{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:V44U676KN7TWWNNH25WAHVBZHY","short_pith_number":"pith:V44U676K","canonical_record":{"source":{"id":"1711.09048","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-24T16:58:45Z","cross_cats_sorted":["cs.RO","cs.SY"],"title_canon_sha256":"ec2a35efa7e7944c679874d9fe00d93e41600efa043b078976ee2c8a5c1bf777","abstract_canon_sha256":"9cc1353a9bff203f3635cd793f143121a3cf587f06a9a62a6298205ab8b7428b"},"schema_version":"1.0"},"canonical_sha256":"af394f7fca6fe76b35a7d76c03d4393e1ad59afefc7d262629fca81e63196513","source":{"kind":"arxiv","id":"1711.09048","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.09048","created_at":"2026-05-17T23:52:55Z"},{"alias_kind":"arxiv_version","alias_value":"1711.09048v3","created_at":"2026-05-17T23:52:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.09048","created_at":"2026-05-17T23:52:55Z"},{"alias_kind":"pith_short_12","alias_value":"V44U676KN7TW","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"V44U676KN7TWWNNH","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"V44U676K","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:V44U676KN7TWWNNH25WAHVBZHY","target":"record","payload":{"canonical_record":{"source":{"id":"1711.09048","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-24T16:58:45Z","cross_cats_sorted":["cs.RO","cs.SY"],"title_canon_sha256":"ec2a35efa7e7944c679874d9fe00d93e41600efa043b078976ee2c8a5c1bf777","abstract_canon_sha256":"9cc1353a9bff203f3635cd793f143121a3cf587f06a9a62a6298205ab8b7428b"},"schema_version":"1.0"},"canonical_sha256":"af394f7fca6fe76b35a7d76c03d4393e1ad59afefc7d262629fca81e63196513","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:55.920292Z","signature_b64":"wmVCJaHVvWRlWH3Irm1NdNti4eNLLGEpXOE73Cjf1AZl02czmPplBL/SHmPAc11p4MsE0q6vB8g0F3UE1g5yAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af394f7fca6fe76b35a7d76c03d4393e1ad59afefc7d262629fca81e63196513","last_reissued_at":"2026-05-17T23:52:55.919588Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:55.919588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.09048","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:52:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a20kgn4kjJ89FVJNWMdN1kOrnblkJ0VR8xtItxp6BWXNLeLeHNBe4NWwyAhco1t3pDnv7nlJJbLfrck5cAOgAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T06:48:33.146386Z"},"content_sha256":"c0fb0ea29691179ececa8e163bb0fd0e2c835b4c124476e5e84e0f621006d222","schema_version":"1.0","event_id":"sha256:c0fb0ea29691179ececa8e163bb0fd0e2c835b4c124476e5e84e0f621006d222"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:V44U676KN7TWWNNH25WAHVBZHY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Compression-Inspired Framework for Macro Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","cs.SY"],"primary_cat":"cs.AI","authors_text":"Bruno C. da Silva, Francisco M. Garcia, Philip S. Thomas","submitted_at":"2017-11-24T16:58:45Z","abstract_excerpt":"In this paper we consider the problem of how a reinforcement learning agent tasked with solving a set of related Markov decision processes can use knowledge acquired early in its lifetime to improve its ability to more rapidly solve novel, but related, tasks. One way of exploiting this experience is by identifying recurrent patterns in trajectories obtained from well-performing policies. We propose a three-step framework in which an agent 1) generates a set of candidate open-loop macros by compressing trajectories drawn from near-optimal policies; 2) evaluates the value of each macro; and 3) s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.09048","kind":"arxiv","version":3},"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":"2026-05-17T23:52:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7AU+VCvtghXqAOotNoFW7s+koFqQo24ctEQAXH1srpdmq3zBA008CvJqiteQYzp2Bv2rY40Y964iLGMkvDePAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T06:48:33.147086Z"},"content_sha256":"bb11d8a06f9496b06456327b4e69361fb9017eb53cc6459552ac7512a9bb4f72","schema_version":"1.0","event_id":"sha256:bb11d8a06f9496b06456327b4e69361fb9017eb53cc6459552ac7512a9bb4f72"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V44U676KN7TWWNNH25WAHVBZHY/bundle.json","state_url":"https://pith.science/pith