{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:QXBAC7PD72RWGNRFRDR6ERONEP","short_pith_number":"pith:QXBAC7PD","canonical_record":{"source":{"id":"2110.08470","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-16T04:51:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f67e96600fbd29f51e01c980207630a801f39695c42194033aecb86ec479bce2","abstract_canon_sha256":"18b673791007e12cd6c7f8f796da6c886d38dc3937e9630a2b5e41be19918e17"},"schema_version":"1.0"},"canonical_sha256":"85c2017de3fea363362588e3e245cd23e4f40ba6f157ff92bf5995c3e1615ea3","source":{"kind":"arxiv","id":"2110.08470","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.08470","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"arxiv_version","alias_value":"2110.08470v3","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08470","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"pith_short_12","alias_value":"QXBAC7PD72RW","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"pith_short_16","alias_value":"QXBAC7PD72RWGNRF","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"pith_short_8","alias_value":"QXBAC7PD","created_at":"2026-07-05T04:09:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:QXBAC7PD72RWGNRFRDR6ERONEP","target":"record","payload":{"canonical_record":{"source":{"id":"2110.08470","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-16T04:51:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f67e96600fbd29f51e01c980207630a801f39695c42194033aecb86ec479bce2","abstract_canon_sha256":"18b673791007e12cd6c7f8f796da6c886d38dc3937e9630a2b5e41be19918e17"},"schema_version":"1.0"},"canonical_sha256":"85c2017de3fea363362588e3e245cd23e4f40ba6f157ff92bf5995c3e1615ea3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:15.897760Z","signature_b64":"8ijS966rFJcRlExskC7JLqHvK+GHnXX53cwdNsjIcQdxCqOmHIir+GyTOI+hGfQ67lov1Bv3/eVLbvi9M6DzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85c2017de3fea363362588e3e245cd23e4f40ba6f157ff92bf5995c3e1615ea3","last_reissued_at":"2026-07-05T04:09:15.897267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:15.897267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.08470","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:09:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BQT369OM5TrgwiPiTRQYAgZ9wjjvJRz14CcVvc/deCJNKa77gMpvASflyCpSR4+XmMIML9upl59ylBu75hAVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T08:03:45.542557Z"},"content_sha256":"438fdeee12443bf0efed6c811fd1c65b513e15d74649ef2909734a2a2e517d47","schema_version":"1.0","event_id":"sha256:438fdeee12443bf0efed6c811fd1c65b513e15d74649ef2909734a2a2e517d47"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:QXBAC7PD72RWGNRFRDR6ERONEP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Case-based Reasoning for Better Generalization in Textual Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Keerthiram Murugesan, Mattia Atzeni, Mrinmaya Sachan, Shehzaad Dhuliawala","submitted_at":"2021-10-16T04:51:34Z","abstract_excerpt":"Text-based games (TBG) have emerged as promising environments for driving research in grounded language understanding and studying problems like generalization and sample efficiency. Several deep reinforcement learning (RL) methods with varying architectures and learning schemes have been proposed for TBGs. However, these methods fail to generalize efficiently, especially under distributional shifts. In a departure from deep RL approaches, in this paper, we propose a general method inspired by case-based reasoning to train agents and generalize out of the training distribution. The case-based "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08470","kind":"arxiv","version":3},"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/2110.08470/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:09:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+PGKB33CcKiXarfQJVQFaZPus6AO/LUMmlwe0ipwoxZhMsvZs6G3UNGFtVGFlTvgFq52N2fBzRMo7+MWl40bBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T08:03:45.543464Z"},"content_sha256":"c83d6334aea781987425020eafccbc9690e263d96b1f7caca70f3f436898824b","schema_version":"1.0","event_id":"sha256:c83d6334aea781987425020eafccbc9690e263d96b1f7caca70f3f436898824b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QXBAC7PD72RWGNRFRDR6ERONEP/bundle.json","state_url":"https://pith.science/pith/QXBAC7PD72RWGNRFRDR6ERONEP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QXBAC7PD72RWGNRFRDR6ERONEP/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":"2026-08-07T08:03:45Z","links":{"resolver":"https://pith.science/pith/QXBAC7PD72RWGNRFRDR6ERONEP","bundle":"https://pith.science/pith/QXBAC7PD72RWGNRFRDR6ERONEP/bundle.json","state":"https://pith.science/pith/QXBAC7PD72RWGNRFRDR6ERONEP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QXBAC7PD72RWGNRFRDR6ERONEP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QXBAC7PD72RWGNRFRDR6ERONEP","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":"18b673791007e12cd6c7f8f796da6c886d38dc3937e9630a2b5e41be19918e17","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-16T04:51:34Z","title_canon_sha256":"f67e96600fbd29f51e01c980207630a801f39695c42194033aecb86ec479bce2"},"schema_version":"1.0","source":{"id":"2110.08470","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.08470","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"arxiv_version","alias_value":"2110.08470v3","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08470","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"pith_short_12","alias_value":"QXBAC7PD72RW","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"pith_short_16","alias_value":"QXBAC7PD72RWGNRF","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"pith_short_8","alias_value":"QXBAC7PD","created_at":"2026-07-05T04:09:15Z"}],"graph_snapshots":[{"event_id":"sha256:c83d6334aea781987425020eafccbc9690e263d96b1f7caca70f3f436898824b","target":"graph","created_at":"2026-07-05T04:09:15Z","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/2110.08470/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-based games (TBG) have emerged as promising environments for driving research in grounded language understanding and studying problems like generalization and sample efficiency. Several deep reinforcement learning (RL) methods with varying architectures and learning schemes have been proposed for TBGs. However, these methods fail to generalize efficiently, especially under distributional shifts. In a departure from deep RL approaches, in this paper, we propose a general method inspired by case-based reasoning to train agents and generalize out of the training distribution. The case-based ","authors_text":"Keerthiram Murugesan, Mattia Atzeni, Mrinmaya Sachan, Shehzaad Dhuliawala","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-16T04:51:34Z","title":"Case-based Reasoning for Better Generalization in Textual Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08470","kind":"arxiv","version":3},"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":"sha256:438fdeee12443bf0efed6c811fd1c65b513e15d74649ef2909734a2a2e517d47","target":"record","created_at":"2026-07-05T04:09:15Z","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":"18b673791007e12cd6c7f8f796da6c886d38dc3937e9630a2b5e41be19918e17","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-16T04:51:34Z","title_canon_sha256":"f67e96600fbd29f51e01c980207630a801f39695c42194033aecb86ec479bce2"},"schema_version":"1.0","source":{"id":"2110.08470","kind":"arxiv","version":3}},"canonical_sha256":"85c2017de3fea363362588e3e245cd23e4f40ba6f157ff92bf5995c3e1615ea3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85c2017de3fea363362588e3e245cd23e4f40ba6f157ff92bf5995c3e1615ea3","first_computed_at":"2026-07-05T04:09:15.897267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:09:15.897267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8ijS966rFJcRlExskC7JLqHvK+GHnXX53cwdNsjIcQdxCqOmHIir+GyTOI+hGfQ67lov1Bv3/eVLbvi9M6DzCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:09:15.897760Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.08470","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:438fdeee12443bf0efed6c811fd1c65b513e15d74649ef2909734a2a2e517d47","sha256:c83d6334aea781987425020eafccbc9690e263d96b1f7caca70f3f436898824b"],"state_sha256":"f52cfe16c5b113fb817764c39613e667348027da8dba3f05d02403f288fc7a39"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qbLTwQAST8MKDjy4cERk96gJMrB9NNZAOFsMmyaKWGfLLcxx5zbJsBNh7XENvFoK902DuPcOdmoqVPUTivKfAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T08:03:45.550087Z","bundle_sha256":"97fc17b9e81d5d62d3d643751093305f8759c87195fbde5ab5834057b3825764"}}