{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PZRYM7POAF6BX6SRPK6TTBLBYY","short_pith_number":"pith:PZRYM7PO","canonical_record":{"source":{"id":"2304.05271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-04-11T15:14:31Z","cross_cats_sorted":[],"title_canon_sha256":"c776a4c0ce7d6403700731a799854e0025c90f893bdfea1f179277fa7465f794","abstract_canon_sha256":"4eb842d118b9bd0a546bba83d8551f15e4dc8b8e4c4820a21918253e2ff9174f"},"schema_version":"1.0"},"canonical_sha256":"7e63867dee017c1bfa517abd398561c6048afaa327f52e19a6971aa39561378b","source":{"kind":"arxiv","id":"2304.05271","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.05271","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"arxiv_version","alias_value":"2304.05271v1","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05271","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"pith_short_12","alias_value":"PZRYM7POAF6B","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"pith_short_16","alias_value":"PZRYM7POAF6BX6SR","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"pith_short_8","alias_value":"PZRYM7PO","created_at":"2026-07-05T05:59:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PZRYM7POAF6BX6SRPK6TTBLBYY","target":"record","payload":{"canonical_record":{"source":{"id":"2304.05271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-04-11T15:14:31Z","cross_cats_sorted":[],"title_canon_sha256":"c776a4c0ce7d6403700731a799854e0025c90f893bdfea1f179277fa7465f794","abstract_canon_sha256":"4eb842d118b9bd0a546bba83d8551f15e4dc8b8e4c4820a21918253e2ff9174f"},"schema_version":"1.0"},"canonical_sha256":"7e63867dee017c1bfa517abd398561c6048afaa327f52e19a6971aa39561378b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:57.833530Z","signature_b64":"fhFxuIczVcKj711E4/dXBzoUhm31xIlV/ny1cQGzI3gF2HwHJmVOpymKWSYok2dOWu6GWwqXBTqgGmdNDs6SDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e63867dee017c1bfa517abd398561c6048afaa327f52e19a6971aa39561378b","last_reissued_at":"2026-07-05T05:59:57.833100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:57.833100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.05271","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":"2026-07-05T05:59:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ym567bXA+S+gHJQ26EQeYNQ8p6gIPTmD+lOGZiRNHBHep5DyHg8gJVYShf7c/XwabPfcseqweeOJWYZn14fJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:20:04.352477Z"},"content_sha256":"0fb02348d00ac1edaabea1436dca2a38023593f8a89f08b47f4ba2efe8907f97","schema_version":"1.0","event_id":"sha256:0fb02348d00ac1edaabea1436dca2a38023593f8a89f08b47f4ba2efe8907f97"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PZRYM7POAF6BX6SRPK6TTBLBYY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automaton-Guided Curriculum Generation for Reinforcement Learning Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abhishek Kulkarni, Alvaro Velasquez, Jivko Sinapov, Robert Wright, Yash Shukla","submitted_at":"2023-04-11T15:14:31Z","abstract_excerpt":"Despite advances in Reinforcement Learning, many sequential decision making tasks remain prohibitively expensive and impractical to learn. Recently, approaches that automatically generate reward functions from logical task specifications have been proposed to mitigate this issue; however, they scale poorly on long-horizon tasks (i.e., tasks where the agent needs to perform a series of correct actions to reach the goal state, considering future transitions while choosing an action). Employing a curriculum (a sequence of increasingly complex tasks) further improves the learning speed of the agen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05271","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/2304.05271/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":"2026-07-05T05:59:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BoZHPwSGUMg89Q/rr2WUGwy3kWieaV2AUyPUCTRd513NclU7CM4Vol+vluLCYfTpnz2qcBfd96kHjdWF0hxMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:20:04.352844Z"},"content_sha256":"092c925cb461c1abc2b1457fc8c1a6f56ca9d2a77bd69a6879fcaeb08f91895e","schema_version":"1.0","event_id":"sha256:092c925cb461c1abc2b1457fc8c1a6f56ca9d2a77bd69a6879fcaeb08f91895e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PZRYM7POAF6BX6SRPK6TTBLBYY/bundle.json","state_url":"https://pith.science