{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:77TDZXEKHKVQUHMFJVZFUBSGWO","short_pith_number":"pith:77TDZXEK","canonical_record":{"source":{"id":"1911.12511","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2019-11-28T03:32:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"036ac8a09420b2933bcfa86aaf3ba7af487f38144005a950db9b602c90e7491d","abstract_canon_sha256":"a5d5a9c5842b340a095ccba9479913b0ed5a4d2c4855e980d4c6ad5d004b3397"},"schema_version":"1.0"},"canonical_sha256":"ffe63cdc8a3aab0a1d854d725a0646b3b7e5dbb29dd339294c090eac45c4ff04","source":{"kind":"arxiv","id":"1911.12511","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.12511","created_at":"2026-07-05T00:22:46Z"},{"alias_kind":"arxiv_version","alias_value":"1911.12511v1","created_at":"2026-07-05T00:22:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.12511","created_at":"2026-07-05T00:22:46Z"},{"alias_kind":"pith_short_12","alias_value":"77TDZXEKHKVQ","created_at":"2026-07-05T00:22:46Z"},{"alias_kind":"pith_short_16","alias_value":"77TDZXEKHKVQUHMF","created_at":"2026-07-05T00:22:46Z"},{"alias_kind":"pith_short_8","alias_value":"77TDZXEK","created_at":"2026-07-05T00:22:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:77TDZXEKHKVQUHMFJVZFUBSGWO","target":"record","payload":{"canonical_record":{"source":{"id":"1911.12511","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2019-11-28T03:32:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"036ac8a09420b2933bcfa86aaf3ba7af487f38144005a950db9b602c90e7491d","abstract_canon_sha256":"a5d5a9c5842b340a095ccba9479913b0ed5a4d2c4855e980d4c6ad5d004b3397"},"schema_version":"1.0"},"canonical_sha256":"ffe63cdc8a3aab0a1d854d725a0646b3b7e5dbb29dd339294c090eac45c4ff04","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:22:46.087950Z","signature_b64":"I8ngStPOi/r6hrv2raLgtVe7iev+uFiGgnN8e8/AEn8Ii2kNKTHycxoBTP7TkZFznWxQAWcb/cxaFRkt0FyzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffe63cdc8a3aab0a1d854d725a0646b3b7e5dbb29dd339294c090eac45c4ff04","last_reissued_at":"2026-07-05T00:22:46.087514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:22:46.087514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.12511","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":"2026-07-05T00:22:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z73/5wvAP+UjH03MoMzMXFelzBD5OLNG252ZCxdaWxexNNs9OEJFxqda0fye0LwTzh1foL/s+4Hhqn7MDVZQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:16:52.272362Z"},"content_sha256":"52dcbc063560c5210da51406dafb558b230eaa0387ab67173fc057bb4d368b14","schema_version":"1.0","event_id":"sha256:52dcbc063560c5210da51406dafb558b230eaa0387ab67173fc057bb4d368b14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:77TDZXEKHKVQUHMFJVZFUBSGWO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Algorithmic Improvements for Deep Reinforcement Learning applied to Interactive Fiction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Doina Precup, Hugo Larochelle, Marc G. Bellemare, Vishal Jain, William Fedus","submitted_at":"2019-11-28T03:32:31Z","abstract_excerpt":"Text-based games are a natural challenge domain for deep reinforcement learning algorithms. Their state and action spaces are combinatorially large, their reward function is sparse, and they are partially observable: the agent is informed of the consequences of its actions through textual feedback. In this paper we emphasize this latter point and consider the design of a deep reinforcement learning agent that can play from feedback alone. Our design recognizes and takes advantage of the structural characteristics of text-based games. We first propose a contextualisation mechanism, based on acc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.12511","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.12511/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":"2026-07-05T00:22:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+jMadKAt50VRTRuhbFNMkjqRARnIDiANj/QJz3K1tD1MEhSyw+kE4nrushJ3mYyQIurhVy2woI5Iqj6++dS+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:16:52.272899Z"},"content_sha256":"725809ce2aad1b73fb73fc2c0dc650926e96647de96535e2885b429257381894","schema_version":"1.0","event_id":"sha256:725809ce2aad1b73fb73fc2c0dc650926e96647de96535e2885b429257381894"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/77TDZXEKHKVQUHMFJVZFUBSGWO/bundle.json","state_url":"https://pith.science