{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NWTRDBY4AU5MISJP4TVII5QRLB","short_pith_number":"pith:NWTRDBY4","schema_version":"1.0","canonical_sha256":"6da711871c053ac4492fe4ea847611586444c0121c15962569b097c36cabb3f7","source":{"kind":"arxiv","id":"1912.08517","version":1},"attestation_state":"computed","paper":{"title":"Distributional Reinforcement Learning for Energy-Based Sequential Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jean-Marc Andreoli, Marc Dymetman, Tetiana Parshakova","submitted_at":"2019-12-18T11:05:27Z","abstract_excerpt":"Global Autoregressive Models (GAMs) are a recent proposal [Parshakova et al., CoNLL 2019] for exploiting global properties of sequences for data-efficient learning of seq2seq models. In the first phase of training, an Energy-Based model (EBM) over sequences is derived. This EBM has high representational power, but is unnormalized and cannot be directly exploited for sampling. To address this issue [Parshakova et al., CoNLL 2019] proposes a distillation technique, which can only be applied under limited conditions. By relating this problem to Policy Gradient techniques in RL, but in a \\emph{dis"},"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":"1912.08517","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-18T11:05:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b80945564824ecb07e58c0d6e2895f2b1509ba59c5007e887694b030b284c1f0","abstract_canon_sha256":"5077a5f200305e41c23a36b671765b171b91e59785f7b6fb871f96ef64e4c5d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:27:03.402157Z","signature_b64":"oej3F/dG4y1QLOAh5RHN50VFz6q0dvqZqlgaPVj8VXJnC20HNnAyYyXRh4JgtSluF4u9oVv7amcQjT+2RYYTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6da711871c053ac4492fe4ea847611586444c0121c15962569b097c36cabb3f7","last_reissued_at":"2026-07-05T00:27:03.401765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:27:03.401765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributional Reinforcement Learning for Energy-Based Sequential Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jean-Marc Andreoli, Marc Dymetman, Tetiana Parshakova","submitted_at":"2019-12-18T11:05:27Z","abstract_excerpt":"Global Autoregressive Models (GAMs) are a recent proposal [Parshakova et al., CoNLL 2019] for exploiting global properties of sequences for data-efficient learning of seq2seq models. In the first phase of training, an Energy-Based model (EBM) over sequences is derived. This EBM has high representational power, but is unnormalized and cannot be directly exploited for sampling. To address this issue [Parshakova et al., CoNLL 2019] proposes a distillation technique, which can only be applied under limited conditions. By relating this problem to Policy Gradient techniques in RL, but in a \\emph{dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.08517","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.08517/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":"1912.08517","created_at":"2026-07-05T00:27:03.401816+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.08517v1","created_at":"2026-07-05T00:27:03.401816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.08517","created_at":"2026-07-05T00:27:03.401816+00:00"},{"alias_kind":"pith_short_12","alias_value":"NWTRDBY4AU5M","created_at":"2026-07-05T00:27:03.401816+00:00"},{"alias_kind":"pith_short_16","alias_value":"NWTRDBY4AU5MISJP","created_at":"2026-07-05T00:27:03.401816+00:00"},{"alias_kind":"pith_short_8","alias_value":"NWTRDBY4","created_at":"2026-07-05T00:27:03.401816+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05773","citing_title":"PIPA: Preference Alignment as Prior-Informed Statistical Estimation","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NWTRDBY4AU5MISJP4TVII5QRLB","json":"https://pith.science/pith/NWTRDBY4AU5MISJP4TVII5QRLB.json","graph_json":"https://pith.science/api/pith-number/NWTRDBY4AU5MISJP4TVII5QRLB/graph.json","events_json":"https://pith.science/api/pith-number/NWTRDBY4AU5MISJP4TVII5QRLB/events.json","paper":"https://pith.science/paper/NWTRDBY4"},"agent_actions":{"view_html":"https://pith.science/pith/NWTRDBY4AU5MISJP4TVII5QRLB","download_json":"https://pith.science/pith/NWTRDBY4AU5MISJP4TVII5QRLB.json","view_paper":"https://pith.science/paper/NWTRDBY4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.08517&json=true","fetch_graph":"https://pith.science/api/pith-number/NWTRDBY4AU5MISJP4TVII5QRLB/graph.json","fetch_events":"https://pith.science/api/pith-number/NWTRDBY4AU5MISJP4TVII5QRLB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NWTRDBY4AU5MISJP4TVII5QRLB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NWTRDBY4AU5MISJP4TVII5QRLB/action/storage_attestation","attest_author":"https://pith.science/pith/NWTRDBY4AU5MISJP4TVII5QRLB/action/author_attestation","sign_citation":"https://pith.science/pith/NWTRDBY4AU5MISJP4TVII5QRLB/action/citation_signature","submit_replication":"https://pith.science/pith/NWTRDBY4AU5MISJP4TVII5QRLB/action/replication_record"}},"created_at":"2026-07-05T00:27:03.401816+00:00","updated_at":"2026-07-05T00:27:03.401816+00:00"}