{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:FTI5Y46GHYK7OTORVLVLC442J5","short_pith_number":"pith:FTI5Y46G","canonical_record":{"source":{"id":"1807.01425","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-07-04T01:49:29Z","cross_cats_sorted":[],"title_canon_sha256":"1f89b51b5d0115cebc47c7058ef840a25c191b319d23ea53ec4b7dbb42e369eb","abstract_canon_sha256":"c505d2f35ddba85a06f107a812385f98355658c92b656185d23326e594a96cb1"},"schema_version":"1.0"},"canonical_sha256":"2cd1dc73c63e15f74dd1aaeab1739a4f6e6d7f25834bde5521dec0d327caa385","source":{"kind":"arxiv","id":"1807.01425","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01425","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01425v1","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01425","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"pith_short_12","alias_value":"FTI5Y46GHYK7","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"FTI5Y46GHYK7OTOR","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"FTI5Y46G","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:FTI5Y46GHYK7OTORVLVLC442J5","target":"record","payload":{"canonical_record":{"source":{"id":"1807.01425","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-07-04T01:49:29Z","cross_cats_sorted":[],"title_canon_sha256":"1f89b51b5d0115cebc47c7058ef840a25c191b319d23ea53ec4b7dbb42e369eb","abstract_canon_sha256":"c505d2f35ddba85a06f107a812385f98355658c92b656185d23326e594a96cb1"},"schema_version":"1.0"},"canonical_sha256":"2cd1dc73c63e15f74dd1aaeab1739a4f6e6d7f25834bde5521dec0d327caa385","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:29.702367Z","signature_b64":"jQ2Uytqv02KGZvXWHGtwF2/nkXxLhTd5B//6b3rD3gfjBBlNaBRj1iKLkRv4mrIW8fsZOigJ3Odn0b/Ih2qOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cd1dc73c63e15f74dd1aaeab1739a4f6e6d7f25834bde5521dec0d327caa385","last_reissued_at":"2026-05-18T00:11:29.701981Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:29.701981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.01425","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":"2026-05-18T00:11:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rf9VdOrNOTK256sDo3xdFH2wlu+1UWFR/+k8dLWnfQKFG0YKNtHmQJmZcdMGLALA2BjyD1Gm7p5rjR04gg5hDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:54:49.930009Z"},"content_sha256":"a71adebb365e2b06c02d6ce49ac31d844388d689031af1f69872de43302a36bd","schema_version":"1.0","event_id":"sha256:a71adebb365e2b06c02d6ce49ac31d844388d689031af1f69872de43302a36bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:FTI5Y46GHYK7OTORVLVLC442J5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Region Growing Curriculum Generation for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Artem Molchanov, Gaurav Sukhatme, Karol Hausman, Stan Birchfield","submitted_at":"2018-07-04T01:49:29Z","abstract_excerpt":"Learning a policy capable of moving an agent between any two states in the environment is important for many robotics problems involving navigation and manipulation. Due to the sparsity of rewards in such tasks, applying reinforcement learning in these scenarios can be challenging. Common approaches for tackling this problem include reward engineering with auxiliary rewards, requiring domain-specific knowledge or changing the objective.\n  In this work, we introduce a method based on region-growing that allows learning in an environment with any pair of initial and goal states. Our algorithm fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01425","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":"2026-05-18T00:11:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L87SG3E4tVf3A5P9hqjfg8OqLZXt78JzRdkQrkM23qoOS6wqNg2oE3/JuF0JuuTlN5s8vA9xNYSRoyKpz4wZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:54:49.930373Z"},"content_sha256":"b57cb64ea364f16d50a871ac270d136998fc70743ce2f1c8e09bf8992639ad2d","schema_version":"1.0","event_id":"sha256:b57cb64ea364f16d50a871ac270d136998fc70743ce2f1c8e09bf8992639ad2d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FTI5Y46GHYK7OTORVLVLC442J5/bundle.json","state_url":"https://pith.science