{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:PPQQ4ULEC7U2L4NDGTKGQ6YEBP","short_pith_number":"pith:PPQQ4ULE","canonical_record":{"source":{"id":"2001.08837","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-23T22:33:18Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"ea30e02263216a58d7f4b215fe8f38136774c3723cf9c8ef4b63d37fefb4882d","abstract_canon_sha256":"c59c6ffbc6820902c3df172f59bfd71e7822a46d6f016f827157d3e972742a81"},"schema_version":"1.0"},"canonical_sha256":"7be10e516417e9a5f1a334d4687b040bcbdc609ccbd2f04e12de029b5dd18faf","source":{"kind":"arxiv","id":"2001.08837","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.08837","created_at":"2026-07-05T00:35:36Z"},{"alias_kind":"arxiv_version","alias_value":"2001.08837v1","created_at":"2026-07-05T00:35:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.08837","created_at":"2026-07-05T00:35:36Z"},{"alias_kind":"pith_short_12","alias_value":"PPQQ4ULEC7U2","created_at":"2026-07-05T00:35:36Z"},{"alias_kind":"pith_short_16","alias_value":"PPQQ4ULEC7U2L4ND","created_at":"2026-07-05T00:35:36Z"},{"alias_kind":"pith_short_8","alias_value":"PPQQ4ULE","created_at":"2026-07-05T00:35:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:PPQQ4ULEC7U2L4NDGTKGQ6YEBP","target":"record","payload":{"canonical_record":{"source":{"id":"2001.08837","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-23T22:33:18Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"ea30e02263216a58d7f4b215fe8f38136774c3723cf9c8ef4b63d37fefb4882d","abstract_canon_sha256":"c59c6ffbc6820902c3df172f59bfd71e7822a46d6f016f827157d3e972742a81"},"schema_version":"1.0"},"canonical_sha256":"7be10e516417e9a5f1a334d4687b040bcbdc609ccbd2f04e12de029b5dd18faf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:36.528514Z","signature_b64":"aBkkmU+XyV/ipdVO3GPtRWzIqh1rMhyqx+O7E01gc5TR4DEYTUe5JOUwYEXBA3gx999zs+03AdcCRW8tCT5NDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7be10e516417e9a5f1a334d4687b040bcbdc609ccbd2f04e12de029b5dd18faf","last_reissued_at":"2026-07-05T00:35:36.528030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:36.528030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2001.08837","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":"2026-07-05T00:35:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eLBSrfdZ5OTScnm/1EkBCO+gVmN58xqYc9esV0FPK/wSuCN5j68LdnXl/UvJ28BIaDmQgiS/sg/RUYUqGDIJCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:06:19.016488Z"},"content_sha256":"ac2ed4ad701d535852c639818a9f046fa13d5794eed85bc8e7739fba93ab036d","schema_version":"1.0","event_id":"sha256:ac2ed4ad701d535852c639818a9f046fa13d5794eed85bc8e7739fba93ab036d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:PPQQ4ULEC7U2L4NDGTKGQ6YEBP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Graph Constrained Reinforcement Learning for Natural Language Action Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Matthew Hausknecht, Prithviraj Ammanabrolu","submitted_at":"2020-01-23T22:33:18Z","abstract_excerpt":"Interactive Fiction games are text-based simulations in which an agent interacts with the world purely through natural language. They are ideal environments for studying how to extend reinforcement learning agents to meet the challenges of natural language understanding, partial observability, and action generation in combinatorially-large text-based action spaces. We present KG-A2C, an agent that builds a dynamic knowledge graph while exploring and generates actions using a template-based action space. We contend that the dual uses of the knowledge graph to reason about game state and to cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.08837","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/2001.08837/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":"2026-07-05T00:35:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O/qrbe+T5nF7kIt/e1FaFOdG2Q0+7NRTQ3W0VcV1gJVxx+5leY0xRoEobuTRJQwQZVXj+EUuS30s8M1pSPrQCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:06:19.017474Z"},"content_sha256":"60d0f576e4d07091f720fed5e64b46239b7ec748dd108803d415c8279fb8ff4f","schema_version":"1.0","event_id":"sha256:60d0f576e4d07091f720fed5e64b46239b7ec748dd108803d415c8279fb8ff4f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PPQQ4ULEC7U2L4NDGTKGQ6YEBP/bundle.json","state_url":"https://pith