{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:RSU7P2S2KWCBCBF7XXQCOATW4M","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":"d8fb0c6422698d85902586e2b27005611c470594ca2e4e6b545e4267fc430a4a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-07-24T20:05:07Z","title_canon_sha256":"904e7816b10a1129b72a79dc1704fe413f5fe21230a8b0548df6d82f456f121b"},"schema_version":"1.0","source":{"id":"1607.07086","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.07086","created_at":"2026-05-18T00:49:36Z"},{"alias_kind":"arxiv_version","alias_value":"1607.07086v3","created_at":"2026-05-18T00:49:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.07086","created_at":"2026-05-18T00:49:36Z"},{"alias_kind":"pith_short_12","alias_value":"RSU7P2S2KWCB","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RSU7P2S2KWCBCBF7","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RSU7P2S2","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:2293e1bef5d3a69c828df2512f0d7eba6c8d029801a331bb6a284c6ba3e2ac6b","target":"graph","created_at":"2026-05-18T00:49:36Z","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"},"paper":{"abstract_excerpt":"We present an approach to training neural networks to generate sequences using actor-critic methods from reinforcement learning (RL). Current log-likelihood training methods are limited by the discrepancy between their training and testing modes, as models must generate tokens conditioned on their previous guesses rather than the ground-truth tokens. We address this problem by introducing a \\textit{critic} network that is trained to predict the value of an output token, given the policy of an \\textit{actor} network. This results in a training procedure that is much closer to the test phase, an","authors_text":"Aaron Courville, Anirudh Goyal, Dzmitry Bahdanau, Joelle Pineau, Kelvin Xu, Philemon Brakel, Ryan Lowe, Yoshua Bengio","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-07-24T20:05:07Z","title":"An Actor-Critic Algorithm for Sequence Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.07086","kind":"arxiv","version":3},"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":"sha256:620f2b42483928e25af70f189aeca5ae328d026bf8e9000d96da5004f0dc694b","target":"record","created_at":"2026-05-18T00:49:36Z","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":"d8fb0c6422698d85902586e2b27005611c470594ca2e4e6b545e4267fc430a4a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-07-24T20:05:07Z","title_canon_sha256":"904e7816b10a1129b72a79dc1704fe413f5fe21230a8b0548df6d82f456f121b"},"schema_version":"1.0","source":{"id":"1607.07086","kind":"arxiv","version":3}},"canonical_sha256":"8ca9f7ea5a55841104bfbde0270276e33ae40b778632e12d9a0beebdc5a83af7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ca9f7ea5a55841104bfbde0270276e33ae40b778632e12d9a0beebdc5a83af7","first_computed_at":"2026-05-18T00:49:36.659419Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:49:36.659419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o8uAVVLOIQH8FgHyOD+3QLy4MqfVGZAlBex0JKA4ktGQv5oRsbDr3dXh6TUQSvXZrHSKZ2Ikh1swho5sXDwuDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:49:36.660112Z","signed_message":"canonical_sha256_bytes"},"source_id":"1607.07086","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:620f2b42483928e25af70f189aeca5ae328d026bf8e9000d96da5004f0dc694b","sha256:2293e1bef5d3a69c828df2512f0d7eba6c8d029801a331bb6a284c6ba3e2ac6b"],"state_sha256":"57087c4d3d23389606324943b3e90e2bce2503fca493f27125ba8acbadbca539"}