{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MBBFHHRNNDTNNJ3EZCF6YTJC2N","short_pith_number":"pith:MBBFHHRN","schema_version":"1.0","canonical_sha256":"6042539e2d68e6d6a764c88bec4d22d37a533ad0583fb5281954484eb36aa1bd","source":{"kind":"arxiv","id":"1912.00589","version":2},"attestation_state":"computed","paper":{"title":"Flow Contrastive Estimation of Energy-Based Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrew M. Dai, Diederik P. Kingma, Erik Nijkamp, Ruiqi Gao, Ying Nian Wu, Zhen Xu","submitted_at":"2019-12-02T06:29:36Z","abstract_excerpt":"This paper studies a training method to jointly estimate an energy-based model and a flow-based model, in which the two models are iteratively updated based on a shared adversarial value function. This joint training method has the following traits. (1) The update of the energy-based model is based on noise contrastive estimation, with the flow model serving as a strong noise distribution. (2) The update of the flow model approximately minimizes the Jensen-Shannon divergence between the flow model and the data distribution. (3) Unlike generative adversarial networks (GAN) which estimates an im"},"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":"1912.00589","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-02T06:29:36Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"d92ffe11aec861aed3e7b77d9b6fcac85a94e18e320e6e8390e0a28febbe5f9a","abstract_canon_sha256":"67005cea78abde49a1f1702a0b1ef7e2bdc6ddde391b954ccf194250c7dafdc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:52:06.676514Z","signature_b64":"HZlj8iAtCaPVDAFk07WohTtzEssdxgpeiYyWdYjLLCVyGJPnkubfFbfePS5J6vltLbDNqqlV+tQvl+GoBVbKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6042539e2d68e6d6a764c88bec4d22d37a533ad0583fb5281954484eb36aa1bd","last_reissued_at":"2026-07-05T00:52:06.676035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:52:06.676035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow Contrastive Estimation of Energy-Based Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrew M. Dai, Diederik P. Kingma, Erik Nijkamp, Ruiqi Gao, Ying Nian Wu, Zhen Xu","submitted_at":"2019-12-02T06:29:36Z","abstract_excerpt":"This paper studies a training method to jointly estimate an energy-based model and a flow-based model, in which the two models are iteratively updated based on a shared adversarial value function. This joint training method has the following traits. (1) The update of the energy-based model is based on noise contrastive estimation, with the flow model serving as a strong noise distribution. (2) The update of the flow model approximately minimizes the Jensen-Shannon divergence between the flow model and the data distribution. (3) Unlike generative adversarial networks (GAN) which estimates an im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.00589","kind":"arxiv","version":2},"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/1912.00589/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":"1912.00589","created_at":"2026-07-05T00:52:06.676105+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.00589v2","created_at":"2026-07-05T00:52:06.676105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00589","created_at":"2026-07-05T00:52:06.676105+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBBFHHRNNDTN","created_at":"2026-07-05T00:52:06.676105+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBBFHHRNNDTNNJ3E","created_at":"2026-07-05T00:52:06.676105+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBBFHHRN","created_at":"2026-07-05T00:52:06.676105+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MBBFHHRNNDTNNJ3EZCF6YTJC2N","json":"https://pith.science/pith/MBBFHHRNNDTNNJ3EZCF6YTJC2N.json","graph_json":"https://pith.science/api/pith-number/MBBFHHRNNDTNNJ3EZCF6YTJC2N/graph.json","events_json":"https://pith.science/api/pith-number/MBBFHHRNNDTNNJ3EZCF6YTJC2N/events.json","paper":"https://pith.science/paper/MBBFHHRN"},"agent_actions":{"view_html":"https://pith.science/pith/MBBFHHRNNDTNNJ3EZCF6YTJC2N","download_json":"https://pith.science/pith/MBBFHHRNNDTNNJ3EZCF6YTJC2N.json","view_paper":"https://pith.science/paper/MBBFHHRN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.00589&json=true","fetch_graph":"https://pith.science/api/pith-number/MBBFHHRNNDTNNJ3EZCF6YTJC2N/graph.json","fetch_events":"https://pith.science/api/pith-number/MBBFHHRNNDTNNJ3EZCF6YTJC2N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBBFHHRNNDTNNJ3EZCF6YTJC2N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBBFHHRNNDTNNJ3EZCF6YTJC2N/action/storage_attestation","attest_author":"https://pith.science/pith/MBBFHHRNNDTNNJ3EZCF6YTJC2N/action/author_attestation","sign_citation":"https://pith.science/pith/MBBFHHRNNDTNNJ3EZCF6YTJC2N/action/citation_signature","submit_replication":"https://pith.science/pith/MBBFHHRNNDTNNJ3EZCF6YTJC2N/action/replication_record"}},"created_at":"2026-07-05T00:52:06.676105+00:00","updated_at":"2026-07-05T00:52:06.676105+00:00"}