{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UQEDKTKYA4A6QB223UV7JNML7U","short_pith_number":"pith:UQEDKTKY","canonical_record":{"source":{"id":"2410.05656","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-08T03:12:57Z","cross_cats_sorted":[],"title_canon_sha256":"98ae627aea0f0328992ec814d56b41e613c1a202ddf9fc4342db09c0d787eba8","abstract_canon_sha256":"29689d1f22172515c9b3a1cb069721b61ff37ae133ac8b6cbc634ab8b90a47f3"},"schema_version":"1.0"},"canonical_sha256":"a408354d580701e8075add2bf4b58bfd2983e7f0a103415d824295d6dfec2ed4","source":{"kind":"arxiv","id":"2410.05656","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.05656","created_at":"2026-07-05T09:17:22Z"},{"alias_kind":"arxiv_version","alias_value":"2410.05656v1","created_at":"2026-07-05T09:17:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05656","created_at":"2026-07-05T09:17:22Z"},{"alias_kind":"pith_short_12","alias_value":"UQEDKTKYA4A6","created_at":"2026-07-05T09:17:22Z"},{"alias_kind":"pith_short_16","alias_value":"UQEDKTKYA4A6QB22","created_at":"2026-07-05T09:17:22Z"},{"alias_kind":"pith_short_8","alias_value":"UQEDKTKY","created_at":"2026-07-05T09:17:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UQEDKTKYA4A6QB223UV7JNML7U","target":"record","payload":{"canonical_record":{"source":{"id":"2410.05656","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-08T03:12:57Z","cross_cats_sorted":[],"title_canon_sha256":"98ae627aea0f0328992ec814d56b41e613c1a202ddf9fc4342db09c0d787eba8","abstract_canon_sha256":"29689d1f22172515c9b3a1cb069721b61ff37ae133ac8b6cbc634ab8b90a47f3"},"schema_version":"1.0"},"canonical_sha256":"a408354d580701e8075add2bf4b58bfd2983e7f0a103415d824295d6dfec2ed4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:22.983018Z","signature_b64":"vT8oxFtjQ1baUCB0IpeG+hltzTIwhHDoyytzxm09GySvBQFLHaLRtyqsf8I4MbEe98JvjAed8NTMX6X4+e8sBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a408354d580701e8075add2bf4b58bfd2983e7f0a103415d824295d6dfec2ed4","last_reissued_at":"2026-07-05T09:17:22.982559Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:22.982559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.05656","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:17:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mkI3PcS7Q/v3ZkBrYFvTjB8ivyjgrMPfF/pju3m+eFkpBx4jLTR2iaBkki9udtkmAezWZsefKZAX9s5B7Q25BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:46:07.142943Z"},"content_sha256":"f3477d8707b72779870aeb6472da9d79a7c82a7d0faa02a395d8b0431212b082","schema_version":"1.0","event_id":"sha256:f3477d8707b72779870aeb6472da9d79a7c82a7d0faa02a395d8b0431212b082"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UQEDKTKYA4A6QB223UV7JNML7U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Modeling Capabilities of Large Language Models for Sequential Decision Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander Toshev, Bogdan Mazoure, Devon Hjelm, Martin Klissarov","submitted_at":"2024-10-08T03:12:57Z","abstract_excerpt":"Large pretrained models are showing increasingly better performance in reasoning and planning tasks across different modalities, opening the possibility to leverage them for complex sequential decision making problems. In this paper, we investigate the capabilities of Large Language Models (LLMs) for reinforcement learning (RL) across a diversity of interactive domains. We evaluate their ability to produce decision-making policies, either directly, by generating actions, or indirectly, by first generating reward models to train an agent with RL. Our results show that, even without task-specifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05656","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/2410.05656/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:17:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DSVcYax5MtYGjvFiyBWFpJNXMz4joWNEDD03qJEPEUNbJqSd2ZljrHJjc1ZbX2U0Dg30a7PNkahEMay221H7Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:46:07.143594Z"},"content_sha256":"e51a5d0de1081d775e8d0770349717f3710a5752059a039684ccbb49c6c05514","schema_version":"1.0","event_id":"sha256:e51a5d0de1081d775e8d0770349717f3710a5752059a039684ccbb49c6c05514"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UQEDKTKYA4A6QB223UV7JNML7U/bundle.json","state_url":"https://pith.science/pith/UQEDKTKYA4A6QB223