{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JKVZYLLEPDDQCTX2YM5OXVBMM2","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":"5f44d4a3142ecba0cc190164c4bedc855757e60e541903bd833ee035b49a331f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T21:09:16Z","title_canon_sha256":"41bbfabad174b831974cbb53270a4a71613110b3a7dc71d3ddb5582ba01d55ea"},"schema_version":"1.0","source":{"id":"2507.05477","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05477","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05477v1","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05477","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"pith_short_12","alias_value":"JKVZYLLEPDDQ","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"pith_short_16","alias_value":"JKVZYLLEPDDQCTX2","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"pith_short_8","alias_value":"JKVZYLLE","created_at":"2026-07-05T11:33:31Z"}],"graph_snapshots":[{"event_id":"sha256:9b46578fb79149ccd17599d82ea17860cde73dcd46153cfc6f4d46a3b9b3cc6b","target":"graph","created_at":"2026-07-05T11:33:31Z","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/2507.05477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot reinforcement learning is necessary for extracting optimal policies in absence of concrete rewards for fast adaptation to future problem settings. Forward-backward representations (FB) have emerged as a promising method for learning optimal policies in absence of rewards via a factorization of the policy occupancy measure. However, up until now, FB and many similar zero-shot reinforcement learning algorithms have been decoupled from the exploration problem, generally relying on other exploration algorithms for data collection. We argue that FB representations should fundamentally be ","authors_text":"Georg Martius, Marin Vlastelica, N\\'uria Armengol Urp\\'i, Stelian Coros","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T21:09:16Z","title":"Epistemically-guided forward-backward exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05477","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":"sha256:8b996ad4cc44795fb672183fa18c4142ee3392af631be897c0df3f2e95e388dc","target":"record","created_at":"2026-07-05T11:33:31Z","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":"5f44d4a3142ecba0cc190164c4bedc855757e60e541903bd833ee035b49a331f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T21:09:16Z","title_canon_sha256":"41bbfabad174b831974cbb53270a4a71613110b3a7dc71d3ddb5582ba01d55ea"},"schema_version":"1.0","source":{"id":"2507.05477","kind":"arxiv","version":1}},"canonical_sha256":"4aab9c2d6478c7014efac33aebd42c668a6a97fb1f5f9e88db2bd94b7bee43f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4aab9c2d6478c7014efac33aebd42c668a6a97fb1f5f9e88db2bd94b7bee43f5","first_computed_at":"2026-07-05T11:33:31.132215Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:31.132215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u5JQszov6imOfTPYIrIiXWBPRaxcOPCuQ73f8158oT0j0WqWbojNNpxTFlRs3KP247DzUW49uBbHlHabV1pCCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:31.132594Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05477","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b996ad4cc44795fb672183fa18c4142ee3392af631be897c0df3f2e95e388dc","sha256:9b46578fb79149ccd17599d82ea17860cde73dcd46153cfc6f4d46a3b9b3cc6b"],"state_sha256":"cb1e696cbf7cc9534eae65b7748d23870b5a6d55da3568c7a5eaeb3958654496"}