{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RAITA6BMOXC2PK6VBFPQMLV45D","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":"2b9ffaeddffcbee444421764d4057c5dde316c33c12fe54d30fb7e1d515b474f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-18T16:23:30Z","title_canon_sha256":"8afda6f6d58487bf445251a846f40ea98db5e45894df2bdb17b4eb9e64ed2985"},"schema_version":"1.0","source":{"id":"2011.09378","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.09378","created_at":"2026-07-05T01:52:43Z"},{"alias_kind":"arxiv_version","alias_value":"2011.09378v1","created_at":"2026-07-05T01:52:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.09378","created_at":"2026-07-05T01:52:43Z"},{"alias_kind":"pith_short_12","alias_value":"RAITA6BMOXC2","created_at":"2026-07-05T01:52:43Z"},{"alias_kind":"pith_short_16","alias_value":"RAITA6BMOXC2PK6V","created_at":"2026-07-05T01:52:43Z"},{"alias_kind":"pith_short_8","alias_value":"RAITA6BM","created_at":"2026-07-05T01:52:43Z"}],"graph_snapshots":[{"event_id":"sha256:720f89e149ab39b21646d04821e2e798e3f1f3de492ee4819d56e27e468a945e","target":"graph","created_at":"2026-07-05T01:52:43Z","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/2011.09378/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) can enable task-oriented dialogue systems to steer the conversation towards successful task completion. In an end-to-end setting, a response can be constructed in a word-level sequential decision making process with the entire system vocabulary as action space. Policies trained in such a fashion do not require expert-defined action spaces, but they have to deal with large action spaces and long trajectories, making RL impractical. Using the latent space of a variational model as action space alleviates this problem. However, current approaches use an uninformed prio","authors_text":"Carel van Niekerk, Christian Geishauser, Hsien-Chin Lin, Marco Moresi, Michael Heck, Milica Ga\\v{s}i\\'c, Nurul Lubis","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-18T16:23:30Z","title":"LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.09378","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:d111e03eb35b0d7da184dec2380db3a661a58593ff5c92cb803e5f49b756a904","target":"record","created_at":"2026-07-05T01:52:43Z","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":"2b9ffaeddffcbee444421764d4057c5dde316c33c12fe54d30fb7e1d515b474f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-18T16:23:30Z","title_canon_sha256":"8afda6f6d58487bf445251a846f40ea98db5e45894df2bdb17b4eb9e64ed2985"},"schema_version":"1.0","source":{"id":"2011.09378","kind":"arxiv","version":1}},"canonical_sha256":"881130782c75c5a7abd5095f062ebce8d034f3c357e3acb7d3248a3020d8b26f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"881130782c75c5a7abd5095f062ebce8d034f3c357e3acb7d3248a3020d8b26f","first_computed_at":"2026-07-05T01:52:43.419582Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:52:43.419582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Kzgfi2Az0jH3xx8dlOq0MhVxfrra8IGG4JNWj7IHVAPg2f8wJvezfnDhjFB+o1NTy7tLsf6b+vhvo+8SCcjCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:52:43.419964Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.09378","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d111e03eb35b0d7da184dec2380db3a661a58593ff5c92cb803e5f49b756a904","sha256:720f89e149ab39b21646d04821e2e798e3f1f3de492ee4819d56e27e468a945e"],"state_sha256":"58477990c5824517683aff0e206faaad3b39827a7a3970b944862bb39c6285fc"}