L/graph.json","fetch_events":"https://pith.science/api/pith-number/YGZYGKZY3EB4WP37QWFS3MBG5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGZYGKZY3EB4WP37QWFS3MBG5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGZYGKZY3EB4WP37QWFS3MBG5L/action/storage_attestation","attest_author":"https://pith.science/pith/YGZYGKZY3EB4WP37QWFS3MBG5L/action/author_attestation","sign_citation":"https://pith.science/pith/YGZYGKZY3EB4WP37QWFS3MBG5L/action/citation_signature","submit_replication":"https://pith.science/pith/YGZYGKZY3EB4WP37QWFS3MBG5L/action/replication_record"}},"created_at":"2026-05-18T01:12:36.886736+00:00","updated_at":"2026-05-18T01:12:36.886736+00:00"}