{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GC3JHTVIQBHPK22FGT6YCHUSIX","short_pith_number":"pith:GC3JHTVI","canonical_record":{"source":{"id":"2306.17033","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-29T15:34:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e35fdc4e9bf79b194b105cd434af57ab10cc20bf749d5d7404523162d21fb1a9","abstract_canon_sha256":"f5524760451bb0454d58a9ead9626735474699a4657e1c4aa984c83d4af6b673"},"schema_version":"1.0"},"canonical_sha256":"30b693cea8804ef56b4534fd811e9245ca739994e3939412839585faae5d67ad","source":{"kind":"arxiv","id":"2306.17033","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.17033","created_at":"2026-07-05T06:26:12Z"},{"alias_kind":"arxiv_version","alias_value":"2306.17033v1","created_at":"2026-07-05T06:26:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17033","created_at":"2026-07-05T06:26:12Z"},{"alias_kind":"pith_short_12","alias_value":"GC3JHTVIQBHP","created_at":"2026-07-05T06:26:12Z"},{"alias_kind":"pith_short_16","alias_value":"GC3JHTVIQBHPK22F","created_at":"2026-07-05T06:26:12Z"},{"alias_kind":"pith_short_8","alias_value":"GC3JHTVI","created_at":"2026-07-05T06:26:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GC3JHTVIQBHPK22FGT6YCHUSIX","target":"record","payload":{"canonical_record":{"source":{"id":"2306.17033","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-29T15:34:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e35fdc4e9bf79b194b105cd434af57ab10cc20bf749d5d7404523162d21fb1a9","abstract_canon_sha256":"f5524760451bb0454d58a9ead9626735474699a4657e1c4aa984c83d4af6b673"},"schema_version":"1.0"},"canonical_sha256":"30b693cea8804ef56b4534fd811e9245ca739994e3939412839585faae5d67ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:12.448689Z","signature_b64":"tXZ4BsHAhH+vI/nujnVAZRpELyq2HVpRlgDv7fBDaCDqnbKFlM22xrbuVDh9euMXU2vCLkAwsn65dyuyLo4eBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30b693cea8804ef56b4534fd811e9245ca739994e3939412839585faae5d67ad","last_reissued_at":"2026-07-05T06:26:12.448186Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:12.448186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.17033","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":"2026-07-05T06:26:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N7fTOKCskufUrCTQKEBALS96Bntzrlc+KUXUa461w1c82Wd9ohgWyJ2sdmF7H6Dw+FPDe46aJOEYrsuqWnCXBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T06:05:36.728497Z"},"content_sha256":"ca319bbb1fad802b00421bcc6c1ea3e76a919fd380d16e4ae30cbbe44c3c85a0","schema_version":"1.0","event_id":"sha256:ca319bbb1fad802b00421bcc6c1ea3e76a919fd380d16e4ae30cbbe44c3c85a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GC3JHTVIQBHPK22FGT6YCHUSIX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Safety-Aware Task Composition for Discrete and Continuous Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kevin Leahy, Makai Mann, Zachary Serlin","submitted_at":"2023-06-29T15:34:26Z","abstract_excerpt":"Compositionality is a critical aspect of scalable system design. Reinforcement learning (RL) has recently shown substantial success in task learning, but has only recently begun to truly leverage composition. In this paper, we focus on Boolean composition of learned tasks as opposed to functional or sequential composition. Existing Boolean composition for RL focuses on reaching a satisfying absorbing state in environments with discrete action spaces, but does not support composable safety (i.e., avoidance) constraints. We advance the state of the art in Boolean composition of learned tasks wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17033","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/2306.17033/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":"2026-07-05T06:26:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aRYGWs0cSxMp5Z0cMt4I2EEcLGy1CFHzZqRGbiMoVktpb30AJ47XhwDnrnRzAc1Lh6zRC41EpvIixjmm3/RgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T06:05:36.729039Z"},"content_sha256":"4ab8005a60c3ebc0956cc5430174efba4e123463459ee4ead840f4b06d1c654f","schema_version":"1.0","event_id":"sha256:4ab8005a60c3ebc0956cc5430174efba4e123463459ee4ead840f4b06d1c654f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GC3JHTVIQBHPK22FGT6YCHUSIX/bundle.json","state_url":"https://pith.science/pith/GC3JHTVIQBHPK22FGT6YCHUSIX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GC3JHTVIQBHPK22FGT6YCHUSIX/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":"2026-08-17T06:05:36Z","links":{"resolver":"https://pith.science/pith/GC3JHTVIQBHPK22FGT6YCHUSIX","bundle":"https://pith.science/pith/GC3JHTVIQBHPK22FGT6YCHUSIX/bundle.json","state":"https://pith.science/pith/GC3JHTVIQBHPK22FGT6YCHUSIX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GC3JHTVIQBHPK22FGT6YCHUSIX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GC3JHTVIQBHPK22FGT6YCHUSIX","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":"f5524760451bb0454d58a9ead9626735474699a4657e1c4aa984c83d4af6b673","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-29T15:34:26Z","title_canon_sha256":"e35fdc4e9bf79b194b105cd434af57ab10cc20bf749d5d7404523162d21fb1a9"},"schema_version":"1.0","source":{"id":"2306.17033","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.17033","created_at":"2026-07-05T06:26:12Z"},{"alias_kind":"arxiv_version","alias_value":"2306.17033v1","created_at":"2026-07-05T06:26:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17033","created_at":"2026-07-05T06:26:12Z"},{"alias_kind":"pith_short_12","alias_value":"GC3JHTVIQBHP","created_at":"2026-07-05T06:26:12Z"},{"alias_kind":"pith_short_16","alias_value":"GC3JHTVIQBHPK22F","created_at":"2026-07-05T06:26:12Z"},{"alias_kind":"pith_short_8","alias_value":"GC3JHTVI","created_at":"2026-07-05T06:26:12Z"}],"graph_snapshots":[{"event_id":"sha256:4ab8005a60c3ebc0956cc5430174efba4e123463459ee4ead840f4b06d1c654f","target":"graph","created_at":"2026-07-05T06:26:12Z","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/2306.17033/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Compositionality is a critical aspect of scalable system design. Reinforcement learning (RL) has recently shown substantial success in task learning, but has only recently begun to truly leverage composition. In this paper, we focus on Boolean composition of learned tasks as opposed to functional or sequential composition. Existing Boolean composition for RL focuses on reaching a satisfying absorbing state in environments with discrete action spaces, but does not support composable safety (i.e., avoidance) constraints. We advance the state of the art in Boolean composition of learned tasks wit","authors_text":"Kevin Leahy, Makai Mann, Zachary Serlin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-29T15:34:26Z","title":"Safety-Aware Task Composition for Discrete and Continuous Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17033","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:ca319bbb1fad802b00421bcc6c1ea3e76a919fd380d16e4ae30cbbe44c3c85a0","target":"record","created_at":"2026-07-05T06:26:12Z","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":"f5524760451bb0454d58a9ead9626735474699a4657e1c4aa984c83d4af6b673","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-29T15:34:26Z","title_canon_sha256":"e35fdc4e9bf79b194b105cd434af57ab10cc20bf749d5d7404523162d21fb1a9"},"schema_version":"1.0","source":{"id":"2306.17033","kind":"arxiv","version":1}},"canonical_sha256":"30b693cea8804ef56b4534fd811e9245ca739994e3939412839585faae5d67ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30b693cea8804ef56b4534fd811e9245ca739994e3939412839585faae5d67ad","first_computed_at":"2026-07-05T06:26:12.448186Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:12.448186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tXZ4BsHAhH+vI/nujnVAZRpELyq2HVpRlgDv7fBDaCDqnbKFlM22xrbuVDh9euMXU2vCLkAwsn65dyuyLo4eBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:12.448689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.17033","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca319bbb1fad802b00421bcc6c1ea3e76a919fd380d16e4ae30cbbe44c3c85a0","sha256:4ab8005a60c3ebc0956cc5430174efba4e123463459ee4ead840f4b06d1c654f"],"state_sha256":"f4940ae4e2714c9b4037d6725a42169699cab3020b22350842da2febdc63756b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mEqBjEzyRMIKJKGaJlB2wQZvBVHJzkzSRdbL+qBcLATTbk1El1sSD89zZQbtuCi3OpLbKtrN4irMAfbmVktHCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T06:05:36.735118Z","bundle_sha256":"e7a5db60579deb57fa1172a89db63fe0063984b53ef790a09ea61e892019d014"}}