{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:OUZWBZG64JG5MJEBZAH3CF7T34","short_pith_number":"pith:OUZWBZG6","canonical_record":{"source":{"id":"1709.04571","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-14T00:18:44Z","cross_cats_sorted":[],"title_canon_sha256":"1d382c0b1d476a4881591eaa3e17fc0501315ed9d578200526129d55cb7abc38","abstract_canon_sha256":"088487a84ff329ba942f9bbede6d9344747979daf2cc5394b117a9c38b810304"},"schema_version":"1.0"},"canonical_sha256":"753360e4dee24dd62481c80fb117f3df2dc9b89f1386dba5183a7cf0e890bdb2","source":{"kind":"arxiv","id":"1709.04571","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.04571","created_at":"2026-05-18T00:35:11Z"},{"alias_kind":"arxiv_version","alias_value":"1709.04571v1","created_at":"2026-05-18T00:35:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.04571","created_at":"2026-05-18T00:35:11Z"},{"alias_kind":"pith_short_12","alias_value":"OUZWBZG64JG5","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OUZWBZG64JG5MJEB","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OUZWBZG6","created_at":"2026-05-18T12:31:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:OUZWBZG64JG5MJEBZAH3CF7T34","target":"record","payload":{"canonical_record":{"source":{"id":"1709.04571","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-14T00:18:44Z","cross_cats_sorted":[],"title_canon_sha256":"1d382c0b1d476a4881591eaa3e17fc0501315ed9d578200526129d55cb7abc38","abstract_canon_sha256":"088487a84ff329ba942f9bbede6d9344747979daf2cc5394b117a9c38b810304"},"schema_version":"1.0"},"canonical_sha256":"753360e4dee24dd62481c80fb117f3df2dc9b89f1386dba5183a7cf0e890bdb2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:11.258367Z","signature_b64":"rcHMJIfsJAAkKxYuH9S7v3XoaDZCG/C7EsagxwmiNkwDE1Hx6YjRJS1b0E9P2WBBTRGtAFeKRkSWmrZe47aoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"753360e4dee24dd62481c80fb117f3df2dc9b89f1386dba5183a7cf0e890bdb2","last_reissued_at":"2026-05-18T00:35:11.257716Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:11.257716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.04571","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":"2026-05-18T00:35:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NIf5O6KO2SbPrNH7MqolQayjewXMI00Nl1+ew6uSYCscz5RYY0OJGjf73h7waUjXP+ywkgwuIIXz5ujOfcLtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:58:05.611744Z"},"content_sha256":"9a98e77481a7b48ea7a812b4e119bc0dfca4eecc2714a794b18ef1f5fcb525b6","schema_version":"1.0","event_id":"sha256:9a98e77481a7b48ea7a812b4e119bc0dfca4eecc2714a794b18ef1f5fcb525b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:OUZWBZG64JG5MJEBZAH3CF7T34","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Waiting is not an Option : Learning Options with a Deliberation Cost","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Doina Precup, Jean Harb, Martin Klissarov, Pierre-Luc Bacon","submitted_at":"2017-09-14T00:18:44Z","abstract_excerpt":"Recent work has shown that temporally extended actions (options) can be learned fully end-to-end as opposed to being specified in advance. While the problem of \"how\" to learn options is increasingly well understood, the question of \"what\" good options should be has remained elusive. We formulate our answer to what \"good\" options should be in the bounded rationality framework (Simon, 1957) through the notion of deliberation cost. We then derive practical gradient-based learning algorithms to implement this objective. Our results in the Arcade Learning Environment (ALE) show increased performanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.04571","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":""},"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":"2026-05-18T00:35:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ihQb2GtLQpb+PEa1QLJtxro8DVx+ijT7pf/+Fz7PNmFXu45qWLXXgRuIsKc0oHZGvtwybtFDh0aCqcPKb+lPCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:58:05.612185Z"},"content_sha256":"386313af2fc46c05a9fdc68f83602299d04930bb6f66ca19ee318dd6499c69c2","schema_version":"1.0","event_id":"sha256:386313af2fc46c05a9fdc68f83602299d04930bb6f66ca19ee318dd6499c69c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OUZWBZG64JG5MJEBZAH3CF7T34/bundle.json","state_url":"https://