{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YMVSPOFEH7CB6YNJU3LIJUV3WD","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":"729204454bbcb795f0f7d7db2d0edbaaaac282821b4ac6f689207f3be42444e3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T18:00:24Z","title_canon_sha256":"1bec916f5978849e271a14adeff0af1b0bbd00a079925e415249c7a2fd122a75"},"schema_version":"1.0","source":{"id":"2607.08837","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08837","created_at":"2026-07-13T00:17:21Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08837v1","created_at":"2026-07-13T00:17:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08837","created_at":"2026-07-13T00:17:21Z"},{"alias_kind":"pith_short_12","alias_value":"YMVSPOFEH7CB","created_at":"2026-07-13T00:17:21Z"},{"alias_kind":"pith_short_16","alias_value":"YMVSPOFEH7CB6YNJ","created_at":"2026-07-13T00:17:21Z"},{"alias_kind":"pith_short_8","alias_value":"YMVSPOFE","created_at":"2026-07-13T00:17:21Z"}],"graph_snapshots":[{"event_id":"sha256:50c511c6ce9d05a7895921757554a9efb7eebdd1091e406facee0ee068914f27","target":"graph","created_at":"2026-07-13T00:17:21Z","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/2607.08837/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject stochasticity in the action space, but such jitter only yields rollouts close to the original. Escaping a weak policy often requires global perturbations that action noise cannot produce. Large language models (LLMs) and vision-language-action (VLA) models offer a pathway: they condition the policy on a natural language prompt, and since the rollout follows from it, modifying the prompt induces global changes. The challenge is finding prompts that induce","authors_text":"David Zhang, John Marangola, Nitish Dashora, Pulkit Agrawal, Raghuram Kowdeed, Richard Li, Ruiyang Luo, Sunshine Jiang, Zhang-Wei Hong","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T18:00:24Z","title":"Prompt-Driven Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08837","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:fed53ef60f87cce4579dcbd8612ad0e496464b28f8aa5980158bc84d2eff923d","target":"record","created_at":"2026-07-13T00:17:21Z","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":"729204454bbcb795f0f7d7db2d0edbaaaac282821b4ac6f689207f3be42444e3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T18:00:24Z","title_canon_sha256":"1bec916f5978849e271a14adeff0af1b0bbd00a079925e415249c7a2fd122a75"},"schema_version":"1.0","source":{"id":"2607.08837","kind":"arxiv","version":1}},"canonical_sha256":"c32b27b8a43fc41f61a9a6d684d2bbb0f4312e532f73f126b7528b7b635b4e19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c32b27b8a43fc41f61a9a6d684d2bbb0f4312e532f73f126b7528b7b635b4e19","first_computed_at":"2026-07-13T00:17:21.050818Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T00:17:21.050818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iU8tmpfg41+H0GfxyumYbZvysY0uxoXXHsf41CqFX63Fk5+TXUC6cASM48Chd/wj3yOG3U4zyTCHIbmT5ayBBg==","signature_status":"signed_v1","signed_at":"2026-07-13T00:17:21.051982Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08837","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fed53ef60f87cce4579dcbd8612ad0e496464b28f8aa5980158bc84d2eff923d","sha256:50c511c6ce9d05a7895921757554a9efb7eebdd1091e406facee0ee068914f27"],"state_sha256":"d152864063f7f6dd3ea61bf6106ebfd1a61887594ade4fd488c34051248f1f25"}