{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:YD353VD2MH4SOSYCT77X2TFPGT","short_pith_number":"pith:YD353VD2","canonical_record":{"source":{"id":"2112.08907","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2021-12-16T14:24:35Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"2ef87c1da9fc79ed86fdad9c841e062ed8c6dec2d1e6c546d973297a00c6881d","abstract_canon_sha256":"ea2ae7f74fb4342f3e9dc4f8c37ad964decd24a66b714c4ce537e59646162471"},"schema_version":"1.0"},"canonical_sha256":"c0f7ddd47a61f9274b029fff7d4caf34f29bb1740eb7c0891e65c7dd2558110c","source":{"kind":"arxiv","id":"2112.08907","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08907","created_at":"2026-07-05T05:04:11Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08907v3","created_at":"2026-07-05T05:04:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08907","created_at":"2026-07-05T05:04:11Z"},{"alias_kind":"pith_short_12","alias_value":"YD353VD2MH4S","created_at":"2026-07-05T05:04:11Z"},{"alias_kind":"pith_short_16","alias_value":"YD353VD2MH4SOSYC","created_at":"2026-07-05T05:04:11Z"},{"alias_kind":"pith_short_8","alias_value":"YD353VD2","created_at":"2026-07-05T05:04:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:YD353VD2MH4SOSYCT77X2TFPGT","target":"record","payload":{"canonical_record":{"source":{"id":"2112.08907","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2021-12-16T14:24:35Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"2ef87c1da9fc79ed86fdad9c841e062ed8c6dec2d1e6c546d973297a00c6881d","abstract_canon_sha256":"ea2ae7f74fb4342f3e9dc4f8c37ad964decd24a66b714c4ce537e59646162471"},"schema_version":"1.0"},"canonical_sha256":"c0f7ddd47a61f9274b029fff7d4caf34f29bb1740eb7c0891e65c7dd2558110c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:11.210943Z","signature_b64":"ENahjCtG7fZTyKOa9UN78/QQfy2qMmyvOpNyVWPr5D82bAUZWHAV71G1s9qNzy4nZDAaFEnj/febhSyjAvjnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0f7ddd47a61f9274b029fff7d4caf34f29bb1740eb7c0891e65c7dd2558110c","last_reissued_at":"2026-07-05T05:04:11.210463Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:11.210463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.08907","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":"2026-07-05T05:04:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E12XFNMLIeH1IMUnpzhZPoWNzSQZ5+7hhC3xx728YExOO8zwN1Tmj8ddwpUlGpdLDq/m9aibQ1ri3FC/MUzlAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T08:03:47.734853Z"},"content_sha256":"7ce27fa8e150f00ec6473777bfa79f0adb2fdadbff92ae9dd06de67980ce7530","schema_version":"1.0","event_id":"sha256:7ce27fa8e150f00ec6473777bfa79f0adb2fdadbff92ae9dd06de67980ce7530"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:YD353VD2MH4SOSYCT77X2TFPGT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inherently Explainable Reinforcement Learning in Natural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.HC","authors_text":"Mark O. Riedl, Prithviraj Ammanabrolu, Xiangyu Peng","submitted_at":"2021-12-16T14:24:35Z","abstract_excerpt":"We focus on the task of creating a reinforcement learning agent that is inherently explainable -- with the ability to produce immediate local explanations by thinking out loud while performing a task and analyzing entire trajectories post-hoc to produce causal explanations. This Hierarchically Explainable Reinforcement Learning agent (HEX-RL), operates in Interactive Fictions, text-based game environments in which an agent perceives and acts upon the world using textual natural language. These games are usually structured as puzzles or quests with long-term dependencies in which an agent must "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08907","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/2112.08907/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":"2026-07-05T05:04:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ndNoa/pGRBrb4D/FP2oFbaMdKrMXXyFEK8iAfuPQAlW6EHHWwKbkCCiaBPKp4NsTUOQd8vM/ErEkaMCDEsUaAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T08:03:47.735232Z"},"content_sha256":"4e0bef00ae7ab8d3201710ab2f6a218459740bdad2a5ca493b76c22bbd5b82af","schema_version":"1.0","event_id":"sha256:4e0bef00ae7ab8d3201710ab2f6a218459740bdad2a5ca493b76c22bbd5b82af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YD353VD2MH4SOSYCT77X2TFPGT/bundle.json","state_url":"https