{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:74AVWBUNDHXWHVCBFIZTAD2KYK","short_pith_number":"pith:74AVWBUN","schema_version":"1.0","canonical_sha256":"ff015b068d19ef63d4412a33300f4ac2b547388649a59ced859a2663f01a8274","source":{"kind":"arxiv","id":"2312.03801","version":1},"attestation_state":"computed","paper":{"title":"Generalization to New Sequential Decision Making Tasks with In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eric Hambro, Mikael Henaff, Roberta Raileanu, Robert Kirk, Sharath Chandra Raparthy","submitted_at":"2023-12-06T15:19:28Z","abstract_excerpt":"Training autonomous agents that can learn new tasks from only a handful of demonstrations is a long-standing problem in machine learning. Recently, transformers have been shown to learn new language or vision tasks without any weight updates from only a few examples, also referred to as in-context learning. However, the sequential decision making setting poses additional challenges having a lower tolerance for errors since the environment's stochasticity or the agent's actions can lead to unseen, and sometimes unrecoverable, states. In this paper, we use an illustrative example to show that na"},"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":"2312.03801","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-06T15:19:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8ed18de0d218f0bd23edecc7700331d48576f255c91f0a601618832cf39221b0","abstract_canon_sha256":"cc75585145b17da3f3da705068e915d670377b46686571e67f7c5b8b9b811a9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:15.220960Z","signature_b64":"+DdIITAESvuh4pR+qClcYXY0ZaavdVlx6BOwEb5tfl2J8DI2wiBxrOwYoFqrFaaAaRGdrAxR8RQWy78OXP4RBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff015b068d19ef63d4412a33300f4ac2b547388649a59ced859a2663f01a8274","last_reissued_at":"2026-07-05T07:21:15.220425Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:15.220425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization to New Sequential Decision Making Tasks with In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eric Hambro, Mikael Henaff, Roberta Raileanu, Robert Kirk, Sharath Chandra Raparthy","submitted_at":"2023-12-06T15:19:28Z","abstract_excerpt":"Training autonomous agents that can learn new tasks from only a handful of demonstrations is a long-standing problem in machine learning. Recently, transformers have been shown to learn new language or vision tasks without any weight updates from only a few examples, also referred to as in-context learning. However, the sequential decision making setting poses additional challenges having a lower tolerance for errors since the environment's stochasticity or the agent's actions can lead to unseen, and sometimes unrecoverable, states. In this paper, we use an illustrative example to show that na"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03801","kind":"arxiv","version":1},"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/2312.03801/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":"2312.03801","created_at":"2026-07-05T07:21:15.220484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03801v1","created_at":"2026-07-05T07:21:15.220484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03801","created_at":"2026-07-05T07:21:15.220484+00:00"},{"alias_kind":"pith_short_12","alias_value":"74AVWBUNDHXW","created_at":"2026-07-05T07:21:15.220484+00:00"},{"alias_kind":"pith_short_16","alias_value":"74AVWBUNDHXWHVCB","created_at":"2026-07-05T07:21:15.220484+00:00"},{"alias_kind":"pith_short_8","alias_value":"74AVWBUN","created_at":"2026-07-05T07:21:15.220484+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24962","citing_title":"Towards Scalable Multi-Task Reinforcement Learning with Large Decision Models","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/74AVWBUNDHXWHVCBFIZTAD2KYK","json":"https://pith.science/pith/74AVWBUNDHXWHVCBFIZTAD2KYK.json","graph_json":"https://pith.science/api/pith-number/74AVWBUNDHXWHVCBFIZTAD2KYK/graph.json","events_json":"https://pith.science/api/pith-number/74AVWBUNDHXWHVCBFIZTAD2KYK/events.json","paper":"https://pith.science/paper/74AVWBUN"},"agent_actions":{"view_html":"https://pith.science/pith/74AVWBUNDHXWHVCBFIZTAD2KYK","download_json":"https://pith.science/pith/74AVWBUNDHXWHVCBFIZTAD2KYK.json","view_paper":"https://pith.science/paper/74AVWBUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03801&json=true","fetch_graph":"https://pith.science/api/pith-number/74AVWBUNDHXWHVCBFIZTAD2KYK/graph.json","fetch_events":"https://pith.science/api/pith-number/74AVWBUNDHXWHVCBFIZTAD2KYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74AVWBUNDHXWHVCBFIZTAD2KYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74AVWBUNDHXWHVCBFIZTAD2KYK/action/storage_attestation","attest_author":"https://pith.science/pith/74AVWBUNDHXWHVCBFIZTAD2KYK/action/author_attestation","sign_citation":"https://pith.science/pith/74AVWBUNDHXWHVCBFIZTAD2KYK/action/citation_signature","submit_replication":"https://pith.science/pith/74AVWBUNDHXWHVCBFIZTAD2KYK/action/replication_record"}},"created_at":"2026-07-05T07:21:15.220484+00:00","updated_at":"2026-07-05T07:21:15.220484+00:00"}