{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GAYA75A247VTWFMDQ5OJWEZVZS","short_pith_number":"pith:GAYA75A2","canonical_record":{"source":{"id":"2403.01734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-04T05:20:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9accb5e64b2f77d66f4089e60057271e0ed00588f7f3fa4e7e271ddd21516748","abstract_canon_sha256":"4f8f399e090a7c95b8261393623003bdf652f3c25e8842112fd7fe197c81cb22"},"schema_version":"1.0"},"canonical_sha256":"30300ff41ae7eb3b1583875c9b1335cc820ffb539bde05dbbcb5f60682c95b2b","source":{"kind":"arxiv","id":"2403.01734","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01734","created_at":"2026-07-05T07:51:51Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01734v1","created_at":"2026-07-05T07:51:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01734","created_at":"2026-07-05T07:51:51Z"},{"alias_kind":"pith_short_12","alias_value":"GAYA75A247VT","created_at":"2026-07-05T07:51:51Z"},{"alias_kind":"pith_short_16","alias_value":"GAYA75A247VTWFMD","created_at":"2026-07-05T07:51:51Z"},{"alias_kind":"pith_short_8","alias_value":"GAYA75A2","created_at":"2026-07-05T07:51:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GAYA75A247VTWFMDQ5OJWEZVZS","target":"record","payload":{"canonical_record":{"source":{"id":"2403.01734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-04T05:20:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9accb5e64b2f77d66f4089e60057271e0ed00588f7f3fa4e7e271ddd21516748","abstract_canon_sha256":"4f8f399e090a7c95b8261393623003bdf652f3c25e8842112fd7fe197c81cb22"},"schema_version":"1.0"},"canonical_sha256":"30300ff41ae7eb3b1583875c9b1335cc820ffb539bde05dbbcb5f60682c95b2b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:51.142986Z","signature_b64":"K8vKcN5mvAkbnnLVwpsKxul+Bh+oUdqkxQY0YWs5JfSR4mbk8U1HJ+YjtwksG0snuSKa7TxTSZww6ZM5+nMlCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30300ff41ae7eb3b1583875c9b1335cc820ffb539bde05dbbcb5f60682c95b2b","last_reissued_at":"2026-07-05T07:51:51.141859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:51.141859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.01734","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":"2026-07-05T07:51:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mY80QUZCfr1872GqeirWz4T24BhCU+fSM+EUfG03/dUnSiP+ZQ11Vs19MhwTcKBO4SliMGFWLLYGEUQwrcQaAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T10:53:38.532610Z"},"content_sha256":"19a9e9f6d6ae85c5e1c5eaf82a5b887822e127b510190848afae47dbda6b3399","schema_version":"1.0","event_id":"sha256:19a9e9f6d6ae85c5e1c5eaf82a5b887822e127b510190848afae47dbda6b3399"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GAYA75A247VTWFMDQ5OJWEZVZS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Goal-Conditioned Reinforcement Learning for Safety-Critical Tasks with Recovery Policy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chenyang Cao, Junbo Tan, Renhao Lu, Xueqian Wang, Zichen Yan","submitted_at":"2024-03-04T05:20:57Z","abstract_excerpt":"Offline goal-conditioned reinforcement learning (GCRL) aims at solving goal-reaching tasks with sparse rewards from an offline dataset. While prior work has demonstrated various approaches for agents to learn near-optimal policies, these methods encounter limitations when dealing with diverse constraints in complex environments, such as safety constraints. Some of these approaches prioritize goal attainment without considering safety, while others excessively focus on safety at the expense of training efficiency. In this paper, we study the problem of constrained offline GCRL and propose a new"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01734","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/2403.01734/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":"2026-07-05T07:51:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+L3drT6Nezgw4NUOjXW5LjQNNHoUzcfeK7MGvLUMe4UwaVMtvR7QXG3GIblTvqaNLzndANLHJox+mLJQBR4KCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T10:53:38.533157Z"},"content_sha256":"f3d45766c09210138df62768e1485057364f298afc595bcc1835d167f79b6715","schema_version":"1.0","event_id":"sha256:f3d45766c09210138df62768e1485057364f298afc595bcc1835d167f79b6715"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GAYA75A247VTWFMDQ5OJWEZVZS/bundle.json","state_url":"https://pith.science