{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XXYT66AXVAO2P4MYC7FCWMIIJZ","short_pith_number":"pith:XXYT66AX","canonical_record":{"source":{"id":"2110.10963","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-10-21T08:21:49Z","cross_cats_sorted":["cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"c3012f53767428fa331c99a21ae2733248b20e516b59ad49af0102749e8d96bf","abstract_canon_sha256":"cde664423cae4df78892c03e5aa5060a3bb683dace1f7d2967e67f331ffd6c01"},"schema_version":"1.0"},"canonical_sha256":"bdf13f7817a81da7f19817ca2b31084e42101381f8553f8758ea0f4586685503","source":{"kind":"arxiv","id":"2110.10963","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.10963","created_at":"2026-07-05T03:24:34Z"},{"alias_kind":"arxiv_version","alias_value":"2110.10963v1","created_at":"2026-07-05T03:24:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10963","created_at":"2026-07-05T03:24:34Z"},{"alias_kind":"pith_short_12","alias_value":"XXYT66AXVAO2","created_at":"2026-07-05T03:24:34Z"},{"alias_kind":"pith_short_16","alias_value":"XXYT66AXVAO2P4MY","created_at":"2026-07-05T03:24:34Z"},{"alias_kind":"pith_short_8","alias_value":"XXYT66AX","created_at":"2026-07-05T03:24:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XXYT66AXVAO2P4MYC7FCWMIIJZ","target":"record","payload":{"canonical_record":{"source":{"id":"2110.10963","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-10-21T08:21:49Z","cross_cats_sorted":["cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"c3012f53767428fa331c99a21ae2733248b20e516b59ad49af0102749e8d96bf","abstract_canon_sha256":"cde664423cae4df78892c03e5aa5060a3bb683dace1f7d2967e67f331ffd6c01"},"schema_version":"1.0"},"canonical_sha256":"bdf13f7817a81da7f19817ca2b31084e42101381f8553f8758ea0f4586685503","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:34.620667Z","signature_b64":"9ff+EAioizZmn9Ab1kP1s6yJsIOLzSw0e3KNTyvvbqVO7emGJs7Dx/ZY4uUQXXlq2+9QyusBdfKw40FE86roDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdf13f7817a81da7f19817ca2b31084e42101381f8553f8758ea0f4586685503","last_reissued_at":"2026-07-05T03:24:34.620101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:34.620101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.10963","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":"2026-07-05T03:24:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xspUF/9FMf2k0pf3gpsnE9oOClueuTDkJ0E7hYw8wE2kBRnqneAK5NBV3jBae5nKPOlUbcJzb57Oj0d7CsZdDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T23:26:16.226455Z"},"content_sha256":"afca518c035ae5d178febcb64abc9a50dab5731bc360f4a66109bb0dc81fc7f3","schema_version":"1.0","event_id":"sha256:afca518c035ae5d178febcb64abc9a50dab5731bc360f4a66109bb0dc81fc7f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XXYT66AXVAO2P4MYC7FCWMIIJZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neuro-Symbolic Reinforcement Learning with First-Order Logic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Akifumi Wachi, Alexander Gray, Asim Munawar, Daiki Kimura, Don Joven Agravante, Masaki Ono, Michiaki Tatsubori, Ryosuke Kohita, Subhajit Chaudhury","submitted_at":"2021-10-21T08:21:49Z","abstract_excerpt":"Deep reinforcement learning (RL) methods often require many trials before convergence, and no direct interpretability of trained policies is provided. In order to achieve fast convergence and interpretability for the policy in RL, we propose a novel RL method for text-based games with a recent neuro-symbolic framework called Logical Neural Network, which can learn symbolic and interpretable rules in their differentiable network. The method is first to extract first-order logical facts from text observation and external word meaning network (ConceptNet), then train a policy in the network with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10963","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/2110.10963/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":"2026-07-05T03:24:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"svEhHHgNW00kuIovJJ5XozEcNgv4TcPQ7MCuXTKTd9avMuSeoZcN8shRm4S+zKDbAo7l1AaJwKBw675m573gAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T23:26:16.226969Z"},"content_sha256":"78f7e5382029ed6cd6a2944ebb94142a4963d5919194f03ce4a68c900acb7d18","schema_version":"1.0","event_id":"sha256:78f7e5382029ed6cd6a2944ebb94142a4963d5919194f03ce4a68c900acb7d18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XXYT66AXVAO2P4MYC7FCWMIIJZ/bundle.json","state_url":"https://pith