UV7JNML7U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UQEDKTKYA4A6QB223UV7JNML7U/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T01:46:07Z","links":{"resolver":"https://pith.science/pith/UQEDKTKYA4A6QB223UV7JNML7U","bundle":"https://pith.science/pith/UQEDKTKYA4A6QB223UV7JNML7U/bundle.json","state":"https://pith.science/pith/UQEDKTKYA4A6QB223UV7JNML7U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UQEDKTKYA4A6QB223UV7JNML7U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UQEDKTKYA4A6QB223UV7JNML7U","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":"29689d1f22172515c9b3a1cb069721b61ff37ae133ac8b6cbc634ab8b90a47f3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-08T03:12:57Z","title_canon_sha256":"98ae627aea0f0328992ec814d56b41e613c1a202ddf9fc4342db09c0d787eba8"},"schema_version":"1.0","source":{"id":"2410.05656","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.05656","created_at":"2026-07-05T09:17:22Z"},{"alias_kind":"arxiv_version","alias_value":"2410.05656v1","created_at":"2026-07-05T09:17:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05656","created_at":"2026-07-05T09:17:22Z"},{"alias_kind":"pith_short_12","alias_value":"UQEDKTKYA4A6","created_at":"2026-07-05T09:17:22Z"},{"alias_kind":"pith_short_16","alias_value":"UQEDKTKYA4A6QB22","created_at":"2026-07-05T09:17:22Z"},{"alias_kind":"pith_short_8","alias_value":"UQEDKTKY","created_at":"2026-07-05T09:17:22Z"}],"graph_snapshots":[{"event_id":"sha256:e51a5d0de1081d775e8d0770349717f3710a5752059a039684ccbb49c6c05514","target":"graph","created_at":"2026-07-05T09:17:22Z","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/2410.05656/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large pretrained models are showing increasingly better performance in reasoning and planning tasks across different modalities, opening the possibility to leverage them for complex sequential decision making problems. In this paper, we investigate the capabilities of Large Language Models (LLMs) for reinforcement learning (RL) across a diversity of interactive domains. We evaluate their ability to produce decision-making policies, either directly, by generating actions, or indirectly, by first generating reward models to train an agent with RL. Our results show that, even without task-specifi","authors_text":"Alexander Toshev, Bogdan Mazoure, Devon Hjelm, Martin Klissarov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-08T03:12:57Z","title":"On the Modeling Capabilities of Large Language Models for Sequential Decision Making"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05656","kind":"arxiv","version":1},"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:f3477d8707b72779870aeb6472da9d79a7c82a7d0faa02a395d8b0431212b082","target":"record","created_at":"2026-07-05T09:17:22Z","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":"29689d1f22172515c9b3a1cb069721b61ff37ae133ac8b6cbc634ab8b90a47f3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-08T03:12:57Z","title_canon_sha256":"98ae627aea0f0328992ec814d56b41e613c1a202ddf9fc4342db09c0d787eba8"},"schema_version":"1.0","source":{"id":"2410.05656","kind":"arxiv","version":1}},"canonical_sha256":"a408354d580701e8075add2bf4b58bfd2983e7f0a103415d824295d6dfec2ed4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a408354d580701e8075add2bf4b58bfd2983e7f0a103415d824295d6dfec2ed4","first_computed_at":"2026-07-05T09:17:22.982559Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:22.982559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vT8oxFtjQ1baUCB0IpeG+hltzTIwhHDoyytzxm09GySvBQFLHaLRtyqsf8I4MbEe98JvjAed8NTMX6X4+e8sBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:22.983018Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.05656","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3477d8707b72779870aeb6472da9d79a7c82a7d0faa02a395d8b0431212b082","sha256:e51a5d0de1081d775e8d0770349717f3710a5752059a039684ccbb49c6c05514"],"state_sha256":"98f0dfda80d59d90a8e122a2d51c1ef6a636031a826afe61fe74e5521d90fb0e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J28t8NZZDg7In1ILvuDFrE8TezUjmRyRkPLCVPqzq6f/dZUSVsIxf74h3JkUBRSfpAICAM/Zfi4nwXjsz1SzAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T01:46:07.150288Z","bundle_sha256":"b5fa7db52afdf6bf43b699e74a02bc9063dcfefd0900cb421433e625e0c39a70"}}