{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3J7S2UBBCXVEIGVVRSHU4VW2IY","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":"bd9fcc1e24e2391f605f237b4a80200c4d397bb7c39dd29196a5f62e6d51d0a8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-09T14:17:05Z","title_canon_sha256":"839ea5b9277093f75a125869e30c9cefbd6dda40cc83ce4bd1069356d198e966"},"schema_version":"1.0","source":{"id":"2202.04478","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.04478","created_at":"2026-07-05T03:56:34Z"},{"alias_kind":"arxiv_version","alias_value":"2202.04478v2","created_at":"2026-07-05T03:56:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.04478","created_at":"2026-07-05T03:56:34Z"},{"alias_kind":"pith_short_12","alias_value":"3J7S2UBBCXVE","created_at":"2026-07-05T03:56:34Z"},{"alias_kind":"pith_short_16","alias_value":"3J7S2UBBCXVEIGVV","created_at":"2026-07-05T03:56:34Z"},{"alias_kind":"pith_short_8","alias_value":"3J7S2UBB","created_at":"2026-07-05T03:56:34Z"}],"graph_snapshots":[{"event_id":"sha256:140560f61b5d87e0a183f34406cf6ac0a4dfe3d80af7a3985c2cabb2fc677a60","target":"graph","created_at":"2026-07-05T03:56:34Z","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/2202.04478/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Solving goal-conditioned tasks with sparse rewards using self-supervised learning is promising because of its simplicity and stability over current reinforcement learning (RL) algorithms. A recent work, called Goal-Conditioned Supervised Learning (GCSL), provides a new learning framework by iteratively relabeling and imitating self-generated experiences. In this paper, we revisit the theoretical property of GCSL -- optimizing a lower bound of the goal reaching objective, and extend GCSL as a novel offline goal-conditioned RL algorithm. The proposed method is named Weighted GCSL (WGCSL), in whi","authors_text":"Chongjie Zhang, Hao Sun, Lei Han, Meng Fang, Rui Yang, Wenzhe Li, Xiu Li, Yali Du, Yiming Lu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-09T14:17:05Z","title":"Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.04478","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":"sha256:331d1db49235b256e50365a5699e076c6330d9c3961317c8ce50bdd87db516e7","target":"record","created_at":"2026-07-05T03:56:34Z","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":"bd9fcc1e24e2391f605f237b4a80200c4d397bb7c39dd29196a5f62e6d51d0a8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-09T14:17:05Z","title_canon_sha256":"839ea5b9277093f75a125869e30c9cefbd6dda40cc83ce4bd1069356d198e966"},"schema_version":"1.0","source":{"id":"2202.04478","kind":"arxiv","version":2}},"canonical_sha256":"da7f2d502115ea441ab58c8f4e56da46295ae195dffdd154c9cb746241735064","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da7f2d502115ea441ab58c8f4e56da46295ae195dffdd154c9cb746241735064","first_computed_at":"2026-07-05T03:56:34.611707Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:56:34.611707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rc6IosUrdre1+TgZLA7NQEfLJ0gdZE6x7P4Qr6+pK85s9SbFRMsMTdWqyG0P0CpvYbJ8pHo+VF+dobIf1sf/BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:56:34.612185Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.04478","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:331d1db49235b256e50365a5699e076c6330d9c3961317c8ce50bdd87db516e7","sha256:140560f61b5d87e0a183f34406cf6ac0a4dfe3d80af7a3985c2cabb2fc677a60"],"state_sha256":"359794a5c72c1121c2f2f289f57786134d8e1dae80dce30b7746a34f66444e90"}