{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XVE3NROPIZ7PV45TYO3FM57UR3","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":"211c477b0bded4715345c39d33c79c2e14df3ce68061f05b5cf695187503cb99","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-02T15:14:43Z","title_canon_sha256":"aba203a93fd06ced65b93b874a2fff9bf71a46fbe6e132e8ea80d61156ffd0be"},"schema_version":"1.0","source":{"id":"1807.00737","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.00737","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"1807.00737v5","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00737","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"XVE3NROPIZ7P","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"XVE3NROPIZ7PV45T","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"XVE3NROP","created_at":"2026-07-05T01:05:08Z"}],"graph_snapshots":[{"event_id":"sha256:325a27caa2fd03ad986017459c33ed1943f71e2d125d0e9554dba331f3ab1c31","target":"graph","created_at":"2026-07-05T01:05:08Z","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/1807.00737/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning goal-oriented dialogues by means of deep reinforcement learning has recently become a popular research topic. However, commonly used policy-based dialogue agents often end up focusing on simple utterances and suboptimal policies. To mitigate this problem, we propose a class of novel temperature-based extensions for policy gradient methods, which are referred to as Tempered Policy Gradients (TPGs). On a recent AI-testbed, i.e., the GuessWhat?! game, we achieve significant improvements with two innovations. The first one is an extension of the state-of-the-art solutions with Seq2Seq and","authors_text":"Rui Zhao, Volker Tresp","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-02T15:14:43Z","title":"Learning Goal-Oriented Visual Dialog via Tempered Policy Gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00737","kind":"arxiv","version":5},"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:f632812526309d0faac7d4fbc4255079498c4b2cc72307d4668d247eb665bec0","target":"record","created_at":"2026-07-05T01:05:08Z","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":"211c477b0bded4715345c39d33c79c2e14df3ce68061f05b5cf695187503cb99","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-02T15:14:43Z","title_canon_sha256":"aba203a93fd06ced65b93b874a2fff9bf71a46fbe6e132e8ea80d61156ffd0be"},"schema_version":"1.0","source":{"id":"1807.00737","kind":"arxiv","version":5}},"canonical_sha256":"bd49b6c5cf467efaf3b3c3b65677f48ee78fbef6966c5e3a48ca75f99accae16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd49b6c5cf467efaf3b3c3b65677f48ee78fbef6966c5e3a48ca75f99accae16","first_computed_at":"2026-07-05T01:05:08.169557Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:05:08.169557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EYyosGtXPW2YON07oucOQCsUcB4hQzdZptfW+Ngh/sM+ZAc+dXVZmzs5xRpLNZIIXMyvkhifk8L5bFIT319hCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:05:08.169923Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.00737","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f632812526309d0faac7d4fbc4255079498c4b2cc72307d4668d247eb665bec0","sha256:325a27caa2fd03ad986017459c33ed1943f71e2d125d0e9554dba331f3ab1c31"],"state_sha256":"1dc3e90444dda94a790dbc8833df570efed61f3a7136af98dcff227d2289f204"}