{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:KGLWLR3V5BDNN6TLEGVFMENTXF","short_pith_number":"pith:KGLWLR3V","canonical_record":{"source":{"id":"1902.08858","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-23T22:27:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f0e99c336f33599dc0b83bd01bc145df3067bd5bb3a5d49be9b6b52795aeb83f","abstract_canon_sha256":"ab127504599354181bcf00eed6bcdae6746c9b57e90223d46dddb63c6c8cb13a"},"schema_version":"1.0"},"canonical_sha256":"519765c775e846d6fa6b21aa5611b3b957f83e218d8292681410978b995485f0","source":{"kind":"arxiv","id":"1902.08858","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.08858","created_at":"2026-05-17T23:48:39Z"},{"alias_kind":"arxiv_version","alias_value":"1902.08858v2","created_at":"2026-05-17T23:48:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.08858","created_at":"2026-05-17T23:48:39Z"},{"alias_kind":"pith_short_12","alias_value":"KGLWLR3V5BDN","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KGLWLR3V5BDNN6TL","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KGLWLR3V","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:KGLWLR3V5BDNN6TLEGVFMENTXF","target":"record","payload":{"canonical_record":{"source":{"id":"1902.08858","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-23T22:27:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f0e99c336f33599dc0b83bd01bc145df3067bd5bb3a5d49be9b6b52795aeb83f","abstract_canon_sha256":"ab127504599354181bcf00eed6bcdae6746c9b57e90223d46dddb63c6c8cb13a"},"schema_version":"1.0"},"canonical_sha256":"519765c775e846d6fa6b21aa5611b3b957f83e218d8292681410978b995485f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:39.458415Z","signature_b64":"RVdurd0Lgimraauq0E9y69E7NfGEHOb9/pPrFoma7ELiyxTCmmJp6YEb8d434HNYjBlWdVig/HcFnpbguBW8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"519765c775e846d6fa6b21aa5611b3b957f83e218d8292681410978b995485f0","last_reissued_at":"2026-05-17T23:48:39.457867Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:39.457867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.08858","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:48:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VUHcHok1JFGb0Agj7Ej6w7RWf5i+LyB7IXvfUoyNNMT/PAEF2MHK5Fz+P9896aiCYZXhDVnJLrGLHA2PBRM5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T08:49:06.579568Z"},"content_sha256":"cb49cbbe7ed74fe77e682fd1b078eb3dfea476e3adeca2b8f5a99963b1d09077","schema_version":"1.0","event_id":"sha256:cb49cbbe7ed74fe77e682fd1b078eb3dfea476e3adeca2b8f5a99963b1d09077"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:KGLWLR3V5BDNN6TLEGVFMENTXF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kaige Xie, Maxine Eskenazi, Tiancheng Zhao","submitted_at":"2019-02-23T22:27:45Z","abstract_excerpt":"Defining action spaces for conversational agents and optimizing their decision-making process with reinforcement learning is an enduring challenge. Common practice has been to use handcrafted dialog acts, or the output vocabulary, e.g. in neural encoder decoders, as the action spaces. Both have their own limitations. This paper proposes a novel latent action framework that treats the action spaces of an end-to-end dialog agent as latent variables and develops unsupervised methods in order to induce its own action space from the data. Comprehensive experiments are conducted examining both conti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.08858","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:48:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FrLFg8T0vxXKETLsP4BmIectkLYkkIXdyzyRp6XQNyAowYa8m1TIRZNIsB4WBVH6toQ9XnkIEG8v/npia46vDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T08:49:06.580274Z"},"content_sha256":"5a03a5dffb989dc12978c2de25e2711bcc4304f3ae6a560d13492a31db41bd7f","schema_version":"1.0","event_id":"sha256:5a03a5dffb989dc12978c2de25e2711bcc4304f3ae6a560d13492a31db41bd7f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KGLWLR3V5BDNN6TLEGVFMENTXF/bundle.json","state_url":"https://pith.science/pith/KGLWLR3V5BDNN6TLEGVFMENTXF