{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4ZPHELSI2MTYHWQNZLXKQSFSFQ","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":"a756a1c63e02b476a1166d9aad848e6219dbecd2293b3235ad4d84bce833c5c1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T08:55:24Z","title_canon_sha256":"c90fca16da114a26b65c1c04697471aea809fc3db506c9e5b892ad11156c4149"},"schema_version":"1.0","source":{"id":"2606.29980","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29980","created_at":"2026-06-30T02:17:43Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29980v1","created_at":"2026-06-30T02:17:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29980","created_at":"2026-06-30T02:17:43Z"},{"alias_kind":"pith_short_12","alias_value":"4ZPHELSI2MTY","created_at":"2026-06-30T02:17:43Z"},{"alias_kind":"pith_short_16","alias_value":"4ZPHELSI2MTYHWQN","created_at":"2026-06-30T02:17:43Z"},{"alias_kind":"pith_short_8","alias_value":"4ZPHELSI","created_at":"2026-06-30T02:17:43Z"}],"graph_snapshots":[{"event_id":"sha256:dc3b3ca2db48075a57bfb5e8d344ad826a8c12ed66b7e4f5691055efb61c6c38","target":"graph","created_at":"2026-06-30T02:17:43Z","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/2606.29980/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot Transfer in Reinforcement Learning (RL) aims to train an agent that can generate optimal policies for any reward function, without additional learning at transfer time, while training only on reward-free trajectories. For their generality over tasks, such models are sometimes called ``Behavioral Foundation Models'' (BFMs). While they have shown strong performances and improvements in recent years, the current framework and algorithms still assume that, during the transfer phase, the agent is informed offline about the reward (the task to solve) through a dataset of state-reward pairs","authors_text":"IRISA, La\\\"etitia Matignon (SyCoSMA), Louis Bagot (SyCoSMA), MALT, Mathieu Lefort (LIRIS, SyCoSMA, UR)","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T08:55:24Z","title":"Exploration and Online Transfer with Behavioral Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29980","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":"sha256:1084f6e07791b480a1d0e48ca7885017d5633469b2874f5d44a9cf2deff7fa7b","target":"record","created_at":"2026-06-30T02:17:43Z","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":"a756a1c63e02b476a1166d9aad848e6219dbecd2293b3235ad4d84bce833c5c1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T08:55:24Z","title_canon_sha256":"c90fca16da114a26b65c1c04697471aea809fc3db506c9e5b892ad11156c4149"},"schema_version":"1.0","source":{"id":"2606.29980","kind":"arxiv","version":1}},"canonical_sha256":"e65e722e48d32783da0dcaeea848b22c1415e267e99f4d8ee7e9f2d9f3a02473","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e65e722e48d32783da0dcaeea848b22c1415e267e99f4d8ee7e9f2d9f3a02473","first_computed_at":"2026-06-30T02:17:43.883154Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:43.883154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8YhDTVvi9CpYqUhT9mQXgffTEHhXTtuHJ8Lj6Auw8V2bNyvSJCfS281cbqWGqVnnnYKzhdp/RPDnUfdtQxAIBQ==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:43.883762Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29980","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1084f6e07791b480a1d0e48ca7885017d5633469b2874f5d44a9cf2deff7fa7b","sha256:dc3b3ca2db48075a57bfb5e8d344ad826a8c12ed66b7e4f5691055efb61c6c38"],"state_sha256":"2f45302ea24768c1c027065b7aa1374e28fcdb58ed349e2e0db2b387600b5444"}