{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6XTHJFIUSAK6JYZMJ6BOX4DVQX","short_pith_number":"pith:6XTHJFIU","schema_version":"1.0","canonical_sha256":"f5e67495149015e4e32c4f82ebf07585eac2ce943ec601bc62bb4fa7ce87c4c1","source":{"kind":"arxiv","id":"2410.19982","version":3},"attestation_state":"computed","paper":{"title":"Random Policy Enables In-Context Reinforcement Learning within Trust Horizons","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Santiago Paternain, Weiqin Chen","submitted_at":"2024-10-25T21:46:25Z","abstract_excerpt":"Pretrained foundation models have exhibited extraordinary in-context learning performance, allowing zero-shot generalization to new tasks not encountered during pretraining. In the case of reinforcement learning (RL), in-context RL (ICRL) emerges when pretraining FMs on decision-making problems in an autoregressive-supervised manner. Nevertheless, current state-of-the-art ICRL algorithms, like Algorithm Distillation, Decision Pretrained Transformer and Decision Importance Transformer, impose stringent requirements on the pretraining dataset concerning the source policies, context information, "},"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":"2410.19982","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-25T21:46:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9017d2a88bb56196bc6f40ae17cb85e994527a97501f4435b1b82387886163b2","abstract_canon_sha256":"0e518e8a9ee16ade47e51ca914d36021d64129a55c0e6c6609595a2b69d0ebd1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:29.139896Z","signature_b64":"/0QggNh6yS1u2CVPP/4BS3yep/Dy1s+AEj8qm3fUyNv4vQX+oOOgYFvO+R2iUtIHyyPqUpXxsGPrQjJawszgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5e67495149015e4e32c4f82ebf07585eac2ce943ec601bc62bb4fa7ce87c4c1","last_reissued_at":"2026-07-05T10:57:29.139331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:29.139331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Random Policy Enables In-Context Reinforcement Learning within Trust Horizons","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Santiago Paternain, Weiqin Chen","submitted_at":"2024-10-25T21:46:25Z","abstract_excerpt":"Pretrained foundation models have exhibited extraordinary in-context learning performance, allowing zero-shot generalization to new tasks not encountered during pretraining. In the case of reinforcement learning (RL), in-context RL (ICRL) emerges when pretraining FMs on decision-making problems in an autoregressive-supervised manner. Nevertheless, current state-of-the-art ICRL algorithms, like Algorithm Distillation, Decision Pretrained Transformer and Decision Importance Transformer, impose stringent requirements on the pretraining dataset concerning the source policies, context information, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19982","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/2410.19982/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":"2410.19982","created_at":"2026-07-05T10:57:29.139391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.19982v3","created_at":"2026-07-05T10:57:29.139391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19982","created_at":"2026-07-05T10:57:29.139391+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XTHJFIUSAK6","created_at":"2026-07-05T10:57:29.139391+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XTHJFIUSAK6JYZM","created_at":"2026-07-05T10:57:29.139391+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XTHJFIU","created_at":"2026-07-05T10:57:29.139391+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/6XTHJFIUSAK6JYZMJ6BOX4DVQX","json":"https://pith.science/pith/6XTHJFIUSAK6JYZMJ6BOX4DVQX.json","graph_json":"https://pith.science/api/pith-number/6XTHJFIUSAK6JYZMJ6BOX4DVQX/graph.json","events_json":"https://pith.science/api/pith-number/6XTHJFIUSAK6JYZMJ6BOX4DVQX/events.json","paper":"https://pith.science/paper/6XTHJFIU"},"agent_actions":{"view_html":"https://pith.science/pith/6XTHJFIUSAK6JYZMJ6BOX4DVQX","download_json":"https://pith.science/pith/6XTHJFIUSAK6JYZMJ6BOX4DVQX.json","view_paper":"https://pith.science/paper/6XTHJFIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.19982&json=true","fetch_graph":"https://pith.science/api/pith-number/6XTHJFIUSAK6JYZMJ6BOX4DVQX/graph.json","fetch_events":"https://pith.science/api/pith-number/6XTHJFIUSAK6JYZMJ6BOX4DVQX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XTHJFIUSAK6JYZMJ6BOX4DVQX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XTHJFIUSAK6JYZMJ6BOX4DVQX/action/storage_attestation","attest_author":"https://pith.science/pith/6XTHJFIUSAK6JYZMJ6BOX4DVQX/action/author_attestation","sign_citation":"https://pith.science/pith/6XTHJFIUSAK6JYZMJ6BOX4DVQX/action/citation_signature","submit_replication":"https://pith.science/pith/6XTHJFIUSAK6JYZMJ6BOX4DVQX/action/replication_record"}},"created_at":"2026-07-05T10:57:29.139391+00:00","updated_at":"2026-07-05T10:57:29.139391+00:00"}