{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:YNSGWJSYGRIKJGG27JJAWFYYZW","short_pith_number":"pith:YNSGWJSY","canonical_record":{"source":{"id":"2001.01577","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-06T13:49:31Z","cross_cats_sorted":[],"title_canon_sha256":"b82e5fa1728f586a1d491a2471434424c10b7cba86f8bccbdd7fd93d2e48a585","abstract_canon_sha256":"945fcdc2b8ad2bdc8740b8b4fd1bfb83992d8928f3f17a9f20490c4fc9270b10"},"schema_version":"1.0"},"canonical_sha256":"c3646b26583450a498dafa520b1718cda7aba18034fc93c3e2723e1270a51d93","source":{"kind":"arxiv","id":"2001.01577","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.01577","created_at":"2026-07-05T00:29:48Z"},{"alias_kind":"arxiv_version","alias_value":"2001.01577v1","created_at":"2026-07-05T00:29:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.01577","created_at":"2026-07-05T00:29:48Z"},{"alias_kind":"pith_short_12","alias_value":"YNSGWJSYGRIK","created_at":"2026-07-05T00:29:48Z"},{"alias_kind":"pith_short_16","alias_value":"YNSGWJSYGRIKJGG2","created_at":"2026-07-05T00:29:48Z"},{"alias_kind":"pith_short_8","alias_value":"YNSGWJSY","created_at":"2026-07-05T00:29:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:YNSGWJSYGRIKJGG27JJAWFYYZW","target":"record","payload":{"canonical_record":{"source":{"id":"2001.01577","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-06T13:49:31Z","cross_cats_sorted":[],"title_canon_sha256":"b82e5fa1728f586a1d491a2471434424c10b7cba86f8bccbdd7fd93d2e48a585","abstract_canon_sha256":"945fcdc2b8ad2bdc8740b8b4fd1bfb83992d8928f3f17a9f20490c4fc9270b10"},"schema_version":"1.0"},"canonical_sha256":"c3646b26583450a498dafa520b1718cda7aba18034fc93c3e2723e1270a51d93","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:29:48.124746Z","signature_b64":"O1QjdbPYuT8ToCcw3cXQ1GavlaXfkjTuCmShoRsTBYQwPBsrNxqlsuEPrNAOv2re6jbg6Zh2LVptI2H9I7FkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3646b26583450a498dafa520b1718cda7aba18034fc93c3e2723e1270a51d93","last_reissued_at":"2026-07-05T00:29:48.124359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:29:48.124359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2001.01577","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":"2026-07-05T00:29:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cqBsrrFy9J1mlJ/+ilZ3zsvcrmzW2GDXBVtvkO8IWh6hzb5P10vF7xq3zVQq586DK39OBU31kARBDeL5lF2HDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:20:35.929508Z"},"content_sha256":"368f8b6bcf8621d32d6b7d79a92c07211f189e3337d8b490c3b412d29dd7b89d","schema_version":"1.0","event_id":"sha256:368f8b6bcf8621d32d6b7d79a92c07211f189e3337d8b490c3b412d29dd7b89d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:YNSGWJSYGRIKJGG27JJAWFYYZW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Reusable Options for Multi-Task Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chris Nota, Francisco M. Garcia, Philip S. Thomas","submitted_at":"2020-01-06T13:49:31Z","abstract_excerpt":"Reinforcement learning (RL) has become an increasingly active area of research in recent years. Although there are many algorithms that allow an agent to solve tasks efficiently, they often ignore the possibility that prior experience related to the task at hand might be available. For many practical applications, it might be unfeasible for an agent to learn how to solve a task from scratch, given that it is generally a computationally expensive process; however, prior experience could be leveraged to make these problems tractable in practice. In this paper, we propose a framework for exploiti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.01577","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/2001.01577/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":"2026-07-05T00:29:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zgf1n416A9HGg6VA/5jiJGX9okgVqGe7XhvMkMwEPQq7e49bmRU1/Dk0v0hd771sjrkerA4PU9mpIbBN9LuLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:20:35.929885Z"},"content_sha256":"137e7e51e45688da18a5580139019622dec7d8bafad50ae38433d2aef6c2f231","schema_version":"1.0","event_id":"sha256:137e7e51e45688da18a5580139019622dec7d8bafad50ae38433d2aef6c2f231"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YNSGWJSYGRIKJGG27JJAWFYYZW/bundle.json","state_url":"https://