pith.science/pith/OUZWBZG64JG5MJEBZAH3CF7T34/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OUZWBZG64JG5MJEBZAH3CF7T34/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":"2026-05-25T23:58:05Z","links":{"resolver":"https://pith.science/pith/OUZWBZG64JG5MJEBZAH3CF7T34","bundle":"https://pith.science/pith/OUZWBZG64JG5MJEBZAH3CF7T34/bundle.json","state":"https://pith.science/pith/OUZWBZG64JG5MJEBZAH3CF7T34/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OUZWBZG64JG5MJEBZAH3CF7T34/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:OUZWBZG64JG5MJEBZAH3CF7T34","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":"088487a84ff329ba942f9bbede6d9344747979daf2cc5394b117a9c38b810304","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-14T00:18:44Z","title_canon_sha256":"1d382c0b1d476a4881591eaa3e17fc0501315ed9d578200526129d55cb7abc38"},"schema_version":"1.0","source":{"id":"1709.04571","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.04571","created_at":"2026-05-18T00:35:11Z"},{"alias_kind":"arxiv_version","alias_value":"1709.04571v1","created_at":"2026-05-18T00:35:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.04571","created_at":"2026-05-18T00:35:11Z"},{"alias_kind":"pith_short_12","alias_value":"OUZWBZG64JG5","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OUZWBZG64JG5MJEB","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OUZWBZG6","created_at":"2026-05-18T12:31:34Z"}],"graph_snapshots":[{"event_id":"sha256:386313af2fc46c05a9fdc68f83602299d04930bb6f66ca19ee318dd6499c69c2","target":"graph","created_at":"2026-05-18T00:35:11Z","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"},"paper":{"abstract_excerpt":"Recent work has shown that temporally extended actions (options) can be learned fully end-to-end as opposed to being specified in advance. While the problem of \"how\" to learn options is increasingly well understood, the question of \"what\" good options should be has remained elusive. We formulate our answer to what \"good\" options should be in the bounded rationality framework (Simon, 1957) through the notion of deliberation cost. We then derive practical gradient-based learning algorithms to implement this objective. Our results in the Arcade Learning Environment (ALE) show increased performanc","authors_text":"Doina Precup, Jean Harb, Martin Klissarov, Pierre-Luc Bacon","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-14T00:18:44Z","title":"When Waiting is not an Option : Learning Options with a Deliberation Cost"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.04571","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":"sha256:9a98e77481a7b48ea7a812b4e119bc0dfca4eecc2714a794b18ef1f5fcb525b6","target":"record","created_at":"2026-05-18T00:35:11Z","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":"088487a84ff329ba942f9bbede6d9344747979daf2cc5394b117a9c38b810304","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-14T00:18:44Z","title_canon_sha256":"1d382c0b1d476a4881591eaa3e17fc0501315ed9d578200526129d55cb7abc38"},"schema_version":"1.0","source":{"id":"1709.04571","kind":"arxiv","version":1}},"canonical_sha256":"753360e4dee24dd62481c80fb117f3df2dc9b89f1386dba5183a7cf0e890bdb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"753360e4dee24dd62481c80fb117f3df2dc9b89f1386dba5183a7cf0e890bdb2","first_computed_at":"2026-05-18T00:35:11.257716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:11.257716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rcHMJIfsJAAkKxYuH9S7v3XoaDZCG/C7EsagxwmiNkwDE1Hx6YjRJS1b0E9P2WBBTRGtAFeKRkSWmrZe47aoBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:11.258367Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.04571","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a98e77481a7b48ea7a812b4e119bc0dfca4eecc2714a794b18ef1f5fcb525b6","sha256:386313af2fc46c05a9fdc68f83602299d04930bb6f66ca19ee318dd6499c69c2"],"state_sha256":"68e3d651ccb83f3410042febbba3d7eaae070f4184902a5030c03819b8478a5a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qSQRipHapvaIJoGnucTa7uzRAOtoV4BVy183BQ6siRaIaW92u3sedsPyLwfYtfdW9Hh1D3zbnYfIRqIs8aPuBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T23:58:05.615664Z","bundle_sha256":"a516d03c68f069c8c845c7fa0ea844ffe124887aafab7b136c24753f2c21a96a"}}