{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LNIEBPSVUSXQNEHZI5GA7D45C3","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":"8d18a737fb45bf0d206d3596a44c1336f80c206fdf6598b1111319558192137f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-09T08:00:12Z","title_canon_sha256":"f4775b8bcc70bbcb4a7ab87dc2619382b7bc6d44e623dc7a48a3c5e7497a591a"},"schema_version":"1.0","source":{"id":"2410.06648","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06648","created_at":"2026-07-05T11:17:36Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06648v5","created_at":"2026-07-05T11:17:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06648","created_at":"2026-07-05T11:17:36Z"},{"alias_kind":"pith_short_12","alias_value":"LNIEBPSVUSXQ","created_at":"2026-07-05T11:17:36Z"},{"alias_kind":"pith_short_16","alias_value":"LNIEBPSVUSXQNEHZ","created_at":"2026-07-05T11:17:36Z"},{"alias_kind":"pith_short_8","alias_value":"LNIEBPSV","created_at":"2026-07-05T11:17:36Z"}],"graph_snapshots":[{"event_id":"sha256:ef2f99e78eacf18c350f9066ddd11b0aca62300dc79dcdfed9f5254ceec9f68c","target":"graph","created_at":"2026-07-05T11:17:36Z","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/2410.06648/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Donglin Wang, Xing Lei, Xuetao Zhang, Zifeng Zhuang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-09T08:00:12Z","title":"Q-WSL: Optimizing Goal-Conditioned RL with Weighted Supervised Learning via Dynamic Programming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06648","kind":"arxiv","version":5},"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":"sha256:3a5add1d0989517a8d78915f78f89dbb6f1fb7e45c00195dcbe0922461d020fc","target":"record","created_at":"2026-07-05T11:17:36Z","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":"8d18a737fb45bf0d206d3596a44c1336f80c206fdf6598b1111319558192137f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-09T08:00:12Z","title_canon_sha256":"f4775b8bcc70bbcb4a7ab87dc2619382b7bc6d44e623dc7a48a3c5e7497a591a"},"schema_version":"1.0","source":{"id":"2410.06648","kind":"arxiv","version":5}},"canonical_sha256":"5b5040be55a4af0690f9474c0f8f9d16c064f440daf8aa3993b23a136d288b4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b5040be55a4af0690f9474c0f8f9d16c064f440daf8aa3993b23a136d288b4d","first_computed_at":"2026-07-05T11:17:36.273653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:36.273653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ypdMCNcDBMzfCZ9axXnhuG4WXPMs4PTpXR+JmZchWCu+zgYIW/ayiJT65dmFut5bJ+gsUixXQvRDf4cyFa1JBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:36.274094Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06648","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a5add1d0989517a8d78915f78f89dbb6f1fb7e45c00195dcbe0922461d020fc","sha256:ef2f99e78eacf18c350f9066ddd11b0aca62300dc79dcdfed9f5254ceec9f68c"],"state_sha256":"1a683340a8d6131784e6c144ddbe13453afb40e27209b931bb2f0f655b9e52f7"}