{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:QKQV7W2VKZLPBQZ5CQTBCNNZMJ","short_pith_number":"pith:QKQV7W2V","canonical_record":{"source":{"id":"2006.11704","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-21T03:29:05Z","cross_cats_sorted":[],"title_canon_sha256":"5e1f1187c6bcdca0729fa6b2907ae26ef8ad6adf5252209d0dbbc4647cf54e65","abstract_canon_sha256":"509d6b946613dd0be5fe525832c8af98cc544942801a779dc1216acdb9663fd1"},"schema_version":"1.0"},"canonical_sha256":"82a15fdb555656f0c33d14261135b962776bb43c60f79dfab1f7228b4bf0c280","source":{"kind":"arxiv","id":"2006.11704","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.11704","created_at":"2026-07-05T01:11:52Z"},{"alias_kind":"arxiv_version","alias_value":"2006.11704v1","created_at":"2026-07-05T01:11:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11704","created_at":"2026-07-05T01:11:52Z"},{"alias_kind":"pith_short_12","alias_value":"QKQV7W2VKZLP","created_at":"2026-07-05T01:11:52Z"},{"alias_kind":"pith_short_16","alias_value":"QKQV7W2VKZLPBQZ5","created_at":"2026-07-05T01:11:52Z"},{"alias_kind":"pith_short_8","alias_value":"QKQV7W2V","created_at":"2026-07-05T01:11:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:QKQV7W2VKZLPBQZ5CQTBCNNZMJ","target":"record","payload":{"canonical_record":{"source":{"id":"2006.11704","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-21T03:29:05Z","cross_cats_sorted":[],"title_canon_sha256":"5e1f1187c6bcdca0729fa6b2907ae26ef8ad6adf5252209d0dbbc4647cf54e65","abstract_canon_sha256":"509d6b946613dd0be5fe525832c8af98cc544942801a779dc1216acdb9663fd1"},"schema_version":"1.0"},"canonical_sha256":"82a15fdb555656f0c33d14261135b962776bb43c60f79dfab1f7228b4bf0c280","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:52.892779Z","signature_b64":"QERq4pPp9jhMWlF528iz2TLySEV8DKPxloP5cpamxnQiQUnyDhfBhiD7WVqsc4uif/jgyrqkY/oUXJ3yOvM5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82a15fdb555656f0c33d14261135b962776bb43c60f79dfab1f7228b4bf0c280","last_reissued_at":"2026-07-05T01:11:52.892312Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:52.892312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.11704","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":"2026-07-05T01:11:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C0Qr9xCAcIjDUxCxdQfvhAa7lCKaxwsAvii3BkRjYHhIz3TkouiCHv9k18IW0UUD1i2yPXlj0J0j8Tj0rwBEAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T17:39:20.926200Z"},"content_sha256":"eda8afadd2679ff0ce818a915894e6d45977c5e096f6b50264a95c13f4117d28","schema_version":"1.0","event_id":"sha256:eda8afadd2679ff0ce818a915894e6d45977c5e096f6b50264a95c13f4117d28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:QKQV7W2VKZLPBQZ5CQTBCNNZMJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Reinforcement Learning for Deep Goal Reasoning: An Expressiveness Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"H\\'ector Mu\\~noz-Avila, Weihang Yuan","submitted_at":"2020-06-21T03:29:05Z","abstract_excerpt":"Hierarchical DQN (h-DQN) is a two-level architecture of feedforward neural networks where the meta level selects goals and the lower level takes actions to achieve the goals. We show tasks that cannot be solved by h-DQN, exemplifying the limitation of this type of hierarchical framework (HF). We describe the recurrent hierarchical framework (RHF), generalizing architectures that use a recurrent neural network at the meta level. We analyze the expressiveness of HF and RHF using context-sensitive grammars. We show that RHF is more expressive than HF. We perform experiments comparing an implement"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11704","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.11704/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":"2026-07-05T01:11:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bjp9+p7WNSjLzal9tYu7tyk0Hev8q4R3qWGiPOh/cjKoSB8mbFM+NnRSv15c9UA9rl00Ax6YtjPH2H1HTY38Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T17:39:20.926801Z"},"content_sha256":"eb9350a351bf9d003f807dabb6ece27b22f89954be01bd8d3dbaf7031709083a","schema_version":"1.0","event_id":"sha256:eb9350a351bf9d003f807dabb6ece27b22f89954be01bd8d3dbaf7031709083a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QKQV7W2VKZLPBQZ5CQTBCNNZMJ/bundle.json","state_url":"https://pith.science