{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:MTA27W7UUYKUU2DOWIHZYV5C6V","short_pith_number":"pith:MTA27W7U","canonical_record":{"source":{"id":"2003.04960","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-03-10T20:41:24Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"97394c3fe1cf0972165681175d3b6a8548b922c2ecb6a1d384258af794227896","abstract_canon_sha256":"0efc1b59daa89766d656038feadb590129c7e7348f6b3d06a87d0771015ca139"},"schema_version":"1.0"},"canonical_sha256":"64c1afdbf4a6154a686eb20f9c57a2f54e9db613bde70f2beedc143e47e325e4","source":{"kind":"arxiv","id":"2003.04960","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.04960","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"arxiv_version","alias_value":"2003.04960v2","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.04960","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"pith_short_12","alias_value":"MTA27W7UUYKU","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"pith_short_16","alias_value":"MTA27W7UUYKUU2DO","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"pith_short_8","alias_value":"MTA27W7U","created_at":"2026-07-05T01:36:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:MTA27W7UUYKUU2DOWIHZYV5C6V","target":"record","payload":{"canonical_record":{"source":{"id":"2003.04960","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-03-10T20:41:24Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"97394c3fe1cf0972165681175d3b6a8548b922c2ecb6a1d384258af794227896","abstract_canon_sha256":"0efc1b59daa89766d656038feadb590129c7e7348f6b3d06a87d0771015ca139"},"schema_version":"1.0"},"canonical_sha256":"64c1afdbf4a6154a686eb20f9c57a2f54e9db613bde70f2beedc143e47e325e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:36:16.613256Z","signature_b64":"vtW0Mgl691vKSyFeipIVHC/8Mur/3C0ioTD6D6pN034EMWAp4pl8mvFsm9YEumoH+3C4Ri+xWhLZ5iBUMfH/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64c1afdbf4a6154a686eb20f9c57a2f54e9db613bde70f2beedc143e47e325e4","last_reissued_at":"2026-07-05T01:36:16.612750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:36:16.612750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.04960","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":"2026-07-05T01:36:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N196mwNqj8slwsMLpR510JEv7hJStdHPyFvWeba/C+L8bDKKERsdgincl5NCuPscQwann5Qd3Rq9sTy6LX28Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:25:32.428847Z"},"content_sha256":"c6f12f04a304f310cc0e7b5b51cf263027f27eb7a3bd45032c9e326e4400a21e","schema_version":"1.0","event_id":"sha256:c6f12f04a304f310cc0e7b5b51cf263027f27eb7a3bd45032c9e326e4400a21e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:MTA27W7UUYKUU2DOWIHZYV5C6V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bei Peng, Jivko Sinapov, Matteo Leonetti, Matthew E. Taylor, Peter Stone, Sanmit Narvekar","submitted_at":"2020-03-10T20:41:24Z","abstract_excerpt":"Reinforcement learning (RL) is a popular paradigm for addressing sequential decision tasks in which the agent has only limited environmental feedback. Despite many advances over the past three decades, learning in many domains still requires a large amount of interaction with the environment, which can be prohibitively expensive in realistic scenarios. To address this problem, transfer learning has been applied to reinforcement learning such that experience gained in one task can be leveraged when starting to learn the next, harder task. More recently, several lines of research have explored h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.04960","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/2003.04960/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":"2026-07-05T01:36:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LfPcEFwIJ40RMa1PMVAkylV30QVS8nOd47knD98dgbbYO0nayktkSFnhU+ilrIgGCcOHmjUGxvrkI9MkfPshDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:25:32.429834Z"},"content_sha256":"b43e393c09ca476115e92977adb7def3c0e0bf6836cc33d216308c99aeb6a568","schema_version":"1.0","event_id":"sha256:b43e393c09ca476115e92977adb7def3c0e0bf6836cc33d216308c99aeb6a568"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MTA27W7UUYKUU2DOWIHZYV5C6V/bundle.json","state_url":"https://pith.science