{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6XTHJFIUSAK6JYZMJ6BOX4DVQX","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":"0e518e8a9ee16ade47e51ca914d36021d64129a55c0e6c6609595a2b69d0ebd1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-25T21:46:25Z","title_canon_sha256":"9017d2a88bb56196bc6f40ae17cb85e994527a97501f4435b1b82387886163b2"},"schema_version":"1.0","source":{"id":"2410.19982","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.19982","created_at":"2026-07-05T10:57:29Z"},{"alias_kind":"arxiv_version","alias_value":"2410.19982v3","created_at":"2026-07-05T10:57:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19982","created_at":"2026-07-05T10:57:29Z"},{"alias_kind":"pith_short_12","alias_value":"6XTHJFIUSAK6","created_at":"2026-07-05T10:57:29Z"},{"alias_kind":"pith_short_16","alias_value":"6XTHJFIUSAK6JYZM","created_at":"2026-07-05T10:57:29Z"},{"alias_kind":"pith_short_8","alias_value":"6XTHJFIU","created_at":"2026-07-05T10:57:29Z"}],"graph_snapshots":[{"event_id":"sha256:bfe7583bea6d4339bdb7163eb88a2270e402c7667b8c0250e825052370d0514e","target":"graph","created_at":"2026-07-05T10:57:29Z","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/2410.19982/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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, ","authors_text":"Santiago Paternain, Weiqin Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-25T21:46:25Z","title":"Random Policy Enables In-Context Reinforcement Learning within Trust Horizons"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19982","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:e681c564dc615377f2368549625fc2e3acbc268a8c3929a8652ce5b570db90d7","target":"record","created_at":"2026-07-05T10:57:29Z","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":"0e518e8a9ee16ade47e51ca914d36021d64129a55c0e6c6609595a2b69d0ebd1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-25T21:46:25Z","title_canon_sha256":"9017d2a88bb56196bc6f40ae17cb85e994527a97501f4435b1b82387886163b2"},"schema_version":"1.0","source":{"id":"2410.19982","kind":"arxiv","version":3}},"canonical_sha256":"f5e67495149015e4e32c4f82ebf07585eac2ce943ec601bc62bb4fa7ce87c4c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5e67495149015e4e32c4f82ebf07585eac2ce943ec601bc62bb4fa7ce87c4c1","first_computed_at":"2026-07-05T10:57:29.139331Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:57:29.139331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/0QggNh6yS1u2CVPP/4BS3yep/Dy1s+AEj8qm3fUyNv4vQX+oOOgYFvO+R2iUtIHyyPqUpXxsGPrQjJawszgAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:57:29.139896Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.19982","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e681c564dc615377f2368549625fc2e3acbc268a8c3929a8652ce5b570db90d7","sha256:bfe7583bea6d4339bdb7163eb88a2270e402c7667b8c0250e825052370d0514e"],"state_sha256":"126fddb1b4cc5d6c219901ed7be6ae890d7ff4961854baca48f0b0f74f48dd60"}