{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NWTRDBY4AU5MISJP4TVII5QRLB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5077a5f200305e41c23a36b671765b171b91e59785f7b6fb871f96ef64e4c5d1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-18T11:05:27Z","title_canon_sha256":"b80945564824ecb07e58c0d6e2895f2b1509ba59c5007e887694b030b284c1f0"},"schema_version":"1.0","source":{"id":"1912.08517","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.08517","created_at":"2026-07-05T00:27:03Z"},{"alias_kind":"arxiv_version","alias_value":"1912.08517v1","created_at":"2026-07-05T00:27:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.08517","created_at":"2026-07-05T00:27:03Z"},{"alias_kind":"pith_short_12","alias_value":"NWTRDBY4AU5M","created_at":"2026-07-05T00:27:03Z"},{"alias_kind":"pith_short_16","alias_value":"NWTRDBY4AU5MISJP","created_at":"2026-07-05T00:27:03Z"},{"alias_kind":"pith_short_8","alias_value":"NWTRDBY4","created_at":"2026-07-05T00:27:03Z"}],"graph_snapshots":[{"event_id":"sha256:4a3ec0c0cb953c543c4c51a96cbf5055b0084029dc588ec76876dacc83716956","target":"graph","created_at":"2026-07-05T00:27:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1912.08517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jean-Marc Andreoli, Marc Dymetman, Tetiana Parshakova","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-18T11:05:27Z","title":"Distributional Reinforcement Learning for Energy-Based Sequential Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.08517","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0bdcb4852f5321541f133cf8bf64ad00f776f588baf73cf0d7d51d42c83c50ac","target":"record","created_at":"2026-07-05T00:27:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5077a5f200305e41c23a36b671765b171b91e59785f7b6fb871f96ef64e4c5d1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-18T11:05:27Z","title_canon_sha256":"b80945564824ecb07e58c0d6e2895f2b1509ba59c5007e887694b030b284c1f0"},"schema_version":"1.0","source":{"id":"1912.08517","kind":"arxiv","version":1}},"canonical_sha256":"6da711871c053ac4492fe4ea847611586444c0121c15962569b097c36cabb3f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6da711871c053ac4492fe4ea847611586444c0121c15962569b097c36cabb3f7","first_computed_at":"2026-07-05T00:27:03.401765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:27:03.401765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oej3F/dG4y1QLOAh5RHN50VFz6q0dvqZqlgaPVj8VXJnC20HNnAyYyXRh4JgtSluF4u9oVv7amcQjT+2RYYTAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:27:03.402157Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.08517","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bdcb4852f5321541f133cf8bf64ad00f776f588baf73cf0d7d51d42c83c50ac","sha256:4a3ec0c0cb953c543c4c51a96cbf5055b0084029dc588ec76876dacc83716956"],"state_sha256":"d73cdcc497d70b94acb423bdd33949a6b60e0495b163731e9699b74fd69c48af"}