{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RRXT52GSJ3KWC4YFLNP4FT443U","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":"630f2b452aba73681135c59899db8292c8c00cece8c008c3af58d53be17ddb16","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T11:20:10Z","title_canon_sha256":"220dd92196f97c6f6be7d6bd034d34c6bf128663795a74a2f52e318bbd2aff8d"},"schema_version":"1.0","source":{"id":"2502.06358","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06358","created_at":"2026-07-05T11:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06358v3","created_at":"2026-07-05T11:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06358","created_at":"2026-07-05T11:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"RRXT52GSJ3KW","created_at":"2026-07-05T11:39:07Z"},{"alias_kind":"pith_short_16","alias_value":"RRXT52GSJ3KWC4YF","created_at":"2026-07-05T11:39:07Z"},{"alias_kind":"pith_short_8","alias_value":"RRXT52GS","created_at":"2026-07-05T11:39:07Z"}],"graph_snapshots":[{"event_id":"sha256:9ee27126edaa539b811108b005a880e5dc038a60e3e31c59dc6b31c7fff323e1","target":"graph","created_at":"2026-07-05T11:39:07Z","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/2502.06358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompting has emerged as the dominant paradigm for adapting large, pre-trained transformer-based models to downstream tasks. The Prompting Decision Transformer (PDT) enables large-scale, multi-task offline Reinforcement Learning (RL) pre-training by leveraging stochastic trajectory prompts to identify the target task. However, these prompts are sampled uniformly from expert demonstrations, overlooking a critical limitation: not all prompts are equally informative for differentiating between tasks. This limits generalization and adaptation, especially in low-data or open-world settings where sa","authors_text":"Finn Rietz, Lele Cao, Oleg Smirnov, Sara Karimi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T11:20:10Z","title":"Prompt-Tuning Bandits: Enabling Few-Shot Generalization for Efficient Multi-Task Offline RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06358","kind":"arxiv","version":3},"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":"sha256:8ce80a155cf19ade84b358e60ddf38306b4ef608acbcf1297bb4d8acb658cb2b","target":"record","created_at":"2026-07-05T11:39:07Z","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":"630f2b452aba73681135c59899db8292c8c00cece8c008c3af58d53be17ddb16","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T11:20:10Z","title_canon_sha256":"220dd92196f97c6f6be7d6bd034d34c6bf128663795a74a2f52e318bbd2aff8d"},"schema_version":"1.0","source":{"id":"2502.06358","kind":"arxiv","version":3}},"canonical_sha256":"8c6f3ee8d24ed56173055b5fc2cf9cdd2b33f329b3631c59b8be563c19072eed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c6f3ee8d24ed56173055b5fc2cf9cdd2b33f329b3631c59b8be563c19072eed","first_computed_at":"2026-07-05T11:39:07.586877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:07.586877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NpufKoj6bzH1q0wF8u1gM6nhg7kgCUhxM+A5XKpy8n1dKezlXhfgktUEibcGgmFejwf7Ji1ii96H+XVdPHVWBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:07.587290Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06358","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ce80a155cf19ade84b358e60ddf38306b4ef608acbcf1297bb4d8acb658cb2b","sha256:9ee27126edaa539b811108b005a880e5dc038a60e3e31c59dc6b31c7fff323e1"],"state_sha256":"1569522750211db6e4c3b415fa315bb01aa8833ea0e300f0839942b030a03e56"}