{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4CG3GA2XQIKVMUG5L3ZODCIYNL","short_pith_number":"pith:4CG3GA2X","schema_version":"1.0","canonical_sha256":"e08db3035782155650dd5ef2e189186acbe1a10854a23785d12e7b6d1900b48a","source":{"kind":"arxiv","id":"1812.11202","version":4},"attestation_state":"computed","paper":{"title":"State representation learning with recurrent capsule networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Louis Annabi, Michael Garcia Ortiz","submitted_at":"2018-12-28T19:31:26Z","abstract_excerpt":"Unsupervised learning of compact and relevant state representations has been proved very useful at solving complex reinforcement learning tasks. In this paper, we propose a recurrent capsule network that learns such representations by trying to predict the future observations in an agent's trajectory."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1812.11202","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-28T19:31:26Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"909c147f6520276df834bf882fe67ecb44f93ea2e2b22f62f2add80252bcabd5","abstract_canon_sha256":"ea9d4068bf0bf9db7132709a865a6e7f769dda546d7b351cec8d1a9ee25faa45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:58.432669Z","signature_b64":"OIh/Q64QhaAp//tUdXzFYvvFyozlhQ3DZ1XtkMTtLtaN6cgiQrsv0Yp/MV3EP63fGVl9Mh2K4htrxGJLn6gbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e08db3035782155650dd5ef2e189186acbe1a10854a23785d12e7b6d1900b48a","last_reissued_at":"2026-05-17T23:52:58.432051Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:58.432051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"State representation learning with recurrent capsule networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Louis Annabi, Michael Garcia Ortiz","submitted_at":"2018-12-28T19:31:26Z","abstract_excerpt":"Unsupervised learning of compact and relevant state representations has been proved very useful at solving complex reinforcement learning tasks. In this paper, we propose a recurrent capsule network that learns such representations by trying to predict the future observations in an agent's trajectory."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.11202","kind":"arxiv","version":4},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1812.11202","created_at":"2026-05-17T23:52:58.432135+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.11202v4","created_at":"2026-05-17T23:52:58.432135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.11202","created_at":"2026-05-17T23:52:58.432135+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CG3GA2XQIKV","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CG3GA2XQIKVMUG5","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CG3GA2X","created_at":"2026-05-18T12:32:05.422762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4CG3GA2XQIKVMUG5L3ZODCIYNL","json":"https://pith.science/pith/4CG3GA2XQIKVMUG5L3ZODCIYNL.json","graph_json":"https://pith.science/api/pith-number/4CG3GA2XQIKVMUG5L3ZODCIYNL/graph.json","events_json":"https://pith.science/api/pith-number/4CG3GA2XQIKVMUG5L3ZODCIYNL/events.json","paper":"https://pith.science/paper/4CG3GA2X"},"agent_actions":{"view_html":"https://pith.science/pith/4CG3GA2XQIKVMUG5L3ZODCIYNL","download_json":"https://pith.science/pith/4CG3GA2XQIKVMUG5L3ZODCIYNL.json","view_paper":"https://pith.science/paper/4CG3GA2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.11202&json=true","fetch_graph":"https://pith.science/api/pith-number/4CG3GA2XQIKVMUG5L3ZODCIYNL/graph.json","fetch_events":"https://pith.science/api/pith-number/4CG3GA2XQIKVMUG5L3ZODCIYNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CG3GA2XQIKVMUG5L3ZODCIYNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CG3GA2XQIKVMUG5L3ZODCIYNL/action/storage_attestation","attest_author":"https://pith.science/pith/4CG3GA2XQIKVMUG5L3ZODCIYNL/action/author_attestation","sign_citation":"https://pith.science/pith/4CG3GA2XQIKVMUG5L3ZODCIYNL/action/citation_signature","submit_replication":"https://pith.science/pith/4CG3GA2XQIKVMUG5L3ZODCIYNL/action/replication_record"}},"created_at":"2026-05-17T23:52:58.432135+00:00","updated_at":"2026-05-17T23:52:58.432135+00:00"}