pith.science/pith/YNSGWJSYGRIKJGG27JJAWFYYZW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YNSGWJSYGRIKJGG27JJAWFYYZW/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":"2026-08-13T15:20:35Z","links":{"resolver":"https://pith.science/pith/YNSGWJSYGRIKJGG27JJAWFYYZW","bundle":"https://pith.science/pith/YNSGWJSYGRIKJGG27JJAWFYYZW/bundle.json","state":"https://pith.science/pith/YNSGWJSYGRIKJGG27JJAWFYYZW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YNSGWJSYGRIKJGG27JJAWFYYZW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:YNSGWJSYGRIKJGG27JJAWFYYZW","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":"945fcdc2b8ad2bdc8740b8b4fd1bfb83992d8928f3f17a9f20490c4fc9270b10","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-06T13:49:31Z","title_canon_sha256":"b82e5fa1728f586a1d491a2471434424c10b7cba86f8bccbdd7fd93d2e48a585"},"schema_version":"1.0","source":{"id":"2001.01577","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.01577","created_at":"2026-07-05T00:29:48Z"},{"alias_kind":"arxiv_version","alias_value":"2001.01577v1","created_at":"2026-07-05T00:29:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.01577","created_at":"2026-07-05T00:29:48Z"},{"alias_kind":"pith_short_12","alias_value":"YNSGWJSYGRIK","created_at":"2026-07-05T00:29:48Z"},{"alias_kind":"pith_short_16","alias_value":"YNSGWJSYGRIKJGG2","created_at":"2026-07-05T00:29:48Z"},{"alias_kind":"pith_short_8","alias_value":"YNSGWJSY","created_at":"2026-07-05T00:29:48Z"}],"graph_snapshots":[{"event_id":"sha256:137e7e51e45688da18a5580139019622dec7d8bafad50ae38433d2aef6c2f231","target":"graph","created_at":"2026-07-05T00:29:48Z","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/2001.01577/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has become an increasingly active area of research in recent years. Although there are many algorithms that allow an agent to solve tasks efficiently, they often ignore the possibility that prior experience related to the task at hand might be available. For many practical applications, it might be unfeasible for an agent to learn how to solve a task from scratch, given that it is generally a computationally expensive process; however, prior experience could be leveraged to make these problems tractable in practice. In this paper, we propose a framework for exploiti","authors_text":"Chris Nota, Francisco M. Garcia, Philip S. Thomas","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-06T13:49:31Z","title":"Learning Reusable Options for Multi-Task Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.01577","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":"sha256:368f8b6bcf8621d32d6b7d79a92c07211f189e3337d8b490c3b412d29dd7b89d","target":"record","created_at":"2026-07-05T00:29:48Z","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":"945fcdc2b8ad2bdc8740b8b4fd1bfb83992d8928f3f17a9f20490c4fc9270b10","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-06T13:49:31Z","title_canon_sha256":"b82e5fa1728f586a1d491a2471434424c10b7cba86f8bccbdd7fd93d2e48a585"},"schema_version":"1.0","source":{"id":"2001.01577","kind":"arxiv","version":1}},"canonical_sha256":"c3646b26583450a498dafa520b1718cda7aba18034fc93c3e2723e1270a51d93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3646b26583450a498dafa520b1718cda7aba18034fc93c3e2723e1270a51d93","first_computed_at":"2026-07-05T00:29:48.124359Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:29:48.124359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O1QjdbPYuT8ToCcw3cXQ1GavlaXfkjTuCmShoRsTBYQwPBsrNxqlsuEPrNAOv2re6jbg6Zh2LVptI2H9I7FkCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:29:48.124746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.01577","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:368f8b6bcf8621d32d6b7d79a92c07211f189e3337d8b490c3b412d29dd7b89d","sha256:137e7e51e45688da18a5580139019622dec7d8bafad50ae38433d2aef6c2f231"],"state_sha256":"0e243299220f3dd0eb018caa7679f012d5aa46be8662a5f8a30e960cf5bcb43a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OM04XRPUQJlRHrupvOJS6mIQI9Th5ZbRM2aEUzd5jMefYqf5PkWIUEl11IEkGfkB3O97kB0Q2xYSIRhDe3X0DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T15:20:35.949411Z","bundle_sha256":"8cbad9dc03d7199bbb82b3f3df211c06875fe5fe8047a4bf45f10fe368826325"}}