/pith/PZRYM7POAF6BX6SRPK6TTBLBYY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PZRYM7POAF6BX6SRPK6TTBLBYY/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":"2026-07-07T08:20:04Z","links":{"resolver":"https://pith.science/pith/PZRYM7POAF6BX6SRPK6TTBLBYY","bundle":"https://pith.science/pith/PZRYM7POAF6BX6SRPK6TTBLBYY/bundle.json","state":"https://pith.science/pith/PZRYM7POAF6BX6SRPK6TTBLBYY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PZRYM7POAF6BX6SRPK6TTBLBYY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PZRYM7POAF6BX6SRPK6TTBLBYY","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":"4eb842d118b9bd0a546bba83d8551f15e4dc8b8e4c4820a21918253e2ff9174f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-04-11T15:14:31Z","title_canon_sha256":"c776a4c0ce7d6403700731a799854e0025c90f893bdfea1f179277fa7465f794"},"schema_version":"1.0","source":{"id":"2304.05271","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.05271","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"arxiv_version","alias_value":"2304.05271v1","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05271","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"pith_short_12","alias_value":"PZRYM7POAF6B","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"pith_short_16","alias_value":"PZRYM7POAF6BX6SR","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"pith_short_8","alias_value":"PZRYM7PO","created_at":"2026-07-05T05:59:57Z"}],"graph_snapshots":[{"event_id":"sha256:092c925cb461c1abc2b1457fc8c1a6f56ca9d2a77bd69a6879fcaeb08f91895e","target":"graph","created_at":"2026-07-05T05:59:57Z","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/2304.05271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite advances in Reinforcement Learning, many sequential decision making tasks remain prohibitively expensive and impractical to learn. Recently, approaches that automatically generate reward functions from logical task specifications have been proposed to mitigate this issue; however, they scale poorly on long-horizon tasks (i.e., tasks where the agent needs to perform a series of correct actions to reach the goal state, considering future transitions while choosing an action). Employing a curriculum (a sequence of increasingly complex tasks) further improves the learning speed of the agen","authors_text":"Abhishek Kulkarni, Alvaro Velasquez, Jivko Sinapov, Robert Wright, Yash Shukla","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-04-11T15:14:31Z","title":"Automaton-Guided Curriculum Generation for Reinforcement Learning Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05271","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":"sha256:0fb02348d00ac1edaabea1436dca2a38023593f8a89f08b47f4ba2efe8907f97","target":"record","created_at":"2026-07-05T05:59:57Z","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":"4eb842d118b9bd0a546bba83d8551f15e4dc8b8e4c4820a21918253e2ff9174f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-04-11T15:14:31Z","title_canon_sha256":"c776a4c0ce7d6403700731a799854e0025c90f893bdfea1f179277fa7465f794"},"schema_version":"1.0","source":{"id":"2304.05271","kind":"arxiv","version":1}},"canonical_sha256":"7e63867dee017c1bfa517abd398561c6048afaa327f52e19a6971aa39561378b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e63867dee017c1bfa517abd398561c6048afaa327f52e19a6971aa39561378b","first_computed_at":"2026-07-05T05:59:57.833100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:59:57.833100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fhFxuIczVcKj711E4/dXBzoUhm31xIlV/ny1cQGzI3gF2HwHJmVOpymKWSYok2dOWu6GWwqXBTqgGmdNDs6SDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:59:57.833530Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.05271","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fb02348d00ac1edaabea1436dca2a38023593f8a89f08b47f4ba2efe8907f97","sha256:092c925cb461c1abc2b1457fc8c1a6f56ca9d2a77bd69a6879fcaeb08f91895e"],"state_sha256":"4fb3796c6af8fc82eab58a8471af1d828a21f35cfca91ce19e8a7d577d280cba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YurRx2TVs6dMlNJPsyxsCRDTG33UdKT9/o7KREWvWCSsAFCtfWOGq0uGCUGF6YJ+xtFO4OhdaxaPO3bGENJLAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:20:04.354759Z","bundle_sha256":"6bd982239abeeb02b2993245833ad8580b78e5744784930cd73dfe214aba138a"}}