/V44U676KN7TWWNNH25WAHVBZHY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V44U676KN7TWWNNH25WAHVBZHY/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":"2026-06-06T06:48:33Z","links":{"resolver":"https://pith.science/pith/V44U676KN7TWWNNH25WAHVBZHY","bundle":"https://pith.science/pith/V44U676KN7TWWNNH25WAHVBZHY/bundle.json","state":"https://pith.science/pith/V44U676KN7TWWNNH25WAHVBZHY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V44U676KN7TWWNNH25WAHVBZHY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:V44U676KN7TWWNNH25WAHVBZHY","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":"9cc1353a9bff203f3635cd793f143121a3cf587f06a9a62a6298205ab8b7428b","cross_cats_sorted":["cs.RO","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-24T16:58:45Z","title_canon_sha256":"ec2a35efa7e7944c679874d9fe00d93e41600efa043b078976ee2c8a5c1bf777"},"schema_version":"1.0","source":{"id":"1711.09048","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.09048","created_at":"2026-05-17T23:52:55Z"},{"alias_kind":"arxiv_version","alias_value":"1711.09048v3","created_at":"2026-05-17T23:52:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.09048","created_at":"2026-05-17T23:52:55Z"},{"alias_kind":"pith_short_12","alias_value":"V44U676KN7TW","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"V44U676KN7TWWNNH","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"V44U676K","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:bb11d8a06f9496b06456327b4e69361fb9017eb53cc6459552ac7512a9bb4f72","target":"graph","created_at":"2026-05-17T23:52:55Z","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":"In this paper we consider the problem of how a reinforcement learning agent tasked with solving a set of related Markov decision processes can use knowledge acquired early in its lifetime to improve its ability to more rapidly solve novel, but related, tasks. One way of exploiting this experience is by identifying recurrent patterns in trajectories obtained from well-performing policies. We propose a three-step framework in which an agent 1) generates a set of candidate open-loop macros by compressing trajectories drawn from near-optimal policies; 2) evaluates the value of each macro; and 3) s","authors_text":"Bruno C. da Silva, Francisco M. Garcia, Philip S. Thomas","cross_cats":["cs.RO","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-24T16:58:45Z","title":"A Compression-Inspired Framework for Macro Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.09048","kind":"arxiv","version":3},"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:c0fb0ea29691179ececa8e163bb0fd0e2c835b4c124476e5e84e0f621006d222","target":"record","created_at":"2026-05-17T23:52:55Z","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":"9cc1353a9bff203f3635cd793f143121a3cf587f06a9a62a6298205ab8b7428b","cross_cats_sorted":["cs.RO","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-24T16:58:45Z","title_canon_sha256":"ec2a35efa7e7944c679874d9fe00d93e41600efa043b078976ee2c8a5c1bf777"},"schema_version":"1.0","source":{"id":"1711.09048","kind":"arxiv","version":3}},"canonical_sha256":"af394f7fca6fe76b35a7d76c03d4393e1ad59afefc7d262629fca81e63196513","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af394f7fca6fe76b35a7d76c03d4393e1ad59afefc7d262629fca81e63196513","first_computed_at":"2026-05-17T23:52:55.919588Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:55.919588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wmVCJaHVvWRlWH3Irm1NdNti4eNLLGEpXOE73Cjf1AZl02czmPplBL/SHmPAc11p4MsE0q6vB8g0F3UE1g5yAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:55.920292Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.09048","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0fb0ea29691179ececa8e163bb0fd0e2c835b4c124476e5e84e0f621006d222","sha256:bb11d8a06f9496b06456327b4e69361fb9017eb53cc6459552ac7512a9bb4f72"],"state_sha256":"4dbdce9583f8a4d7480199a8ed043a67a0305b40e3a21380e9c536070b716bc5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b0SFxOWyNc3hWsv8Tf22sKbhhTZV+zJs/ZE1Ci3QphBjG4xIkc+kTEYuOFxJicd80c3rg3Psd2t4OP6d0cR7Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T06:48:33.150704Z","bundle_sha256":"294ae3dea0c8051e836d19028828eb7833be65f12e1fcc1287e582778c997aed"}}