{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VCIQ54OL3WPKJQWCQYU4QZZZ5G","short_pith_number":"pith:VCIQ54OL","canonical_record":{"source":{"id":"2305.16147","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-25T15:18:46Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"15c7f9130d75a5f1b6323ab2f7eb3bd2fda65bfc898b27950ccda88de6789d28","abstract_canon_sha256":"462fe4c8b3294140163d46a4ec70913e9bec442b09ff177fcdb52dab516ad7fb"},"schema_version":"1.0"},"canonical_sha256":"a8910ef1cbdd9ea4c2c28629c86739e9b9de7d7ea0d680bdfca0655fec9be3a1","source":{"kind":"arxiv","id":"2305.16147","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16147","created_at":"2026-07-05T07:51:09Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16147v2","created_at":"2026-07-05T07:51:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16147","created_at":"2026-07-05T07:51:09Z"},{"alias_kind":"pith_short_12","alias_value":"VCIQ54OL3WPK","created_at":"2026-07-05T07:51:09Z"},{"alias_kind":"pith_short_16","alias_value":"VCIQ54OL3WPKJQWC","created_at":"2026-07-05T07:51:09Z"},{"alias_kind":"pith_short_8","alias_value":"VCIQ54OL","created_at":"2026-07-05T07:51:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VCIQ54OL3WPKJQWCQYU4QZZZ5G","target":"record","payload":{"canonical_record":{"source":{"id":"2305.16147","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-25T15:18:46Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"15c7f9130d75a5f1b6323ab2f7eb3bd2fda65bfc898b27950ccda88de6789d28","abstract_canon_sha256":"462fe4c8b3294140163d46a4ec70913e9bec442b09ff177fcdb52dab516ad7fb"},"schema_version":"1.0"},"canonical_sha256":"a8910ef1cbdd9ea4c2c28629c86739e9b9de7d7ea0d680bdfca0655fec9be3a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:09.241869Z","signature_b64":"QfTsZ4hcwYhBtgNx3RTk3Hcm9GWZe6igVcEANFKGfeyJDO/dpR7ETsSRYqDhdVYF3wXEYl6TnlRDsKDZrc6vDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8910ef1cbdd9ea4c2c28629c86739e9b9de7d7ea0d680bdfca0655fec9be3a1","last_reissued_at":"2026-07-05T07:51:09.241428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:09.241428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.16147","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":"2026-07-05T07:51:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FzD79FxzAa+MTlLvrv6B8M+UkhSIexOj0sKS1MXsZ+aDzfN0oPLwBLXI3RR9TlvInIZZXxnUFPtpWo4vUx75Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T02:58:29.315862Z"},"content_sha256":"57ca9044c21aecae8f19bd09791494f2f07b7b767feef180d2c7a64bf9e81a38","schema_version":"1.0","event_id":"sha256:57ca9044c21aecae8f19bd09791494f2f07b7b767feef180d2c7a64bf9e81a38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VCIQ54OL3WPKJQWCQYU4QZZZ5G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Safety Constraints from Demonstrations with Unknown Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Krause, David Lindner, Katja Hofmann, Sebastian Tschiatschek, Xin Chen","submitted_at":"2023-05-25T15:18:46Z","abstract_excerpt":"We propose Convex Constraint Learning for Reinforcement Learning (CoCoRL), a novel approach for inferring shared constraints in a Constrained Markov Decision Process (CMDP) from a set of safe demonstrations with possibly different reward functions. While previous work is limited to demonstrations with known rewards or fully known environment dynamics, CoCoRL can learn constraints from demonstrations with different unknown rewards without knowledge of the environment dynamics. CoCoRL constructs a convex safe set based on demonstrations, which provably guarantees safety even for potentially sub-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16147","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/2305.16147/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":"2026-07-05T07:51:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E5nQkc1z6VQo2ujVR23akFzglwvjqXu09kemZyJLyYraeU/tHPeLRbQO/eo8d6KMSqn9VQk0SBtQozsRUwD7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T02:58:29.316876Z"},"content_sha256":"7f5f3fe92898b0abe93139b245d0366eb06c62b067123ab789320922418d1ab3","schema_version":"1.0","event_id":"sha256:7f5f3fe92898b0abe93139b245d0366eb06c62b067123ab789320922418d1ab3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VCIQ54OL3WPKJQWCQYU4QZZZ5G/bundle.json","state_url":"https://pith.science