/pith/GAYA75A247VTWFMDQ5OJWEZVZS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GAYA75A247VTWFMDQ5OJWEZVZS/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":"2026-08-23T10:53:38Z","links":{"resolver":"https://pith.science/pith/GAYA75A247VTWFMDQ5OJWEZVZS","bundle":"https://pith.science/pith/GAYA75A247VTWFMDQ5OJWEZVZS/bundle.json","state":"https://pith.science/pith/GAYA75A247VTWFMDQ5OJWEZVZS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GAYA75A247VTWFMDQ5OJWEZVZS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GAYA75A247VTWFMDQ5OJWEZVZS","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":"4f8f399e090a7c95b8261393623003bdf652f3c25e8842112fd7fe197c81cb22","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-04T05:20:57Z","title_canon_sha256":"9accb5e64b2f77d66f4089e60057271e0ed00588f7f3fa4e7e271ddd21516748"},"schema_version":"1.0","source":{"id":"2403.01734","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01734","created_at":"2026-07-05T07:51:51Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01734v1","created_at":"2026-07-05T07:51:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01734","created_at":"2026-07-05T07:51:51Z"},{"alias_kind":"pith_short_12","alias_value":"GAYA75A247VT","created_at":"2026-07-05T07:51:51Z"},{"alias_kind":"pith_short_16","alias_value":"GAYA75A247VTWFMD","created_at":"2026-07-05T07:51:51Z"},{"alias_kind":"pith_short_8","alias_value":"GAYA75A2","created_at":"2026-07-05T07:51:51Z"}],"graph_snapshots":[{"event_id":"sha256:f3d45766c09210138df62768e1485057364f298afc595bcc1835d167f79b6715","target":"graph","created_at":"2026-07-05T07:51:51Z","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/2403.01734/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline goal-conditioned reinforcement learning (GCRL) aims at solving goal-reaching tasks with sparse rewards from an offline dataset. While prior work has demonstrated various approaches for agents to learn near-optimal policies, these methods encounter limitations when dealing with diverse constraints in complex environments, such as safety constraints. Some of these approaches prioritize goal attainment without considering safety, while others excessively focus on safety at the expense of training efficiency. In this paper, we study the problem of constrained offline GCRL and propose a new","authors_text":"Chenyang Cao, Junbo Tan, Renhao Lu, Xueqian Wang, Zichen Yan","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-04T05:20:57Z","title":"Offline Goal-Conditioned Reinforcement Learning for Safety-Critical Tasks with Recovery Policy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01734","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":"sha256:19a9e9f6d6ae85c5e1c5eaf82a5b887822e127b510190848afae47dbda6b3399","target":"record","created_at":"2026-07-05T07:51:51Z","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":"4f8f399e090a7c95b8261393623003bdf652f3c25e8842112fd7fe197c81cb22","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-04T05:20:57Z","title_canon_sha256":"9accb5e64b2f77d66f4089e60057271e0ed00588f7f3fa4e7e271ddd21516748"},"schema_version":"1.0","source":{"id":"2403.01734","kind":"arxiv","version":1}},"canonical_sha256":"30300ff41ae7eb3b1583875c9b1335cc820ffb539bde05dbbcb5f60682c95b2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30300ff41ae7eb3b1583875c9b1335cc820ffb539bde05dbbcb5f60682c95b2b","first_computed_at":"2026-07-05T07:51:51.141859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:51.141859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K8vKcN5mvAkbnnLVwpsKxul+Bh+oUdqkxQY0YWs5JfSR4mbk8U1HJ+YjtwksG0snuSKa7TxTSZww6ZM5+nMlCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:51.142986Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.01734","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19a9e9f6d6ae85c5e1c5eaf82a5b887822e127b510190848afae47dbda6b3399","sha256:f3d45766c09210138df62768e1485057364f298afc595bcc1835d167f79b6715"],"state_sha256":"7c155b2691ffc30060e06d46214c0ff99885e9d17f06b8f105c003c0b49560c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iiSftbxS89DmC1oKMsCZrD5Mh+Asvk6WJJVYM6NFwSeRwPqJRfl6e12uTg4esz5cPSi50e5rotPIpwtNUWTTBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T10:53:38.537351Z","bundle_sha256":"f31c581c6bf9af416eb2fff2a6b2c70366e67b58bb5bc0d18120464b76b7962b"}}