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KGLWLR3V5BDNN6TLEGVFMENTXF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T08:49:06Z","links":{"resolver":"https://pith.science/pith/KGLWLR3V5BDNN6TLEGVFMENTXF","bundle":"https://pith.science/pith/KGLWLR3V5BDNN6TLEGVFMENTXF/bundle.json","state":"https://pith.science/pith/KGLWLR3V5BDNN6TLEGVFMENTXF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KGLWLR3V5BDNN6TLEGVFMENTXF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KGLWLR3V5BDNN6TLEGVFMENTXF","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":"ab127504599354181bcf00eed6bcdae6746c9b57e90223d46dddb63c6c8cb13a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-23T22:27:45Z","title_canon_sha256":"f0e99c336f33599dc0b83bd01bc145df3067bd5bb3a5d49be9b6b52795aeb83f"},"schema_version":"1.0","source":{"id":"1902.08858","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.08858","created_at":"2026-05-17T23:48:39Z"},{"alias_kind":"arxiv_version","alias_value":"1902.08858v2","created_at":"2026-05-17T23:48:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.08858","created_at":"2026-05-17T23:48:39Z"},{"alias_kind":"pith_short_12","alias_value":"KGLWLR3V5BDN","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KGLWLR3V5BDNN6TL","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KGLWLR3V","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:5a03a5dffb989dc12978c2de25e2711bcc4304f3ae6a560d13492a31db41bd7f","target":"graph","created_at":"2026-05-17T23:48:39Z","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":"Defining action spaces for conversational agents and optimizing their decision-making process with reinforcement learning is an enduring challenge. Common practice has been to use handcrafted dialog acts, or the output vocabulary, e.g. in neural encoder decoders, as the action spaces. Both have their own limitations. This paper proposes a novel latent action framework that treats the action spaces of an end-to-end dialog agent as latent variables and develops unsupervised methods in order to induce its own action space from the data. Comprehensive experiments are conducted examining both conti","authors_text":"Kaige Xie, Maxine Eskenazi, Tiancheng Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-23T22:27:45Z","title":"Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.08858","kind":"arxiv","version":2},"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:cb49cbbe7ed74fe77e682fd1b078eb3dfea476e3adeca2b8f5a99963b1d09077","target":"record","created_at":"2026-05-17T23:48:39Z","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":"ab127504599354181bcf00eed6bcdae6746c9b57e90223d46dddb63c6c8cb13a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-23T22:27:45Z","title_canon_sha256":"f0e99c336f33599dc0b83bd01bc145df3067bd5bb3a5d49be9b6b52795aeb83f"},"schema_version":"1.0","source":{"id":"1902.08858","kind":"arxiv","version":2}},"canonical_sha256":"519765c775e846d6fa6b21aa5611b3b957f83e218d8292681410978b995485f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"519765c775e846d6fa6b21aa5611b3b957f83e218d8292681410978b995485f0","first_computed_at":"2026-05-17T23:48:39.457867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:39.457867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RVdurd0Lgimraauq0E9y69E7NfGEHOb9/pPrFoma7ELiyxTCmmJp6YEb8d434HNYjBlWdVig/HcFnpbguBW8AA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:39.458415Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.08858","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb49cbbe7ed74fe77e682fd1b078eb3dfea476e3adeca2b8f5a99963b1d09077","sha256:5a03a5dffb989dc12978c2de25e2711bcc4304f3ae6a560d13492a31db41bd7f"],"state_sha256":"b7afbb8c6cb0863740729ee18c70d8696bc66071af6d3c151308e4f6faa07503"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g9rZL5J0vbTRYYJbCAg/H7cS+0wVF9auRplNfDVItkd63GJD0z2EIKZ97lechAGIyh17tjPQrrnMB5U+MlygDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T08:49:06.583912Z","bundle_sha256":"8372ab0e2f604a8d49ed636ffdbe3e0885d9c903a9faf95f1c68aed8b42fd208"}}