://pith.science/pith/YD353VD2MH4SOSYCT77X2TFPGT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YD353VD2MH4SOSYCT77X2TFPGT/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":"2026-07-11T08:03:47Z","links":{"resolver":"https://pith.science/pith/YD353VD2MH4SOSYCT77X2TFPGT","bundle":"https://pith.science/pith/YD353VD2MH4SOSYCT77X2TFPGT/bundle.json","state":"https://pith.science/pith/YD353VD2MH4SOSYCT77X2TFPGT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YD353VD2MH4SOSYCT77X2TFPGT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YD353VD2MH4SOSYCT77X2TFPGT","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":"ea2ae7f74fb4342f3e9dc4f8c37ad964decd24a66b714c4ce537e59646162471","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2021-12-16T14:24:35Z","title_canon_sha256":"2ef87c1da9fc79ed86fdad9c841e062ed8c6dec2d1e6c546d973297a00c6881d"},"schema_version":"1.0","source":{"id":"2112.08907","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08907","created_at":"2026-07-05T05:04:11Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08907v3","created_at":"2026-07-05T05:04:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08907","created_at":"2026-07-05T05:04:11Z"},{"alias_kind":"pith_short_12","alias_value":"YD353VD2MH4S","created_at":"2026-07-05T05:04:11Z"},{"alias_kind":"pith_short_16","alias_value":"YD353VD2MH4SOSYC","created_at":"2026-07-05T05:04:11Z"},{"alias_kind":"pith_short_8","alias_value":"YD353VD2","created_at":"2026-07-05T05:04:11Z"}],"graph_snapshots":[{"event_id":"sha256:4e0bef00ae7ab8d3201710ab2f6a218459740bdad2a5ca493b76c22bbd5b82af","target":"graph","created_at":"2026-07-05T05:04:11Z","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/2112.08907/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We focus on the task of creating a reinforcement learning agent that is inherently explainable -- with the ability to produce immediate local explanations by thinking out loud while performing a task and analyzing entire trajectories post-hoc to produce causal explanations. This Hierarchically Explainable Reinforcement Learning agent (HEX-RL), operates in Interactive Fictions, text-based game environments in which an agent perceives and acts upon the world using textual natural language. These games are usually structured as puzzles or quests with long-term dependencies in which an agent must ","authors_text":"Mark O. Riedl, Prithviraj Ammanabrolu, Xiangyu Peng","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2021-12-16T14:24:35Z","title":"Inherently Explainable Reinforcement Learning in Natural Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08907","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":"sha256:7ce27fa8e150f00ec6473777bfa79f0adb2fdadbff92ae9dd06de67980ce7530","target":"record","created_at":"2026-07-05T05:04:11Z","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":"ea2ae7f74fb4342f3e9dc4f8c37ad964decd24a66b714c4ce537e59646162471","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2021-12-16T14:24:35Z","title_canon_sha256":"2ef87c1da9fc79ed86fdad9c841e062ed8c6dec2d1e6c546d973297a00c6881d"},"schema_version":"1.0","source":{"id":"2112.08907","kind":"arxiv","version":3}},"canonical_sha256":"c0f7ddd47a61f9274b029fff7d4caf34f29bb1740eb7c0891e65c7dd2558110c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0f7ddd47a61f9274b029fff7d4caf34f29bb1740eb7c0891e65c7dd2558110c","first_computed_at":"2026-07-05T05:04:11.210463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:11.210463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ENahjCtG7fZTyKOa9UN78/QQfy2qMmyvOpNyVWPr5D82bAUZWHAV71G1s9qNzy4nZDAaFEnj/febhSyjAvjnBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:11.210943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.08907","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ce27fa8e150f00ec6473777bfa79f0adb2fdadbff92ae9dd06de67980ce7530","sha256:4e0bef00ae7ab8d3201710ab2f6a218459740bdad2a5ca493b76c22bbd5b82af"],"state_sha256":"ac1536a623b732f4c0c72b53f708759df842b0ef4b2e6c7e69776a5b62f46e30"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uKxAjqCk6nfITOY2/jfJgf0qwbT87stkJmuqZO6ZmK2p7JMYyUbOPrsXov0+SUyH5W5GXdmmtG6Mk1Qs4BS/CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T08:03:47.737858Z","bundle_sha256":"3f15df0e1b8033da7b795ca40216a57bf3f6d38d3fe34221a169bf88b3a23b6f"}}