/pith/77TDZXEKHKVQUHMFJVZFUBSGWO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/77TDZXEKHKVQUHMFJVZFUBSGWO/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":"2026-08-20T04:16:52Z","links":{"resolver":"https://pith.science/pith/77TDZXEKHKVQUHMFJVZFUBSGWO","bundle":"https://pith.science/pith/77TDZXEKHKVQUHMFJVZFUBSGWO/bundle.json","state":"https://pith.science/pith/77TDZXEKHKVQUHMFJVZFUBSGWO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/77TDZXEKHKVQUHMFJVZFUBSGWO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:77TDZXEKHKVQUHMFJVZFUBSGWO","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":"a5d5a9c5842b340a095ccba9479913b0ed5a4d2c4855e980d4c6ad5d004b3397","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2019-11-28T03:32:31Z","title_canon_sha256":"036ac8a09420b2933bcfa86aaf3ba7af487f38144005a950db9b602c90e7491d"},"schema_version":"1.0","source":{"id":"1911.12511","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.12511","created_at":"2026-07-05T00:22:46Z"},{"alias_kind":"arxiv_version","alias_value":"1911.12511v1","created_at":"2026-07-05T00:22:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.12511","created_at":"2026-07-05T00:22:46Z"},{"alias_kind":"pith_short_12","alias_value":"77TDZXEKHKVQ","created_at":"2026-07-05T00:22:46Z"},{"alias_kind":"pith_short_16","alias_value":"77TDZXEKHKVQUHMF","created_at":"2026-07-05T00:22:46Z"},{"alias_kind":"pith_short_8","alias_value":"77TDZXEK","created_at":"2026-07-05T00:22:46Z"}],"graph_snapshots":[{"event_id":"sha256:725809ce2aad1b73fb73fc2c0dc650926e96647de96535e2885b429257381894","target":"graph","created_at":"2026-07-05T00:22:46Z","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/1911.12511/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-based games are a natural challenge domain for deep reinforcement learning algorithms. Their state and action spaces are combinatorially large, their reward function is sparse, and they are partially observable: the agent is informed of the consequences of its actions through textual feedback. In this paper we emphasize this latter point and consider the design of a deep reinforcement learning agent that can play from feedback alone. Our design recognizes and takes advantage of the structural characteristics of text-based games. We first propose a contextualisation mechanism, based on acc","authors_text":"Doina Precup, Hugo Larochelle, Marc G. Bellemare, Vishal Jain, William Fedus","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2019-11-28T03:32:31Z","title":"Algorithmic Improvements for Deep Reinforcement Learning applied to Interactive Fiction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.12511","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":"sha256:52dcbc063560c5210da51406dafb558b230eaa0387ab67173fc057bb4d368b14","target":"record","created_at":"2026-07-05T00:22:46Z","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":"a5d5a9c5842b340a095ccba9479913b0ed5a4d2c4855e980d4c6ad5d004b3397","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2019-11-28T03:32:31Z","title_canon_sha256":"036ac8a09420b2933bcfa86aaf3ba7af487f38144005a950db9b602c90e7491d"},"schema_version":"1.0","source":{"id":"1911.12511","kind":"arxiv","version":1}},"canonical_sha256":"ffe63cdc8a3aab0a1d854d725a0646b3b7e5dbb29dd339294c090eac45c4ff04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffe63cdc8a3aab0a1d854d725a0646b3b7e5dbb29dd339294c090eac45c4ff04","first_computed_at":"2026-07-05T00:22:46.087514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:22:46.087514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I8ngStPOi/r6hrv2raLgtVe7iev+uFiGgnN8e8/AEn8Ii2kNKTHycxoBTP7TkZFznWxQAWcb/cxaFRkt0FyzAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:22:46.087950Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.12511","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52dcbc063560c5210da51406dafb558b230eaa0387ab67173fc057bb4d368b14","sha256:725809ce2aad1b73fb73fc2c0dc650926e96647de96535e2885b429257381894"],"state_sha256":"da287663cb3be0ec03b8a68b48fe5d2306aedf295d25f612bf7ef49c909a8260"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t4TF9sU6Y5nNRyOD/Uroja54QE4UcaYX/07SGOywJ2qQHuVS3dDLAloQWxLe4u74Loptgkqgz9anJoUG0u0eCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T04:16:52.276816Z","bundle_sha256":"5e878a4c9f00bb1118199fa5fd746069cf6efe89881b1db7f4bf86d677d6f281"}}