/pith/QKQV7W2VKZLPBQZ5CQTBCNNZMJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QKQV7W2VKZLPBQZ5CQTBCNNZMJ/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":"2026-08-18T17:39:20Z","links":{"resolver":"https://pith.science/pith/QKQV7W2VKZLPBQZ5CQTBCNNZMJ","bundle":"https://pith.science/pith/QKQV7W2VKZLPBQZ5CQTBCNNZMJ/bundle.json","state":"https://pith.science/pith/QKQV7W2VKZLPBQZ5CQTBCNNZMJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QKQV7W2VKZLPBQZ5CQTBCNNZMJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QKQV7W2VKZLPBQZ5CQTBCNNZMJ","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":"509d6b946613dd0be5fe525832c8af98cc544942801a779dc1216acdb9663fd1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-21T03:29:05Z","title_canon_sha256":"5e1f1187c6bcdca0729fa6b2907ae26ef8ad6adf5252209d0dbbc4647cf54e65"},"schema_version":"1.0","source":{"id":"2006.11704","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.11704","created_at":"2026-07-05T01:11:52Z"},{"alias_kind":"arxiv_version","alias_value":"2006.11704v1","created_at":"2026-07-05T01:11:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11704","created_at":"2026-07-05T01:11:52Z"},{"alias_kind":"pith_short_12","alias_value":"QKQV7W2VKZLP","created_at":"2026-07-05T01:11:52Z"},{"alias_kind":"pith_short_16","alias_value":"QKQV7W2VKZLPBQZ5","created_at":"2026-07-05T01:11:52Z"},{"alias_kind":"pith_short_8","alias_value":"QKQV7W2V","created_at":"2026-07-05T01:11:52Z"}],"graph_snapshots":[{"event_id":"sha256:eb9350a351bf9d003f807dabb6ece27b22f89954be01bd8d3dbaf7031709083a","target":"graph","created_at":"2026-07-05T01:11:52Z","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/2006.11704/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hierarchical DQN (h-DQN) is a two-level architecture of feedforward neural networks where the meta level selects goals and the lower level takes actions to achieve the goals. We show tasks that cannot be solved by h-DQN, exemplifying the limitation of this type of hierarchical framework (HF). We describe the recurrent hierarchical framework (RHF), generalizing architectures that use a recurrent neural network at the meta level. We analyze the expressiveness of HF and RHF using context-sensitive grammars. We show that RHF is more expressive than HF. We perform experiments comparing an implement","authors_text":"H\\'ector Mu\\~noz-Avila, Weihang Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-21T03:29:05Z","title":"Hierarchical Reinforcement Learning for Deep Goal Reasoning: An Expressiveness Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11704","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:eda8afadd2679ff0ce818a915894e6d45977c5e096f6b50264a95c13f4117d28","target":"record","created_at":"2026-07-05T01:11:52Z","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":"509d6b946613dd0be5fe525832c8af98cc544942801a779dc1216acdb9663fd1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-21T03:29:05Z","title_canon_sha256":"5e1f1187c6bcdca0729fa6b2907ae26ef8ad6adf5252209d0dbbc4647cf54e65"},"schema_version":"1.0","source":{"id":"2006.11704","kind":"arxiv","version":1}},"canonical_sha256":"82a15fdb555656f0c33d14261135b962776bb43c60f79dfab1f7228b4bf0c280","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"82a15fdb555656f0c33d14261135b962776bb43c60f79dfab1f7228b4bf0c280","first_computed_at":"2026-07-05T01:11:52.892312Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:11:52.892312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QERq4pPp9jhMWlF528iz2TLySEV8DKPxloP5cpamxnQiQUnyDhfBhiD7WVqsc4uif/jgyrqkY/oUXJ3yOvM5CA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:11:52.892779Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.11704","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eda8afadd2679ff0ce818a915894e6d45977c5e096f6b50264a95c13f4117d28","sha256:eb9350a351bf9d003f807dabb6ece27b22f89954be01bd8d3dbaf7031709083a"],"state_sha256":"885ce488aec8c428c4a015fcf547115e11fe025a1e57a4f1d20a39f9145fc636"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pp3aT4VZzOAnvpNy1vQKfRKL2TJqqEoB/M72vt4liUof4Tew7CW4gTj3QRqPJZoQeLvI2nchrPr0hJyX5jH+DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T17:39:20.932162Z","bundle_sha256":"61ee687c396ad963ec79264e664ff1b8fc54506f5760dfe7a6665e5589b00cc3"}}