/pith/VCIQ54OL3WPKJQWCQYU4QZZZ5G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VCIQ54OL3WPKJQWCQYU4QZZZ5G/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":"2026-08-15T02:58:29Z","links":{"resolver":"https://pith.science/pith/VCIQ54OL3WPKJQWCQYU4QZZZ5G","bundle":"https://pith.science/pith/VCIQ54OL3WPKJQWCQYU4QZZZ5G/bundle.json","state":"https://pith.science/pith/VCIQ54OL3WPKJQWCQYU4QZZZ5G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VCIQ54OL3WPKJQWCQYU4QZZZ5G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VCIQ54OL3WPKJQWCQYU4QZZZ5G","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":"462fe4c8b3294140163d46a4ec70913e9bec442b09ff177fcdb52dab516ad7fb","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-25T15:18:46Z","title_canon_sha256":"15c7f9130d75a5f1b6323ab2f7eb3bd2fda65bfc898b27950ccda88de6789d28"},"schema_version":"1.0","source":{"id":"2305.16147","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16147","created_at":"2026-07-05T07:51:09Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16147v2","created_at":"2026-07-05T07:51:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16147","created_at":"2026-07-05T07:51:09Z"},{"alias_kind":"pith_short_12","alias_value":"VCIQ54OL3WPK","created_at":"2026-07-05T07:51:09Z"},{"alias_kind":"pith_short_16","alias_value":"VCIQ54OL3WPKJQWC","created_at":"2026-07-05T07:51:09Z"},{"alias_kind":"pith_short_8","alias_value":"VCIQ54OL","created_at":"2026-07-05T07:51:09Z"}],"graph_snapshots":[{"event_id":"sha256:7f5f3fe92898b0abe93139b245d0366eb06c62b067123ab789320922418d1ab3","target":"graph","created_at":"2026-07-05T07:51:09Z","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/2305.16147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Convex Constraint Learning for Reinforcement Learning (CoCoRL), a novel approach for inferring shared constraints in a Constrained Markov Decision Process (CMDP) from a set of safe demonstrations with possibly different reward functions. While previous work is limited to demonstrations with known rewards or fully known environment dynamics, CoCoRL can learn constraints from demonstrations with different unknown rewards without knowledge of the environment dynamics. CoCoRL constructs a convex safe set based on demonstrations, which provably guarantees safety even for potentially sub-","authors_text":"Andreas Krause, David Lindner, Katja Hofmann, Sebastian Tschiatschek, Xin Chen","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-25T15:18:46Z","title":"Learning Safety Constraints from Demonstrations with Unknown Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16147","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":"sha256:57ca9044c21aecae8f19bd09791494f2f07b7b767feef180d2c7a64bf9e81a38","target":"record","created_at":"2026-07-05T07:51:09Z","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":"462fe4c8b3294140163d46a4ec70913e9bec442b09ff177fcdb52dab516ad7fb","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-25T15:18:46Z","title_canon_sha256":"15c7f9130d75a5f1b6323ab2f7eb3bd2fda65bfc898b27950ccda88de6789d28"},"schema_version":"1.0","source":{"id":"2305.16147","kind":"arxiv","version":2}},"canonical_sha256":"a8910ef1cbdd9ea4c2c28629c86739e9b9de7d7ea0d680bdfca0655fec9be3a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8910ef1cbdd9ea4c2c28629c86739e9b9de7d7ea0d680bdfca0655fec9be3a1","first_computed_at":"2026-07-05T07:51:09.241428Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:09.241428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QfTsZ4hcwYhBtgNx3RTk3Hcm9GWZe6igVcEANFKGfeyJDO/dpR7ETsSRYqDhdVYF3wXEYl6TnlRDsKDZrc6vDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:09.241869Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.16147","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57ca9044c21aecae8f19bd09791494f2f07b7b767feef180d2c7a64bf9e81a38","sha256:7f5f3fe92898b0abe93139b245d0366eb06c62b067123ab789320922418d1ab3"],"state_sha256":"0cc84568963b69cfc70b869b0d1198fba0c743ae3c5c2818ceae7111300262f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iAjpB61mOtv/NSQtii7kWyTqdkrUOVteRbSTyCneCofQ6zIHbjwRleQ0peVrYKzcfvSJ7GWGQdHWuuz+AcJbCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T02:58:29.334128Z","bundle_sha256":"f4f58618039bb9a3277d23b8ac3acdba0d693657d8e22d317127ed360c6010ee"}}