{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3J7S2UBBCXVEIGVVRSHU4VW2IY","short_pith_number":"pith:3J7S2UBB","schema_version":"1.0","canonical_sha256":"da7f2d502115ea441ab58c8f4e56da46295ae195dffdd154c9cb746241735064","source":{"kind":"arxiv","id":"2202.04478","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chongjie Zhang, Hao Sun, Lei Han, Meng Fang, Rui Yang, Wenzhe Li, Xiu Li, Yali Du, Yiming Lu","submitted_at":"2022-02-09T14:17:05Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2202.04478","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-09T14:17:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"839ea5b9277093f75a125869e30c9cefbd6dda40cc83ce4bd1069356d198e966","abstract_canon_sha256":"bd9fcc1e24e2391f605f237b4a80200c4d397bb7c39dd29196a5f62e6d51d0a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:34.612185Z","signature_b64":"rc6IosUrdre1+TgZLA7NQEfLJ0gdZE6x7P4Qr6+pK85s9SbFRMsMTdWqyG0P0CpvYbJ8pHo+VF+dobIf1sf/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da7f2d502115ea441ab58c8f4e56da46295ae195dffdd154c9cb746241735064","last_reissued_at":"2026-07-05T03:56:34.611707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:34.611707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chongjie Zhang, Hao Sun, Lei Han, Meng Fang, Rui Yang, Wenzhe Li, Xiu Li, Yali Du, Yiming Lu","submitted_at":"2022-02-09T14:17:05Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.04478","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/2202.04478/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2202.04478","created_at":"2026-07-05T03:56:34.611765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.04478v2","created_at":"2026-07-05T03:56:34.611765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.04478","created_at":"2026-07-05T03:56:34.611765+00:00"},{"alias_kind":"pith_short_12","alias_value":"3J7S2UBBCXVE","created_at":"2026-07-05T03:56:34.611765+00:00"},{"alias_kind":"pith_short_16","alias_value":"3J7S2UBBCXVEIGVV","created_at":"2026-07-05T03:56:34.611765+00:00"},{"alias_kind":"pith_short_8","alias_value":"3J7S2UBB","created_at":"2026-07-05T03:56:34.611765+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30503","citing_title":"Physics-informed Goal-Conditioned Reinforcement Learning under Hybrid Contact Dynamics","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01862","citing_title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","ref_index":221,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20627","citing_title":"Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3J7S2UBBCXVEIGVVRSHU4VW2IY","json":"https://pith.science/pith/3J7S2UBBCXVEIGVVRSHU4VW2IY.json","graph_json":"https://pith.science/api/pith-number/3J7S2UBBCXVEIGVVRSHU4VW2IY/graph.json","events_json":"https://pith.science/api/pith-number/3J7S2UBBCXVEIGVVRSHU4VW2IY/events.json","paper":"https://pith.science/paper/3J7S2UBB"},"agent_actions":{"view_html":"https://pith.science/pith/3J7S2UBBCXVEIGVVRSHU4VW2IY","download_json":"https://pith.science/pith/3J7S2UBBCXVEIGVVRSHU4VW2IY.json","view_paper":"https://pith.science/paper/3J7S2UBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.04478&json=true","fetch_graph":"https://pith.science/api/pith-number/3J7S2UBBCXVEIGVVRSHU4VW2IY/graph.json","fetch_events":"https://pith.science/api/pith-number/3J7S2UBBCXVEIGVVRSHU4VW2IY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3J7S2UBBCXVEIGVVRSHU4VW2IY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3J7S2UBBCXVEIGVVRSHU4VW2IY/action/storage_attestation","attest_author":"https://pith.science/pith/3J7S2UBBCXVEIGVVRSHU4VW2IY/action/author_attestation","sign_citation":"https://pith.science/pith/3J7S2UBBCXVEIGVVRSHU4VW2IY/action/citation_signature","submit_replication":"https://pith.science/pith/3J7S2UBBCXVEIGVVRSHU4VW2IY/action/replication_record"}},"created_at":"2026-07-05T03:56:34.611765+00:00","updated_at":"2026-07-05T03:56:34.611765+00:00"}