{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GA7SADDW2FJCFKN5QHY7YCZDM5","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":"4153a697f470d4f601981c19cc2798cae5a5e5ebd608295c292db35f79827bc8","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T19:09:10Z","title_canon_sha256":"c1374c118265eb34ef74ec000c2193d20d044ad5cbfaab97a743d2e0e5d84bd8"},"schema_version":"1.0","source":{"id":"2402.15567","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15567","created_at":"2026-07-05T08:23:18Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15567v2","created_at":"2026-07-05T08:23:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15567","created_at":"2026-07-05T08:23:18Z"},{"alias_kind":"pith_short_12","alias_value":"GA7SADDW2FJC","created_at":"2026-07-05T08:23:18Z"},{"alias_kind":"pith_short_16","alias_value":"GA7SADDW2FJCFKN5","created_at":"2026-07-05T08:23:18Z"},{"alias_kind":"pith_short_8","alias_value":"GA7SADDW","created_at":"2026-07-05T08:23:18Z"}],"graph_snapshots":[{"event_id":"sha256:7986a39a41435ba3c3279c39c0c63511a29f27f108090836f019b028e0cb81ce","target":"graph","created_at":"2026-07-05T08:23:18Z","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/2402.15567/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised and self-supervised objectives, such as next token prediction, have enabled pre-training generalist models from large amounts of unlabeled data. In reinforcement learning (RL), however, finding a truly general and scalable unsupervised pre-training objective for generalist policies from offline data remains a major open question. While a number of methods have been proposed to enable generic self-supervised RL, based on principles such as goal-conditioned RL, behavioral cloning, and unsupervised skill learning, such methods remain limited in terms of either the diversity of the di","authors_text":"Seohong Park, Sergey Levine, Tobias Kreiman","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T19:09:10Z","title":"Foundation Policies with Hilbert Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15567","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":"sha256:63a0660852aba1f4b9de18d83c2d8bd2546aba9b18c7511253ee2fbeee3684c5","target":"record","created_at":"2026-07-05T08:23:18Z","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":"4153a697f470d4f601981c19cc2798cae5a5e5ebd608295c292db35f79827bc8","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T19:09:10Z","title_canon_sha256":"c1374c118265eb34ef74ec000c2193d20d044ad5cbfaab97a743d2e0e5d84bd8"},"schema_version":"1.0","source":{"id":"2402.15567","kind":"arxiv","version":2}},"canonical_sha256":"303f200c76d15222a9bd81f1fc0b2367538ec566affcceb64bc7ac46a31c5e42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"303f200c76d15222a9bd81f1fc0b2367538ec566affcceb64bc7ac46a31c5e42","first_computed_at":"2026-07-05T08:23:18.593151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:18.593151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FGQFhbuk7zxrLFk0Ys5Ps/BVtPuHJVSasbx1VD7LGbpTW7kHGbW50Kh92z1yWiJzAkbSqbYK5B44dxwW5nguDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:18.593689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15567","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63a0660852aba1f4b9de18d83c2d8bd2546aba9b18c7511253ee2fbeee3684c5","sha256:7986a39a41435ba3c3279c39c0c63511a29f27f108090836f019b028e0cb81ce"],"state_sha256":"526dbbbcd0ff982b8a3421150e13663f38e57c4f4549bae4ba5f1f7b16667435"}