{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:USVAANPMIO7O3KC555LDYNBOIQ","short_pith_number":"pith:USVAANPM","canonical_record":{"source":{"id":"1907.12477","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-29T15:27:50Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"55c7fd81263dddc45a11124c9a7bf275ae64d8ba56db7c97ce0f7933cdd0d563","abstract_canon_sha256":"0e110d9cfcfc75eb69d7c5c2dc65a3989fdbd35559dec92f2fa7c38f8d117557"},"schema_version":"1.0"},"canonical_sha256":"a4aa0035ec43beeda85def563c342e4422b5f220bcee7224a1367b44b0fe5633","source":{"kind":"arxiv","id":"1907.12477","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:USVAANPMIO7O3KC555LDYNBOIQ","target":"record","payload":{"canonical_record":{"source":{"id":"1907.12477","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-29T15:27:50Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"55c7fd81263dddc45a11124c9a7bf275ae64d8ba56db7c97ce0f7933cdd0d563","abstract_canon_sha256":"0e110d9cfcfc75eb69d7c5c2dc65a3989fdbd35559dec92f2fa7c38f8d117557"},"schema_version":"1.0"},"canonical_sha256":"a4aa0035ec43beeda85def563c342e4422b5f220bcee7224a1367b44b0fe5633","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:06:10.140539Z","signature_b64":"iDkUByPvsEgzJtSBm5kvRHWmMGoTdoJpNVV5Zu6B/zXXz+RL8zljwWls3PppSGv3q3xKp1VBlZWlV7JjbLxzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4aa0035ec43beeda85def563c342e4422b5f220bcee7224a1367b44b0fe5633","last_reissued_at":"2026-07-05T00:06:10.140077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:06:10.140077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.12477","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:06:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YUv9c1gQw1i28wZZgfFwvJgQDQzJtBvTgMsxnKzsjZ/MsKXi/m+cswY2VM274K0FlvDLITpbEZ1QzPeJ10j9Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:37:41.489522Z"},"content_sha256":"adc47139765cdec54531ea2df1628b4115faad949610f422f1006056e6fe7c67","schema_version":"1.0","event_id":"sha256:adc47139765cdec54531ea2df1628b4115faad949610f422f1006056e6fe7c67"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:USVAANPMIO7O3KC555LDYNBOIQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semantic RL with Action Grammars: Data-Efficient Learning of Hierarchical Task Abstractions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Aldo Faisal, Robert Tjarko Lange","submitted_at":"2019-07-29T15:27:50Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.12477","kind":"arxiv","version":2},"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/1907.12477/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":"2026-07-05T00:06:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gk2cksWwUrwXjV0xhqc3uDAtO7vVbGqauZjvqvDrgIVUFWdwafFeZfiRo0fPZsBFngr57Xb7gkZpmYPE9yeOAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:37:41.491528Z"},"content_sha256":"b2056035b58cfe48ead70c4884acd0fe2aa6f36284b6eb301ae6429d5a19c038","schema_version":"1.0","event_id":"sha256:b2056035b58cfe48ead70c4884acd0fe2aa6f36284b6eb301ae6429d5a19c038"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/USVAANPMIO7O3KC555LDYNBOIQ/bundle.json","state_url":"https://pith.science/pith/USVAANPMIO7O3KC555LDYNBOIQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/USVAANPMIO7O3KC555LDYNBOIQ/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":"2026-08-06T04:37:41Z","links":{"resolver":"https://pith.science/pith/USVAANPMIO7O3KC555LDYNBOIQ","bundle":"https://pith.science/pith/USVAANPMIO7O3KC555LDYNBOIQ/bundle.json","state":"https://pith.science/pith/USVAANPMIO7O3KC555LDYNBOIQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/USVAANPMIO7O3KC555LDYNBOIQ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L7EwZsXDqU14/UpCr0A/k6niQbw74vomQ5zrdXo8g8syi+CZgnk3sOgE3oz8NzRCqBVXAlfK3J46eStjZ2fFAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:37:41.498760Z","bundle_sha256":"1ccc121e8515b35eb14e3b1815e95408e4c699dc28cd4aecb24ff1816200768a"}}