{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OTHMYETJCYDQIOQUACQMRTW6AN","short_pith_number":"pith:OTHMYETJ","canonical_record":{"source":{"id":"1812.00855","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-03T16:00:48Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"89e8f4dbdb0a73a8ca8a1167c532e7cc056b549d669ec95303b6bc6686ec8db1","abstract_canon_sha256":"463c3556fb0d3863d0f0b61877c3a038ff5ddf08c3b6404248be536b4f1e67eb"},"schema_version":"1.0"},"canonical_sha256":"74cecc12691607043a1400a0c8cede036aff209db6875378e62654774aad459f","source":{"kind":"arxiv","id":"1812.00855","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.00855","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"arxiv_version","alias_value":"1812.00855v1","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00855","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"pith_short_12","alias_value":"OTHMYETJCYDQ","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OTHMYETJCYDQIOQU","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OTHMYETJ","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OTHMYETJCYDQIOQUACQMRTW6AN","target":"record","payload":{"canonical_record":{"source":{"id":"1812.00855","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-03T16:00:48Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"89e8f4dbdb0a73a8ca8a1167c532e7cc056b549d669ec95303b6bc6686ec8db1","abstract_canon_sha256":"463c3556fb0d3863d0f0b61877c3a038ff5ddf08c3b6404248be536b4f1e67eb"},"schema_version":"1.0"},"canonical_sha256":"74cecc12691607043a1400a0c8cede036aff209db6875378e62654774aad459f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:18.802102Z","signature_b64":"WqxaxDpd63nmRAy92ksQSRZV8zk6X9yShcbcV6ZmoAmzJ382E+aQMTMseTSl0pXPUa4Rofpx9+NWlyWwBVnFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74cecc12691607043a1400a0c8cede036aff209db6875378e62654774aad459f","last_reissued_at":"2026-05-17T23:59:18.801632Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:18.801632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.00855","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WUFnA8gFZgAibRmwa4cS1o3UzG7M1nKc7rKBz0GhSxJnGM/9XoMdRhTeAGFBFfbmSQ2Rl4g7ckDJQDUweM5PBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:00:41.078846Z"},"content_sha256":"d1e224cb015def5dd5e2bcf63a60d0fa28643843a16f44f96cbf78877213e2f4","schema_version":"1.0","event_id":"sha256:d1e224cb015def5dd5e2bcf63a60d0fa28643843a16f44f96cbf78877213e2f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OTHMYETJCYDQIOQUACQMRTW6AN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Solving Text-based Games by Producing Adaptive Action Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Layla El Asri, Marc-Alexandre C\\^ot\\'e, Ruo Yu Tao, Xingdi Yuan","submitted_at":"2018-12-03T16:00:48Z","abstract_excerpt":"To solve a text-based game, an agent needs to formulate valid text commands for a given context and find the ones that lead to success. Recent attempts at solving text-based games with deep reinforcement learning have focused on the latter, i.e., learning to act optimally when valid actions are known in advance. In this work, we propose to tackle the first task and train a model that generates the set of all valid commands for a given context. We try three generative models on a dataset generated with Textworld. The best model can generate valid commands which were unseen at training and achie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00855","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":""},"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":"2026-05-17T23:59:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4hyfzkf9VfKwf2uPqvRXt0vBwZevJAzpTiO+E+IPrDTNplUwvbYb5PvW4eV5Zy0L2ZMIrmnOFwdxAzQY6RSIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:00:41.079198Z"},"content_sha256":"7c0ba5f74a3a7485712f8d4ef359791fca52a99611d767beca81c30162e01e4b","schema_version":"1.0","event_id":"sha256:7c0ba5f74a3a7485712f8d4ef359791fca52a99611d767beca81c30162e01e4b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OTHMYETJCYDQIOQUACQMRTW6AN/bundle.json","state_url":"https://pith.science/pith/OTHMYETJCYDQIOQUACQMRTW6AN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OTHMYETJCYDQIOQUACQMRTW6AN/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":"2026-05-27T15:00:41Z","links":{"resolver":"https://pith.science/pith/OTHMYETJCYDQIOQUACQMRTW6AN","bundle":"https://pith.science/pith/OTHMYETJCYDQIOQUACQMRTW6AN/bundle.json","state":"https://pith.science/pith/OTHMYETJCYDQIOQUACQMRTW6AN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OTHMYETJCYDQIOQUACQMRTW6AN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OTHMYETJCYDQIOQUACQMRTW6AN","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":"463c3556fb0d3863d0f0b61877c3a038ff5ddf08c3b6404248be536b4f1e67eb","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-03T16:00:48Z","title_canon_sha256":"89e8f4dbdb0a73a8ca8a1167c532e7cc056b549d669ec95303b6bc6686ec8db1"},"schema_version":"1.0","source":{"id":"1812.00855","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.00855","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"arxiv_version","alias_value":"1812.00855v1","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00855","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"pith_short_12","alias_value":"OTHMYETJCYDQ","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OTHMYETJCYDQIOQU","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OTHMYETJ","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:7c0ba5f74a3a7485712f8d4ef359791fca52a99611d767beca81c30162e01e4b","target":"graph","created_at":"2026-05-17T23:59:18Z","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":"To solve a text-based game, an agent needs to formulate valid text commands for a given context and find the ones that lead to success. Recent attempts at solving text-based games with deep reinforcement learning have focused on the latter, i.e., learning to act optimally when valid actions are known in advance. In this work, we propose to tackle the first task and train a model that generates the set of all valid commands for a given context. We try three generative models on a dataset generated with Textworld. The best model can generate valid commands which were unseen at training and achie","authors_text":"Layla El Asri, Marc-Alexandre C\\^ot\\'e, Ruo Yu Tao, Xingdi Yuan","cross_cats":["cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-03T16:00:48Z","title":"Towards Solving Text-based Games by Producing Adaptive Action Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00855","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:d1e224cb015def5dd5e2bcf63a60d0fa28643843a16f44f96cbf78877213e2f4","target":"record","created_at":"2026-05-17T23:59:18Z","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":"463c3556fb0d3863d0f0b61877c3a038ff5ddf08c3b6404248be536b4f1e67eb","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-03T16:00:48Z","title_canon_sha256":"89e8f4dbdb0a73a8ca8a1167c532e7cc056b549d669ec95303b6bc6686ec8db1"},"schema_version":"1.0","source":{"id":"1812.00855","kind":"arxiv","version":1}},"canonical_sha256":"74cecc12691607043a1400a0c8cede036aff209db6875378e62654774aad459f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74cecc12691607043a1400a0c8cede036aff209db6875378e62654774aad459f","first_computed_at":"2026-05-17T23:59:18.801632Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:18.801632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WqxaxDpd63nmRAy92ksQSRZV8zk6X9yShcbcV6ZmoAmzJ382E+aQMTMseTSl0pXPUa4Rofpx9+NWlyWwBVnFCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:18.802102Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.00855","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1e224cb015def5dd5e2bcf63a60d0fa28643843a16f44f96cbf78877213e2f4","sha256:7c0ba5f74a3a7485712f8d4ef359791fca52a99611d767beca81c30162e01e4b"],"state_sha256":"21a93fa469d2953e622470e137aff5a61b721fdf186acdc1630e85d42683b18f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S6aqrrTE+ER2sa9Vhlm7njp6v78cg1Qwa1H4lCgpihp/7Lb2wWfyB+X85lRwP1yeDu3hafj45mj4LwJVFN+WAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T15:00:41.082591Z","bundle_sha256":"6fb97e0b64ea1201268ae47e8d3b7e812eca071911c01a071a7a7b80337a00d3"}}