{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PW5WZJPZSDHTTQL6XK74IJEHPB","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":"481741e548063d8741fb7bf6a4f96556448cd1fb4c83638338ec00109261a152","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-20T16:58:55Z","title_canon_sha256":"4516161db04067e898934ded53997f7e772403d9d17a77252714bb4face4ec1e"},"schema_version":"1.0","source":{"id":"2312.13327","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.13327","created_at":"2026-07-05T08:38:35Z"},{"alias_kind":"arxiv_version","alias_value":"2312.13327v6","created_at":"2026-07-05T08:38:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13327","created_at":"2026-07-05T08:38:35Z"},{"alias_kind":"pith_short_12","alias_value":"PW5WZJPZSDHT","created_at":"2026-07-05T08:38:35Z"},{"alias_kind":"pith_short_16","alias_value":"PW5WZJPZSDHTTQL6","created_at":"2026-07-05T08:38:35Z"},{"alias_kind":"pith_short_8","alias_value":"PW5WZJPZ","created_at":"2026-07-05T08:38:35Z"}],"graph_snapshots":[{"event_id":"sha256:9f0bcfa72c153da0305d61afbccad4de5433423e2bba7a7a423a38d0c57e4e88","target":"graph","created_at":"2026-07-05T08:38:35Z","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/2312.13327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, it has been shown that transformers pre-trained on diverse datasets with multi-episode contexts can generalize to new reinforcement learning tasks in-context. A key limitation of previously proposed models is their reliance on a predefined action space size and structure. The introduction of a new action space often requires data re-collection and model re-training, which can be costly for some applications. In our work, we show that it is possible to mitigate this issue by proposing the Headless-AD model that, despite being trained only once, is capable of generalizing to discrete a","authors_text":"Alexander Nikulin, Ilya Zisman, Sergey Kolesnikov, Viacheslav Sinii, Vladislav Kurenkov","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-20T16:58:55Z","title":"In-Context Reinforcement Learning for Variable Action Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13327","kind":"arxiv","version":6},"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:ec64b1f42cc87a3826a7e1ccf42069eea33dc54d02bebaba512c915713293bff","target":"record","created_at":"2026-07-05T08:38:35Z","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":"481741e548063d8741fb7bf6a4f96556448cd1fb4c83638338ec00109261a152","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-20T16:58:55Z","title_canon_sha256":"4516161db04067e898934ded53997f7e772403d9d17a77252714bb4face4ec1e"},"schema_version":"1.0","source":{"id":"2312.13327","kind":"arxiv","version":6}},"canonical_sha256":"7dbb6ca5f990cf39c17ebabfc42487787944cd982772d00289dc6888b2d0f72d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7dbb6ca5f990cf39c17ebabfc42487787944cd982772d00289dc6888b2d0f72d","first_computed_at":"2026-07-05T08:38:35.725369Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:35.725369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eobpxEXWQHInEU+ORlxL7MrtwZkjtlWOupDFBTFRAPNGXOrSO6/IzMfWTFVXAeEyHWc0cObITk3rqy6nK54BAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:35.725859Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.13327","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec64b1f42cc87a3826a7e1ccf42069eea33dc54d02bebaba512c915713293bff","sha256:9f0bcfa72c153da0305d61afbccad4de5433423e2bba7a7a423a38d0c57e4e88"],"state_sha256":"90de1e54cdaa64e9b13ed5ef39a56f8839d571378dfd7cc92f3f31221867ae46"}