.science/pith/PPQQ4ULEC7U2L4NDGTKGQ6YEBP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PPQQ4ULEC7U2L4NDGTKGQ6YEBP/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":"2026-08-18T14:06:19Z","links":{"resolver":"https://pith.science/pith/PPQQ4ULEC7U2L4NDGTKGQ6YEBP","bundle":"https://pith.science/pith/PPQQ4ULEC7U2L4NDGTKGQ6YEBP/bundle.json","state":"https://pith.science/pith/PPQQ4ULEC7U2L4NDGTKGQ6YEBP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PPQQ4ULEC7U2L4NDGTKGQ6YEBP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PPQQ4ULEC7U2L4NDGTKGQ6YEBP","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":"c59c6ffbc6820902c3df172f59bfd71e7822a46d6f016f827157d3e972742a81","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-23T22:33:18Z","title_canon_sha256":"ea30e02263216a58d7f4b215fe8f38136774c3723cf9c8ef4b63d37fefb4882d"},"schema_version":"1.0","source":{"id":"2001.08837","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.08837","created_at":"2026-07-05T00:35:36Z"},{"alias_kind":"arxiv_version","alias_value":"2001.08837v1","created_at":"2026-07-05T00:35:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.08837","created_at":"2026-07-05T00:35:36Z"},{"alias_kind":"pith_short_12","alias_value":"PPQQ4ULEC7U2","created_at":"2026-07-05T00:35:36Z"},{"alias_kind":"pith_short_16","alias_value":"PPQQ4ULEC7U2L4ND","created_at":"2026-07-05T00:35:36Z"},{"alias_kind":"pith_short_8","alias_value":"PPQQ4ULE","created_at":"2026-07-05T00:35:36Z"}],"graph_snapshots":[{"event_id":"sha256:60d0f576e4d07091f720fed5e64b46239b7ec748dd108803d415c8279fb8ff4f","target":"graph","created_at":"2026-07-05T00:35:36Z","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/2001.08837/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Interactive Fiction games are text-based simulations in which an agent interacts with the world purely through natural language. They are ideal environments for studying how to extend reinforcement learning agents to meet the challenges of natural language understanding, partial observability, and action generation in combinatorially-large text-based action spaces. We present KG-A2C, an agent that builds a dynamic knowledge graph while exploring and generates actions using a template-based action space. We contend that the dual uses of the knowledge graph to reason about game state and to cons","authors_text":"Matthew Hausknecht, Prithviraj Ammanabrolu","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-23T22:33:18Z","title":"Graph Constrained Reinforcement Learning for Natural Language Action Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.08837","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:ac2ed4ad701d535852c639818a9f046fa13d5794eed85bc8e7739fba93ab036d","target":"record","created_at":"2026-07-05T00:35:36Z","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":"c59c6ffbc6820902c3df172f59bfd71e7822a46d6f016f827157d3e972742a81","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-23T22:33:18Z","title_canon_sha256":"ea30e02263216a58d7f4b215fe8f38136774c3723cf9c8ef4b63d37fefb4882d"},"schema_version":"1.0","source":{"id":"2001.08837","kind":"arxiv","version":1}},"canonical_sha256":"7be10e516417e9a5f1a334d4687b040bcbdc609ccbd2f04e12de029b5dd18faf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7be10e516417e9a5f1a334d4687b040bcbdc609ccbd2f04e12de029b5dd18faf","first_computed_at":"2026-07-05T00:35:36.528030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:35:36.528030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aBkkmU+XyV/ipdVO3GPtRWzIqh1rMhyqx+O7E01gc5TR4DEYTUe5JOUwYEXBA3gx999zs+03AdcCRW8tCT5NDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:35:36.528514Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.08837","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac2ed4ad701d535852c639818a9f046fa13d5794eed85bc8e7739fba93ab036d","sha256:60d0f576e4d07091f720fed5e64b46239b7ec748dd108803d415c8279fb8ff4f"],"state_sha256":"ef781eeb8a7485dfb8c213568c936256a7c3d9401734a5217477e41621cbf587"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aYe9VYkQ9zfL4f938QKs2U+Gy2dyGGiLdLC6OxPrKbjW0SSbudciaqYTYtTlwao7bhYaA8vGXJH1431tp4EcAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T14:06:19.024701Z","bundle_sha256":"1df37d96edf22fb39710fee7127bb35c3bfdca669f8d1719f52cf69f449142ac"}}