/pith/MTA27W7UUYKUU2DOWIHZYV5C6V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MTA27W7UUYKUU2DOWIHZYV5C6V/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":"2026-08-10T23:25:32Z","links":{"resolver":"https://pith.science/pith/MTA27W7UUYKUU2DOWIHZYV5C6V","bundle":"https://pith.science/pith/MTA27W7UUYKUU2DOWIHZYV5C6V/bundle.json","state":"https://pith.science/pith/MTA27W7UUYKUU2DOWIHZYV5C6V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MTA27W7UUYKUU2DOWIHZYV5C6V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:MTA27W7UUYKUU2DOWIHZYV5C6V","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":"0efc1b59daa89766d656038feadb590129c7e7348f6b3d06a87d0771015ca139","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-03-10T20:41:24Z","title_canon_sha256":"97394c3fe1cf0972165681175d3b6a8548b922c2ecb6a1d384258af794227896"},"schema_version":"1.0","source":{"id":"2003.04960","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.04960","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"arxiv_version","alias_value":"2003.04960v2","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.04960","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"pith_short_12","alias_value":"MTA27W7UUYKU","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"pith_short_16","alias_value":"MTA27W7UUYKUU2DO","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"pith_short_8","alias_value":"MTA27W7U","created_at":"2026-07-05T01:36:16Z"}],"graph_snapshots":[{"event_id":"sha256:b43e393c09ca476115e92977adb7def3c0e0bf6836cc33d216308c99aeb6a568","target":"graph","created_at":"2026-07-05T01:36:16Z","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/2003.04960/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is a popular paradigm for addressing sequential decision tasks in which the agent has only limited environmental feedback. Despite many advances over the past three decades, learning in many domains still requires a large amount of interaction with the environment, which can be prohibitively expensive in realistic scenarios. To address this problem, transfer learning has been applied to reinforcement learning such that experience gained in one task can be leveraged when starting to learn the next, harder task. More recently, several lines of research have explored h","authors_text":"Bei Peng, Jivko Sinapov, Matteo Leonetti, Matthew E. Taylor, Peter Stone, Sanmit Narvekar","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-03-10T20:41:24Z","title":"Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.04960","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:c6f12f04a304f310cc0e7b5b51cf263027f27eb7a3bd45032c9e326e4400a21e","target":"record","created_at":"2026-07-05T01:36:16Z","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":"0efc1b59daa89766d656038feadb590129c7e7348f6b3d06a87d0771015ca139","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-03-10T20:41:24Z","title_canon_sha256":"97394c3fe1cf0972165681175d3b6a8548b922c2ecb6a1d384258af794227896"},"schema_version":"1.0","source":{"id":"2003.04960","kind":"arxiv","version":2}},"canonical_sha256":"64c1afdbf4a6154a686eb20f9c57a2f54e9db613bde70f2beedc143e47e325e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64c1afdbf4a6154a686eb20f9c57a2f54e9db613bde70f2beedc143e47e325e4","first_computed_at":"2026-07-05T01:36:16.612750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:36:16.612750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vtW0Mgl691vKSyFeipIVHC/8Mur/3C0ioTD6D6pN034EMWAp4pl8mvFsm9YEumoH+3C4Ri+xWhLZ5iBUMfH/Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:36:16.613256Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.04960","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6f12f04a304f310cc0e7b5b51cf263027f27eb7a3bd45032c9e326e4400a21e","sha256:b43e393c09ca476115e92977adb7def3c0e0bf6836cc33d216308c99aeb6a568"],"state_sha256":"b2a8554cbc257101fa5b77dfb9981b2535d62318378d922cc1136ed0662d91d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vYPYCbm3TOIecrVTfgeCzMJ3+/iUzth/oZn5BufSk26dnlTYcjhgKezAYOL5IaZ4AKJAnCkBtiNrTPWqAqB/Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T23:25:32.436041Z","bundle_sha256":"4b290887d1f7a2f4ebd9a97f439877ab412ae5a4b2e23a55467f35ddf129dc2f"}}