{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:7YDLCX3ECWE7ZKYRQMC54Y5KMK","short_pith_number":"pith:7YDLCX3E","canonical_record":{"source":{"id":"2109.09876","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-20T22:50:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f3746eae351b836bd5ffb877ddf98b9975b2bc1ec896f159d59a92abdbed980b","abstract_canon_sha256":"87cf5f80f81de9a7a77b87270f73666a792015dc9b2fba51d9bc59823e1e8733"},"schema_version":"1.0"},"canonical_sha256":"fe06b15f641589fcab118305de63aa62a99568c3c4a0a6f68ee221fa8a1f8107","source":{"kind":"arxiv","id":"2109.09876","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.09876","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"arxiv_version","alias_value":"2109.09876v2","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09876","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"pith_short_12","alias_value":"7YDLCX3ECWE7","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"pith_short_16","alias_value":"7YDLCX3ECWE7ZKYR","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"pith_short_8","alias_value":"7YDLCX3E","created_at":"2026-07-05T04:17:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:7YDLCX3ECWE7ZKYRQMC54Y5KMK","target":"record","payload":{"canonical_record":{"source":{"id":"2109.09876","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-20T22:50:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f3746eae351b836bd5ffb877ddf98b9975b2bc1ec896f159d59a92abdbed980b","abstract_canon_sha256":"87cf5f80f81de9a7a77b87270f73666a792015dc9b2fba51d9bc59823e1e8733"},"schema_version":"1.0"},"canonical_sha256":"fe06b15f641589fcab118305de63aa62a99568c3c4a0a6f68ee221fa8a1f8107","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:17.015529Z","signature_b64":"n3g29QtUd5IDAzu4RTiCHT1h0WQzhhMVM7A1nDdsJ5LCToXd764M2cB6WGo/l0erGwaeP8YdCLH/K01+2VAfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe06b15f641589fcab118305de63aa62a99568c3c4a0a6f68ee221fa8a1f8107","last_reissued_at":"2026-07-05T04:17:17.014994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:17.014994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.09876","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":"2026-07-05T04:17:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"47+XUnbspNVYHGRoU5Pw/cgYd+ubgLGWJN3LW4rXLB2dcFqGI6yqcI7LzEtUrsULIqwIpYAjndp15UgTHs2rCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T01:03:33.365572Z"},"content_sha256":"79126ff64934ce10fd1da6efc39d83c5b199dbca64fa710fa439ddf469b4b975","schema_version":"1.0","event_id":"sha256:79126ff64934ce10fd1da6efc39d83c5b199dbca64fa710fa439ddf469b4b975"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:7YDLCX3ECWE7ZKYRQMC54Y5KMK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Context-Specific Representation Abstraction for Deep Option Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dong-Ki Kim, Gerald Tesauro, Jonathan P. How, Marwa Abdulhai, Matthew Riemer, Miao Liu","submitted_at":"2021-09-20T22:50:01Z","abstract_excerpt":"Hierarchical reinforcement learning has focused on discovering temporally extended actions, such as options, that can provide benefits in problems requiring extensive exploration. One promising approach that learns these options end-to-end is the option-critic (OC) framework. We examine and show in this paper that OC does not decompose a problem into simpler sub-problems, but instead increases the size of the search over policy space with each option considering the entire state space during learning. This issue can result in practical limitations of this method, including sample inefficient l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09876","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/2109.09876/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":"2026-07-05T04:17:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LlW8tG5Op81PV7LtaHJK4wJ+WSqJSa6uMF8j3lTqQ+99+R9wfCENUQmlcEvoEFs2HgPiilVI7A9prf2y4/T+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T01:03:33.365925Z"},"content_sha256":"adc719ba6c6e6e159b3288154b7daa4747edb20e9bc97d16a301e1d39830f9d9","schema_version":"1.0","event_id":"sha256:adc719ba6c6e6e159b3288154b7daa4747edb20e9bc97d16a301e1d39830f9d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7YDLCX3ECWE7ZKYRQMC54Y5KMK/bundle.json","state_url":"https://pith.science/pith/7YDLCX3ECWE7ZKYRQMC54Y5KMK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7YDLCX3ECWE7ZKYRQMC54Y5KMK/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":"2026-08-22T01:03:33Z","links":{"resolver":"https://pith.science/pith/7YDLCX3ECWE7ZKYRQMC54Y5KMK","bundle":"https://pith.science/pith/7YDLCX3ECWE7ZKYRQMC54Y5KMK/bundle.json","state":"https://pith.science/pith/7YDLCX3ECWE7ZKYRQMC54Y5KMK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7YDLCX3ECWE7ZKYRQMC54Y5KMK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7YDLCX3ECWE7ZKYRQMC54Y5KMK","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":"87cf5f80f81de9a7a77b87270f73666a792015dc9b2fba51d9bc59823e1e8733","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-20T22:50:01Z","title_canon_sha256":"f3746eae351b836bd5ffb877ddf98b9975b2bc1ec896f159d59a92abdbed980b"},"schema_version":"1.0","source":{"id":"2109.09876","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.09876","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"arxiv_version","alias_value":"2109.09876v2","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09876","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"pith_short_12","alias_value":"7YDLCX3ECWE7","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"pith_short_16","alias_value":"7YDLCX3ECWE7ZKYR","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"pith_short_8","alias_value":"7YDLCX3E","created_at":"2026-07-05T04:17:17Z"}],"graph_snapshots":[{"event_id":"sha256:adc719ba6c6e6e159b3288154b7daa4747edb20e9bc97d16a301e1d39830f9d9","target":"graph","created_at":"2026-07-05T04:17:17Z","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/2109.09876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hierarchical reinforcement learning has focused on discovering temporally extended actions, such as options, that can provide benefits in problems requiring extensive exploration. One promising approach that learns these options end-to-end is the option-critic (OC) framework. We examine and show in this paper that OC does not decompose a problem into simpler sub-problems, but instead increases the size of the search over policy space with each option considering the entire state space during learning. This issue can result in practical limitations of this method, including sample inefficient l","authors_text":"Dong-Ki Kim, Gerald Tesauro, Jonathan P. How, Marwa Abdulhai, Matthew Riemer, Miao Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-20T22:50:01Z","title":"Context-Specific Representation Abstraction for Deep Option Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09876","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":"sha256:79126ff64934ce10fd1da6efc39d83c5b199dbca64fa710fa439ddf469b4b975","target":"record","created_at":"2026-07-05T04:17:17Z","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":"87cf5f80f81de9a7a77b87270f73666a792015dc9b2fba51d9bc59823e1e8733","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-20T22:50:01Z","title_canon_sha256":"f3746eae351b836bd5ffb877ddf98b9975b2bc1ec896f159d59a92abdbed980b"},"schema_version":"1.0","source":{"id":"2109.09876","kind":"arxiv","version":2}},"canonical_sha256":"fe06b15f641589fcab118305de63aa62a99568c3c4a0a6f68ee221fa8a1f8107","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe06b15f641589fcab118305de63aa62a99568c3c4a0a6f68ee221fa8a1f8107","first_computed_at":"2026-07-05T04:17:17.014994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:17.014994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n3g29QtUd5IDAzu4RTiCHT1h0WQzhhMVM7A1nDdsJ5LCToXd764M2cB6WGo/l0erGwaeP8YdCLH/K01+2VAfDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:17.015529Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.09876","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79126ff64934ce10fd1da6efc39d83c5b199dbca64fa710fa439ddf469b4b975","sha256:adc719ba6c6e6e159b3288154b7daa4747edb20e9bc97d16a301e1d39830f9d9"],"state_sha256":"59a8210351ef050113216ed8e98ec785ff072e7bf6cb8abd169917b82fd26311"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FnUJ+aAmTtkfoYohoAasxZKwz/y/f43GtAK4185+CYZvAsy73aZPXLB0QSPrEGoQzfwftYYG8pf93wSBwdmGBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T01:03:33.369211Z","bundle_sha256":"82ecc2a86591b11e8398c22999ab54c267241a991f07cac312877d003ddb087c"}}