/pith/FTI5Y46GHYK7OTORVLVLC442J5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FTI5Y46GHYK7OTORVLVLC442J5/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":"2026-05-28T13:54:49Z","links":{"resolver":"https://pith.science/pith/FTI5Y46GHYK7OTORVLVLC442J5","bundle":"https://pith.science/pith/FTI5Y46GHYK7OTORVLVLC442J5/bundle.json","state":"https://pith.science/pith/FTI5Y46GHYK7OTORVLVLC442J5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FTI5Y46GHYK7OTORVLVLC442J5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:FTI5Y46GHYK7OTORVLVLC442J5","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":"c505d2f35ddba85a06f107a812385f98355658c92b656185d23326e594a96cb1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-07-04T01:49:29Z","title_canon_sha256":"1f89b51b5d0115cebc47c7058ef840a25c191b319d23ea53ec4b7dbb42e369eb"},"schema_version":"1.0","source":{"id":"1807.01425","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01425","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01425v1","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01425","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"pith_short_12","alias_value":"FTI5Y46GHYK7","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"FTI5Y46GHYK7OTOR","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"FTI5Y46G","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:b57cb64ea364f16d50a871ac270d136998fc70743ce2f1c8e09bf8992639ad2d","target":"graph","created_at":"2026-05-18T00:11:29Z","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":"Learning a policy capable of moving an agent between any two states in the environment is important for many robotics problems involving navigation and manipulation. Due to the sparsity of rewards in such tasks, applying reinforcement learning in these scenarios can be challenging. Common approaches for tackling this problem include reward engineering with auxiliary rewards, requiring domain-specific knowledge or changing the objective.\n  In this work, we introduce a method based on region-growing that allows learning in an environment with any pair of initial and goal states. Our algorithm fi","authors_text":"Artem Molchanov, Gaurav Sukhatme, Karol Hausman, Stan Birchfield","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-07-04T01:49:29Z","title":"Region Growing Curriculum Generation for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01425","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:a71adebb365e2b06c02d6ce49ac31d844388d689031af1f69872de43302a36bd","target":"record","created_at":"2026-05-18T00:11:29Z","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":"c505d2f35ddba85a06f107a812385f98355658c92b656185d23326e594a96cb1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-07-04T01:49:29Z","title_canon_sha256":"1f89b51b5d0115cebc47c7058ef840a25c191b319d23ea53ec4b7dbb42e369eb"},"schema_version":"1.0","source":{"id":"1807.01425","kind":"arxiv","version":1}},"canonical_sha256":"2cd1dc73c63e15f74dd1aaeab1739a4f6e6d7f25834bde5521dec0d327caa385","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cd1dc73c63e15f74dd1aaeab1739a4f6e6d7f25834bde5521dec0d327caa385","first_computed_at":"2026-05-18T00:11:29.701981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:29.701981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jQ2Uytqv02KGZvXWHGtwF2/nkXxLhTd5B//6b3rD3gfjBBlNaBRj1iKLkRv4mrIW8fsZOigJ3Odn0b/Ih2qOCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:29.702367Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.01425","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a71adebb365e2b06c02d6ce49ac31d844388d689031af1f69872de43302a36bd","sha256:b57cb64ea364f16d50a871ac270d136998fc70743ce2f1c8e09bf8992639ad2d"],"state_sha256":"d7a36e4a89185d8cc2b8735bada98971ecbe344bb24e854f44ce17a103286c7d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"17/s1eOrMxazomseR4mbpS5Mj7kQsOIu0b55KkcP/rY6zMnwAZgkny/Kk+xPAe+L5kjQew/dk26MD8Gi1NJBDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T13:54:49.932293Z","bundle_sha256":"39f3d51b5ac4b73a902a0be7908ce351326155693d3d4fbe709d165ff66a91b9"}}