{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:VOHXD7CAWEEVOUA4TFYRQGLBAI","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":"2bd9b9de27af83bcc72c29db1d755be44152b8353f29a94eda527f872a12151c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-05T18:00:03Z","title_canon_sha256":"7fb1759efc4e14a1f1ac5bb21fd183a87c59b6e89168428f93aeaa92c5f01eab"},"schema_version":"1.0","source":{"id":"2010.02229","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.02229","created_at":"2026-07-05T01:40:48Z"},{"alias_kind":"arxiv_version","alias_value":"2010.02229v1","created_at":"2026-07-05T01:40:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.02229","created_at":"2026-07-05T01:40:48Z"},{"alias_kind":"pith_short_12","alias_value":"VOHXD7CAWEEV","created_at":"2026-07-05T01:40:48Z"},{"alias_kind":"pith_short_16","alias_value":"VOHXD7CAWEEVOUA4","created_at":"2026-07-05T01:40:48Z"},{"alias_kind":"pith_short_8","alias_value":"VOHXD7CA","created_at":"2026-07-05T01:40:48Z"}],"graph_snapshots":[{"event_id":"sha256:3ddf5bbe19f928fe3edc3f520f8aaba813a5e376e5730ebda6ed9e0c42046914","target":"graph","created_at":"2026-07-05T01:40:48Z","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/2010.02229/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider problems of making sequences of decisions to accomplish tasks, interacting via the medium of language. These problems are often tackled with reinforcement learning approaches. We find that these models do not generalize well when applied to novel task domains. However, the large amount of computation necessary to adequately train and explore the search space of sequential decision making, under a reinforcement learning paradigm, precludes the inclusion of large contextualized language models, which might otherwise enable the desired generalization ability. We introduce a teacher-st","authors_text":"Jonathan May, Ralph Weischedel, Xusen Yin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-05T18:00:03Z","title":"Learning to Generalize for Sequential Decision Making"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.02229","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":"sha256:753cee625178c21b843aeb9971e216f1729fd15b1f4114a07591df74e06f69e0","target":"record","created_at":"2026-07-05T01:40:48Z","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":"2bd9b9de27af83bcc72c29db1d755be44152b8353f29a94eda527f872a12151c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-05T18:00:03Z","title_canon_sha256":"7fb1759efc4e14a1f1ac5bb21fd183a87c59b6e89168428f93aeaa92c5f01eab"},"schema_version":"1.0","source":{"id":"2010.02229","kind":"arxiv","version":1}},"canonical_sha256":"ab8f71fc40b10957501c997118196102312a192c422f7195f839ea87b786edb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab8f71fc40b10957501c997118196102312a192c422f7195f839ea87b786edb2","first_computed_at":"2026-07-05T01:40:48.152120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:40:48.152120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"heLfc4enTogtCl3kUZur/wl4dpnCYZXGKOHHLXxjOuqJJKKILE9kiGDOcA2GR12wwZHkNCoPl+qHZNbxJ2SbDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:40:48.152486Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.02229","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:753cee625178c21b843aeb9971e216f1729fd15b1f4114a07591df74e06f69e0","sha256:3ddf5bbe19f928fe3edc3f520f8aaba813a5e376e5730ebda6ed9e0c42046914"],"state_sha256":"e86b8b3a465a1209ce771d7f87628c8ddaa4c58fb15a0de1bf87637c35953bfb"}