{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:USVAANPMIO7O3KC555LDYNBOIQ","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":"0e110d9cfcfc75eb69d7c5c2dc65a3989fdbd35559dec92f2fa7c38f8d117557","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-29T15:27:50Z","title_canon_sha256":"55c7fd81263dddc45a11124c9a7bf275ae64d8ba56db7c97ce0f7933cdd0d563"},"schema_version":"1.0","source":{"id":"1907.12477","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.12477","created_at":"2026-07-05T00:06:10Z"},{"alias_kind":"arxiv_version","alias_value":"1907.12477v2","created_at":"2026-07-05T00:06:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.12477","created_at":"2026-07-05T00:06:10Z"},{"alias_kind":"pith_short_12","alias_value":"USVAANPMIO7O","created_at":"2026-07-05T00:06:10Z"},{"alias_kind":"pith_short_16","alias_value":"USVAANPMIO7O3KC5","created_at":"2026-07-05T00:06:10Z"},{"alias_kind":"pith_short_8","alias_value":"USVAANPM","created_at":"2026-07-05T00:06:10Z"}],"graph_snapshots":[{"event_id":"sha256:b2056035b58cfe48ead70c4884acd0fe2aa6f36284b6eb301ae6429d5a19c038","target":"graph","created_at":"2026-07-05T00:06:10Z","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/1907.12477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hierarchical Reinforcement Learning algorithms have successfully been applied to temporal credit assignment problems with sparse reward signals. However, state-of-the-art algorithms require manual specification of sub-task structures, a sample inefficient exploration phase or lack semantic interpretability. Humans, on the other hand, efficiently detect hierarchical sub-structures induced by their surroundings. It has been argued that this inference process universally applies to language, logical reasoning as well as motor control. Therefore, we propose a cognitive-inspired Reinforcement Learn","authors_text":"Aldo Faisal, Robert Tjarko Lange","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-29T15:27:50Z","title":"Semantic RL with Action Grammars: Data-Efficient Learning of Hierarchical Task Abstractions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.12477","kind":"arxiv","version":2},"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:adc47139765cdec54531ea2df1628b4115faad949610f422f1006056e6fe7c67","target":"record","created_at":"2026-07-05T00:06:10Z","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":"0e110d9cfcfc75eb69d7c5c2dc65a3989fdbd35559dec92f2fa7c38f8d117557","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-29T15:27:50Z","title_canon_sha256":"55c7fd81263dddc45a11124c9a7bf275ae64d8ba56db7c97ce0f7933cdd0d563"},"schema_version":"1.0","source":{"id":"1907.12477","kind":"arxiv","version":2}},"canonical_sha256":"a4aa0035ec43beeda85def563c342e4422b5f220bcee7224a1367b44b0fe5633","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4aa0035ec43beeda85def563c342e4422b5f220bcee7224a1367b44b0fe5633","first_computed_at":"2026-07-05T00:06:10.140077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:06:10.140077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iDkUByPvsEgzJtSBm5kvRHWmMGoTdoJpNVV5Zu6B/zXXz+RL8zljwWls3PppSGv3q3xKp1VBlZWlV7JjbLxzCA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:06:10.140539Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.12477","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:adc47139765cdec54531ea2df1628b4115faad949610f422f1006056e6fe7c67","sha256:b2056035b58cfe48ead70c4884acd0fe2aa6f36284b6eb301ae6429d5a19c038"],"state_sha256":"dedaf1b5bcb733deb229dd89106c9af741417e9fbf62827b4287fd3d00297a17"}