.science/pith/XXYT66AXVAO2P4MYC7FCWMIIJZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XXYT66AXVAO2P4MYC7FCWMIIJZ/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":"2026-08-14T23:26:16Z","links":{"resolver":"https://pith.science/pith/XXYT66AXVAO2P4MYC7FCWMIIJZ","bundle":"https://pith.science/pith/XXYT66AXVAO2P4MYC7FCWMIIJZ/bundle.json","state":"https://pith.science/pith/XXYT66AXVAO2P4MYC7FCWMIIJZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XXYT66AXVAO2P4MYC7FCWMIIJZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XXYT66AXVAO2P4MYC7FCWMIIJZ","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":"cde664423cae4df78892c03e5aa5060a3bb683dace1f7d2967e67f331ffd6c01","cross_cats_sorted":["cs.CL","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-10-21T08:21:49Z","title_canon_sha256":"c3012f53767428fa331c99a21ae2733248b20e516b59ad49af0102749e8d96bf"},"schema_version":"1.0","source":{"id":"2110.10963","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.10963","created_at":"2026-07-05T03:24:34Z"},{"alias_kind":"arxiv_version","alias_value":"2110.10963v1","created_at":"2026-07-05T03:24:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10963","created_at":"2026-07-05T03:24:34Z"},{"alias_kind":"pith_short_12","alias_value":"XXYT66AXVAO2","created_at":"2026-07-05T03:24:34Z"},{"alias_kind":"pith_short_16","alias_value":"XXYT66AXVAO2P4MY","created_at":"2026-07-05T03:24:34Z"},{"alias_kind":"pith_short_8","alias_value":"XXYT66AX","created_at":"2026-07-05T03:24:34Z"}],"graph_snapshots":[{"event_id":"sha256:78f7e5382029ed6cd6a2944ebb94142a4963d5919194f03ce4a68c900acb7d18","target":"graph","created_at":"2026-07-05T03:24:34Z","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/2110.10963/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (RL) methods often require many trials before convergence, and no direct interpretability of trained policies is provided. In order to achieve fast convergence and interpretability for the policy in RL, we propose a novel RL method for text-based games with a recent neuro-symbolic framework called Logical Neural Network, which can learn symbolic and interpretable rules in their differentiable network. The method is first to extract first-order logical facts from text observation and external word meaning network (ConceptNet), then train a policy in the network with ","authors_text":"Akifumi Wachi, Alexander Gray, Asim Munawar, Daiki Kimura, Don Joven Agravante, Masaki Ono, Michiaki Tatsubori, Ryosuke Kohita, Subhajit Chaudhury","cross_cats":["cs.CL","cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-10-21T08:21:49Z","title":"Neuro-Symbolic Reinforcement Learning with First-Order Logic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10963","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:afca518c035ae5d178febcb64abc9a50dab5731bc360f4a66109bb0dc81fc7f3","target":"record","created_at":"2026-07-05T03:24:34Z","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":"cde664423cae4df78892c03e5aa5060a3bb683dace1f7d2967e67f331ffd6c01","cross_cats_sorted":["cs.CL","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-10-21T08:21:49Z","title_canon_sha256":"c3012f53767428fa331c99a21ae2733248b20e516b59ad49af0102749e8d96bf"},"schema_version":"1.0","source":{"id":"2110.10963","kind":"arxiv","version":1}},"canonical_sha256":"bdf13f7817a81da7f19817ca2b31084e42101381f8553f8758ea0f4586685503","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bdf13f7817a81da7f19817ca2b31084e42101381f8553f8758ea0f4586685503","first_computed_at":"2026-07-05T03:24:34.620101Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:24:34.620101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9ff+EAioizZmn9Ab1kP1s6yJsIOLzSw0e3KNTyvvbqVO7emGJs7Dx/ZY4uUQXXlq2+9QyusBdfKw40FE86roDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:24:34.620667Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.10963","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afca518c035ae5d178febcb64abc9a50dab5731bc360f4a66109bb0dc81fc7f3","sha256:78f7e5382029ed6cd6a2944ebb94142a4963d5919194f03ce4a68c900acb7d18"],"state_sha256":"f5d9894adefca0532133568fc239d405aa5f48c9e69af85157e774167652fa29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wqeEmnEZq7aa2X6CYLoknuqfLVU4Wg+svoNMu4ZH2Xv6ObVafTF8NFjsr80fv53XylCA7dtr1FKAT8lCmEq+Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T23:26:16.230649Z","bundle_sha256":"297f9446032cd5ea3881eaed22e58227dac3f076a122d3f6e0e276b1298c0754"}}