{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:KPRBYYTCDABKKA5N2PHRNEP2QX","short_pith_number":"pith:KPRBYYTC","canonical_record":{"source":{"id":"1701.02392","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-09T23:36:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a159335a1b777f2e468122172f315ed97107fa2720319fd6e7ece69a564702e9","abstract_canon_sha256":"f82e6f197ccab0e9589fd1f504521c4c12c33c8917cbe2bb2036443b8752b989"},"schema_version":"1.0"},"canonical_sha256":"53e21c62621802a503add3cf1691fa85d904b0db59289e7b0fef4436d29a1cf1","source":{"kind":"arxiv","id":"1701.02392","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.02392","created_at":"2026-05-18T00:53:04Z"},{"alias_kind":"arxiv_version","alias_value":"1701.02392v1","created_at":"2026-05-18T00:53:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.02392","created_at":"2026-05-18T00:53:04Z"},{"alias_kind":"pith_short_12","alias_value":"KPRBYYTCDABK","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"KPRBYYTCDABKKA5N","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"KPRBYYTC","created_at":"2026-05-18T12:31:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:KPRBYYTCDABKKA5N2PHRNEP2QX","target":"record","payload":{"canonical_record":{"source":{"id":"1701.02392","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-09T23:36:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a159335a1b777f2e468122172f315ed97107fa2720319fd6e7ece69a564702e9","abstract_canon_sha256":"f82e6f197ccab0e9589fd1f504521c4c12c33c8917cbe2bb2036443b8752b989"},"schema_version":"1.0"},"canonical_sha256":"53e21c62621802a503add3cf1691fa85d904b0db59289e7b0fef4436d29a1cf1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:53:04.349069Z","signature_b64":"+KRWJBhFoRHVBqIhnUsifMiOPUzmm0oZ1yrsw2MSu6geJ7Rl7c/W9sP7Jb79AgE8wrG8mRaXFifXayF254R5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53e21c62621802a503add3cf1691fa85d904b0db59289e7b0fef4436d29a1cf1","last_reissued_at":"2026-05-18T00:53:04.348480Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:53:04.348480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1701.02392","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":"2026-05-18T00:53:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K4sQ2UnSHAAb7Pwe96hrWQRmV/lflQ6MtF+qWs+0BLp636lKKjh/66DzkAAvOx4Y2SZsxrzhRVR6ADZWIfZBBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T02:26:15.612398Z"},"content_sha256":"64098a83ca868a6c4c228a82ab19483d50cdb2cb6b0a1d450cfd531c53ff686f","schema_version":"1.0","event_id":"sha256:64098a83ca868a6c4c228a82ab19483d50cdb2cb6b0a1d450cfd531c53ff686f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:KPRBYYTCDABKKA5N2PHRNEP2QX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning via Recurrent Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Prithwijit Guha, Santosha K. Dwivedy, Tanmay Shankar","submitted_at":"2017-01-09T23:36:05Z","abstract_excerpt":"Deep Reinforcement Learning has enabled the learning of policies for complex tasks in partially observable environments, without explicitly learning the underlying model of the tasks. While such model-free methods achieve considerable performance, they often ignore the structure of task. We present a natural representation of to Reinforcement Learning (RL) problems using Recurrent Convolutional Neural Networks (RCNNs), to better exploit this inherent structure. We define 3 such RCNNs, whose forward passes execute an efficient Value Iteration, propagate beliefs of state in partially observable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.02392","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":"2026-05-18T00:53:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+uhnF73sTHbDInSR0uwB/sDI3cQOxf0LoDOB5hIeiQ1TNcRXCtLXWNhhJqMhOd4hPwa9jXRn0JuNl++REzELCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T02:26:15.612749Z"},"content_sha256":"8d70646c4e8f8506abb109b662e4551c73f55366a1be9e7df3948e4cedc3ffea","schema_version":"1.0","event_id":"sha256:8d70646c4e8f8506abb109b662e4551c73f55366a1be9e7df3948e4cedc3ffea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KPRBYYTCDABKKA5N2PHRNEP2QX/bundle.json","state_url":"https://pith.science/pith/KPRBYYTCDABKKA5N2PHRNEP2QX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KPRBYYTCDABKKA5N2PHRNEP2QX/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":"2026-06-24T02:26:15Z","links":{"resolver":"https://pith.science/pith/KPRBYYTCDABKKA5N2PHRNEP2QX","bundle":"https://pith.science/pith/KPRBYYTCDABKKA5N2PHRNEP2QX/bundle.json","state":"https://pith.science/pith/KPRBYYTCDABKKA5N2PHRNEP2QX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KPRBYYTCDABKKA5N2PHRNEP2QX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:KPRBYYTCDABKKA5N2PHRNEP2QX","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":"f82e6f197ccab0e9589fd1f504521c4c12c33c8917cbe2bb2036443b8752b989","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-09T23:36:05Z","title_canon_sha256":"a159335a1b777f2e468122172f315ed97107fa2720319fd6e7ece69a564702e9"},"schema_version":"1.0","source":{"id":"1701.02392","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.02392","created_at":"2026-05-18T00:53:04Z"},{"alias_kind":"arxiv_version","alias_value":"1701.02392v1","created_at":"2026-05-18T00:53:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.02392","created_at":"2026-05-18T00:53:04Z"},{"alias_kind":"pith_short_12","alias_value":"KPRBYYTCDABK","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"KPRBYYTCDABKKA5N","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"KPRBYYTC","created_at":"2026-05-18T12:31:24Z"}],"graph_snapshots":[{"event_id":"sha256:8d70646c4e8f8506abb109b662e4551c73f55366a1be9e7df3948e4cedc3ffea","target":"graph","created_at":"2026-05-18T00:53:04Z","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":"Deep Reinforcement Learning has enabled the learning of policies for complex tasks in partially observable environments, without explicitly learning the underlying model of the tasks. While such model-free methods achieve considerable performance, they often ignore the structure of task. We present a natural representation of to Reinforcement Learning (RL) problems using Recurrent Convolutional Neural Networks (RCNNs), to better exploit this inherent structure. We define 3 such RCNNs, whose forward passes execute an efficient Value Iteration, propagate beliefs of state in partially observable ","authors_text":"Prithwijit Guha, Santosha K. Dwivedy, Tanmay Shankar","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-09T23:36:05Z","title":"Reinforcement Learning via Recurrent Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.02392","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":"sha256:64098a83ca868a6c4c228a82ab19483d50cdb2cb6b0a1d450cfd531c53ff686f","target":"record","created_at":"2026-05-18T00:53:04Z","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":"f82e6f197ccab0e9589fd1f504521c4c12c33c8917cbe2bb2036443b8752b989","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-09T23:36:05Z","title_canon_sha256":"a159335a1b777f2e468122172f315ed97107fa2720319fd6e7ece69a564702e9"},"schema_version":"1.0","source":{"id":"1701.02392","kind":"arxiv","version":1}},"canonical_sha256":"53e21c62621802a503add3cf1691fa85d904b0db59289e7b0fef4436d29a1cf1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53e21c62621802a503add3cf1691fa85d904b0db59289e7b0fef4436d29a1cf1","first_computed_at":"2026-05-18T00:53:04.348480Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:53:04.348480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+KRWJBhFoRHVBqIhnUsifMiOPUzmm0oZ1yrsw2MSu6geJ7Rl7c/W9sP7Jb79AgE8wrG8mRaXFifXayF254R5BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:53:04.349069Z","signed_message":"canonical_sha256_bytes"},"source_id":"1701.02392","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64098a83ca868a6c4c228a82ab19483d50cdb2cb6b0a1d450cfd531c53ff686f","sha256:8d70646c4e8f8506abb109b662e4551c73f55366a1be9e7df3948e4cedc3ffea"],"state_sha256":"616bad849edb95ae82a064ab27f2b01c21396343878271895f943e294e233b79"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QWhAc94dcfLCWDl56tDLU7ZouvDaJ04IWnMdURuL/qiKpTq/aOsIrxTZBahczkZGlZm+gsLkzWvrbLgVCitBBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-24T02:26:15.614721Z","bundle_sha256":"3164208cffcdb2259f0cea1e96c39295dbf0c70ac00695cef94594db45e3d9f8"}}