{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LNIEBPSVUSXQNEHZI5GA7D45C3","short_pith_number":"pith:LNIEBPSV","schema_version":"1.0","canonical_sha256":"5b5040be55a4af0690f9474c0f8f9d16c064f440daf8aa3993b23a136d288b4d","source":{"kind":"arxiv","id":"2410.06648","version":5},"attestation_state":"computed","paper":{"title":"Q-WSL: Optimizing Goal-Conditioned RL with Weighted Supervised Learning via Dynamic Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Donglin Wang, Xing Lei, Xuetao Zhang, Zifeng Zhuang","submitted_at":"2024-10-09T08:00:12Z","abstract_excerpt":"A novel class of advanced algorithms, termed Goal-Conditioned Weighted Supervised Learning (GCWSL), has recently emerged to tackle the challenges posed by sparse rewards in goal-conditioned reinforcement learning (RL). GCWSL consistently delivers strong performance across a diverse set of goal-reaching tasks due to its simplicity, effectiveness, and stability. However, GCWSL methods lack a crucial capability known as trajectory stitching, which is essential for learning optimal policies when faced with unseen skills during testing. This limitation becomes particularly pronounced when the repla"},"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":"2410.06648","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-09T08:00:12Z","cross_cats_sorted":[],"title_canon_sha256":"f4775b8bcc70bbcb4a7ab87dc2619382b7bc6d44e623dc7a48a3c5e7497a591a","abstract_canon_sha256":"8d18a737fb45bf0d206d3596a44c1336f80c206fdf6598b1111319558192137f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:36.274094Z","signature_b64":"ypdMCNcDBMzfCZ9axXnhuG4WXPMs4PTpXR+JmZchWCu+zgYIW/ayiJT65dmFut5bJ+gsUixXQvRDf4cyFa1JBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b5040be55a4af0690f9474c0f8f9d16c064f440daf8aa3993b23a136d288b4d","last_reissued_at":"2026-07-05T11:17:36.273653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:36.273653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Q-WSL: Optimizing Goal-Conditioned RL with Weighted Supervised Learning via Dynamic Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Donglin Wang, Xing Lei, Xuetao Zhang, Zifeng Zhuang","submitted_at":"2024-10-09T08:00:12Z","abstract_excerpt":"A novel class of advanced algorithms, termed Goal-Conditioned Weighted Supervised Learning (GCWSL), has recently emerged to tackle the challenges posed by sparse rewards in goal-conditioned reinforcement learning (RL). GCWSL consistently delivers strong performance across a diverse set of goal-reaching tasks due to its simplicity, effectiveness, and stability. However, GCWSL methods lack a crucial capability known as trajectory stitching, which is essential for learning optimal policies when faced with unseen skills during testing. This limitation becomes particularly pronounced when the repla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06648","kind":"arxiv","version":5},"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/2410.06648/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":"2410.06648","created_at":"2026-07-05T11:17:36.273713+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.06648v5","created_at":"2026-07-05T11:17:36.273713+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06648","created_at":"2026-07-05T11:17:36.273713+00:00"},{"alias_kind":"pith_short_12","alias_value":"LNIEBPSVUSXQ","created_at":"2026-07-05T11:17:36.273713+00:00"},{"alias_kind":"pith_short_16","alias_value":"LNIEBPSVUSXQNEHZ","created_at":"2026-07-05T11:17:36.273713+00:00"},{"alias_kind":"pith_short_8","alias_value":"LNIEBPSV","created_at":"2026-07-05T11:17:36.273713+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02577","citing_title":"Reachability Weighted Offline Goal-conditioned Resampling","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LNIEBPSVUSXQNEHZI5GA7D45C3","json":"https://pith.science/pith/LNIEBPSVUSXQNEHZI5GA7D45C3.json","graph_json":"https://pith.science/api/pith-number/LNIEBPSVUSXQNEHZI5GA7D45C3/graph.json","events_json":"https://pith.science/api/pith-number/LNIEBPSVUSXQNEHZI5GA7D45C3/events.json","paper":"https://pith.science/paper/LNIEBPSV"},"agent_actions":{"view_html":"https://pith.science/pith/LNIEBPSVUSXQNEHZI5GA7D45C3","download_json":"https://pith.science/pith/LNIEBPSVUSXQNEHZI5GA7D45C3.json","view_paper":"https://pith.science/paper/LNIEBPSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.06648&json=true","fetch_graph":"https://pith.science/api/pith-number/LNIEBPSVUSXQNEHZI5GA7D45C3/graph.json","fetch_events":"https://pith.science/api/pith-number/LNIEBPSVUSXQNEHZI5GA7D45C3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LNIEBPSVUSXQNEHZI5GA7D45C3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LNIEBPSVUSXQNEHZI5GA7D45C3/action/storage_attestation","attest_author":"https://pith.science/pith/LNIEBPSVUSXQNEHZI5GA7D45C3/action/author_attestation","sign_citation":"https://pith.science/pith/LNIEBPSVUSXQNEHZI5GA7D45C3/action/citation_signature","submit_replication":"https://pith.science/pith/LNIEBPSVUSXQNEHZI5GA7D45C3/action/replication_record"}},"created_at":"2026-07-05T11:17:36.273713+00:00","updated_at":"2026-07-05T11:17:36.273713+00:00"}