{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RAITA6BMOXC2PK6VBFPQMLV45D","short_pith_number":"pith:RAITA6BM","schema_version":"1.0","canonical_sha256":"881130782c75c5a7abd5095f062ebce8d034f3c357e3acb7d3248a3020d8b26f","source":{"kind":"arxiv","id":"2011.09378","version":1},"attestation_state":"computed","paper":{"title":"LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Carel van Niekerk, Christian Geishauser, Hsien-Chin Lin, Marco Moresi, Michael Heck, Milica Ga\\v{s}i\\'c, Nurul Lubis","submitted_at":"2020-11-18T16:23:30Z","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"},"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":"2011.09378","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-18T16:23:30Z","cross_cats_sorted":[],"title_canon_sha256":"8afda6f6d58487bf445251a846f40ea98db5e45894df2bdb17b4eb9e64ed2985","abstract_canon_sha256":"2b9ffaeddffcbee444421764d4057c5dde316c33c12fe54d30fb7e1d515b474f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:52:43.419964Z","signature_b64":"7Kzgfi2Az0jH3xx8dlOq0MhVxfrra8IGG4JNWj7IHVAPg2f8wJvezfnDhjFB+o1NTy7tLsf6b+vhvo+8SCcjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"881130782c75c5a7abd5095f062ebce8d034f3c357e3acb7d3248a3020d8b26f","last_reissued_at":"2026-07-05T01:52:43.419582Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:52:43.419582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Carel van Niekerk, Christian Geishauser, Hsien-Chin Lin, Marco Moresi, Michael Heck, Milica Ga\\v{s}i\\'c, Nurul Lubis","submitted_at":"2020-11-18T16:23:30Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.09378","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/2011.09378/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":"2011.09378","created_at":"2026-07-05T01:52:43.419640+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.09378v1","created_at":"2026-07-05T01:52:43.419640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.09378","created_at":"2026-07-05T01:52:43.419640+00:00"},{"alias_kind":"pith_short_12","alias_value":"RAITA6BMOXC2","created_at":"2026-07-05T01:52:43.419640+00:00"},{"alias_kind":"pith_short_16","alias_value":"RAITA6BMOXC2PK6V","created_at":"2026-07-05T01:52:43.419640+00:00"},{"alias_kind":"pith_short_8","alias_value":"RAITA6BM","created_at":"2026-07-05T01:52:43.419640+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.14584","citing_title":"Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialogues","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RAITA6BMOXC2PK6VBFPQMLV45D","json":"https://pith.science/pith/RAITA6BMOXC2PK6VBFPQMLV45D.json","graph_json":"https://pith.science/api/pith-number/RAITA6BMOXC2PK6VBFPQMLV45D/graph.json","events_json":"https://pith.science/api/pith-number/RAITA6BMOXC2PK6VBFPQMLV45D/events.json","paper":"https://pith.science/paper/RAITA6BM"},"agent_actions":{"view_html":"https://pith.science/pith/RAITA6BMOXC2PK6VBFPQMLV45D","download_json":"https://pith.science/pith/RAITA6BMOXC2PK6VBFPQMLV45D.json","view_paper":"https://pith.science/paper/RAITA6BM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.09378&json=true","fetch_graph":"https://pith.science/api/pith-number/RAITA6BMOXC2PK6VBFPQMLV45D/graph.json","fetch_events":"https://pith.science/api/pith-number/RAITA6BMOXC2PK6VBFPQMLV45D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RAITA6BMOXC2PK6VBFPQMLV45D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RAITA6BMOXC2PK6VBFPQMLV45D/action/storage_attestation","attest_author":"https://pith.science/pith/RAITA6BMOXC2PK6VBFPQMLV45D/action/author_attestation","sign_citation":"https://pith.science/pith/RAITA6BMOXC2PK6VBFPQMLV45D/action/citation_signature","submit_replication":"https://pith.science/pith/RAITA6BMOXC2PK6VBFPQMLV45D/action/replication_record"}},"created_at":"2026-07-05T01:52:43.419640+00:00","updated_at":"2026-07-05T01:52:43.419640+00:00"}