{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RRXT52GSJ3KWC4YFLNP4FT443U","short_pith_number":"pith:RRXT52GS","schema_version":"1.0","canonical_sha256":"8c6f3ee8d24ed56173055b5fc2cf9cdd2b33f329b3631c59b8be563c19072eed","source":{"kind":"arxiv","id":"2502.06358","version":3},"attestation_state":"computed","paper":{"title":"Prompt-Tuning Bandits: Enabling Few-Shot Generalization for Efficient Multi-Task Offline RL","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Finn Rietz, Lele Cao, Oleg Smirnov, Sara Karimi","submitted_at":"2025-02-10T11:20:10Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.06358","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T11:20:10Z","cross_cats_sorted":[],"title_canon_sha256":"220dd92196f97c6f6be7d6bd034d34c6bf128663795a74a2f52e318bbd2aff8d","abstract_canon_sha256":"630f2b452aba73681135c59899db8292c8c00cece8c008c3af58d53be17ddb16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:07.587290Z","signature_b64":"NpufKoj6bzH1q0wF8u1gM6nhg7kgCUhxM+A5XKpy8n1dKezlXhfgktUEibcGgmFejwf7Ji1ii96H+XVdPHVWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c6f3ee8d24ed56173055b5fc2cf9cdd2b33f329b3631c59b8be563c19072eed","last_reissued_at":"2026-07-05T11:39:07.586877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:07.586877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt-Tuning Bandits: Enabling Few-Shot Generalization for Efficient Multi-Task Offline RL","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Finn Rietz, Lele Cao, Oleg Smirnov, Sara Karimi","submitted_at":"2025-02-10T11:20:10Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06358","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.06358/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.06358","created_at":"2026-07-05T11:39:07.586929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06358v3","created_at":"2026-07-05T11:39:07.586929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06358","created_at":"2026-07-05T11:39:07.586929+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRXT52GSJ3KW","created_at":"2026-07-05T11:39:07.586929+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRXT52GSJ3KWC4YF","created_at":"2026-07-05T11:39:07.586929+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRXT52GS","created_at":"2026-07-05T11:39:07.586929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RRXT52GSJ3KWC4YFLNP4FT443U","json":"https://pith.science/pith/RRXT52GSJ3KWC4YFLNP4FT443U.json","graph_json":"https://pith.science/api/pith-number/RRXT52GSJ3KWC4YFLNP4FT443U/graph.json","events_json":"https://pith.science/api/pith-number/RRXT52GSJ3KWC4YFLNP4FT443U/events.json","paper":"https://pith.science/paper/RRXT52GS"},"agent_actions":{"view_html":"https://pith.science/pith/RRXT52GSJ3KWC4YFLNP4FT443U","download_json":"https://pith.science/pith/RRXT52GSJ3KWC4YFLNP4FT443U.json","view_paper":"https://pith.science/paper/RRXT52GS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06358&json=true","fetch_graph":"https://pith.science/api/pith-number/RRXT52GSJ3KWC4YFLNP4FT443U/graph.json","fetch_events":"https://pith.science/api/pith-number/RRXT52GSJ3KWC4YFLNP4FT443U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRXT52GSJ3KWC4YFLNP4FT443U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRXT52GSJ3KWC4YFLNP4FT443U/action/storage_attestation","attest_author":"https://pith.science/pith/RRXT52GSJ3KWC4YFLNP4FT443U/action/author_attestation","sign_citation":"https://pith.science/pith/RRXT52GSJ3KWC4YFLNP4FT443U/action/citation_signature","submit_replication":"https://pith.science/pith/RRXT52GSJ3KWC4YFLNP4FT443U/action/replication_record"}},"created_at":"2026-07-05T11:39:07.586929+00:00","updated_at":"2026-07-05T11:39:07.586929+00:00"}