{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:O7GZ4G57JC3I5L37ASZCWCCYO4","short_pith_number":"pith:O7GZ4G57","canonical_record":{"source":{"id":"2405.11422","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-19T01:43:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5852554dce3c6466ed02a9305228a23e0bbbd2aea58f59210cb38ebe2bedbfd3","abstract_canon_sha256":"09cfeccf29d2fd2805e573f58f71bf7c21eeb3d102c7b01be20ec2019b6e3b32"},"schema_version":"1.0"},"canonical_sha256":"77cd9e1bbf48b68eaf7f04b22b085877384b70b19a7eca1c394616f897c86e48","source":{"kind":"arxiv","id":"2405.11422","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11422","created_at":"2026-07-05T08:20:39Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11422v1","created_at":"2026-07-05T08:20:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11422","created_at":"2026-07-05T08:20:39Z"},{"alias_kind":"pith_short_12","alias_value":"O7GZ4G57JC3I","created_at":"2026-07-05T08:20:39Z"},{"alias_kind":"pith_short_16","alias_value":"O7GZ4G57JC3I5L37","created_at":"2026-07-05T08:20:39Z"},{"alias_kind":"pith_short_8","alias_value":"O7GZ4G57","created_at":"2026-07-05T08:20:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:O7GZ4G57JC3I5L37ASZCWCCYO4","target":"record","payload":{"canonical_record":{"source":{"id":"2405.11422","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-19T01:43:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5852554dce3c6466ed02a9305228a23e0bbbd2aea58f59210cb38ebe2bedbfd3","abstract_canon_sha256":"09cfeccf29d2fd2805e573f58f71bf7c21eeb3d102c7b01be20ec2019b6e3b32"},"schema_version":"1.0"},"canonical_sha256":"77cd9e1bbf48b68eaf7f04b22b085877384b70b19a7eca1c394616f897c86e48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:39.148483Z","signature_b64":"lLxJb9tOePOGSOxQqvQaYE71HPZ3s5sd8yH5gQlBwm+k76s88wWRLkCPuVBX1iLVOECp5U2hDg8UrvBe6Bn2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77cd9e1bbf48b68eaf7f04b22b085877384b70b19a7eca1c394616f897c86e48","last_reissued_at":"2026-07-05T08:20:39.148094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:39.148094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.11422","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":"2026-07-05T08:20:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YIpyr57T/x+dEBP2hnFTt4qM7vvIDP6xvWlXD3BEJgTqHEK/TVcruv+NfWPwDCLBJwiPsc0q7Wf3cv10OyesCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:59:21.337658Z"},"content_sha256":"f2ff8fd4ddda5efb51e1c1b8e6efbfbcd2a6b5be42281abe14dc56faeb4d3a6e","schema_version":"1.0","event_id":"sha256:f2ff8fd4ddda5efb51e1c1b8e6efbfbcd2a6b5be42281abe14dc56faeb4d3a6e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:O7GZ4G57JC3I5L37ASZCWCCYO4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models are Biased Reinforcement Learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Nicolas Yax, Stefano Palminteri, William M. Hayes","submitted_at":"2024-05-19T01:43:52Z","abstract_excerpt":"In-context learning enables large language models (LLMs) to perform a variety of tasks, including learning to make reward-maximizing choices in simple bandit tasks. Given their potential use as (autonomous) decision-making agents, it is important to understand how these models perform such reinforcement learning (RL) tasks and the extent to which they are susceptible to biases. Motivated by the fact that, in humans, it has been widely documented that the value of an outcome depends on how it compares to other local outcomes, the present study focuses on whether similar value encoding biases ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11422","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/2405.11422/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":"2026-07-05T08:20:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QSWB9zDSqmbwdSjKv8DjgE2b4eJZNAJ0p33rn2RKlX/aKRM2ZjLmmcisU27W31pllxcykegQ3YQgvJdEw6x0Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:59:21.338200Z"},"content_sha256":"e0a7387a122071497b751df36b52629f94870de52c250499914d09190d97cdb7","schema_version":"1.0","event_id":"sha256:e0a7387a122071497b751df36b52629f94870de52c250499914d09190d97cdb7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O7GZ4G57JC3I5L37ASZCWCCYO4/bundle.json","state_url":"https://pith.science/pith/O7GZ4G57JC3I5L37ASZCWCCYO4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O7GZ4G57JC3I5L37ASZCWCCYO4/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":"2026-08-08T12:59:21Z","links":{"resolver":"https://pith.science/pith/O7GZ4G57JC3I5L37ASZCWCCYO4","bundle":"https://pith.science/pith/O7GZ4G57JC3I5L37ASZCWCCYO4/bundle.json","state":"https://pith.science/pith/O7GZ4G57JC3I5L37ASZCWCCYO4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O7GZ4G57JC3I5L37ASZCWCCYO4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O7GZ4G57JC3I5L37ASZCWCCYO4","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":"09cfeccf29d2fd2805e573f58f71bf7c21eeb3d102c7b01be20ec2019b6e3b32","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-19T01:43:52Z","title_canon_sha256":"5852554dce3c6466ed02a9305228a23e0bbbd2aea58f59210cb38ebe2bedbfd3"},"schema_version":"1.0","source":{"id":"2405.11422","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11422","created_at":"2026-07-05T08:20:39Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11422v1","created_at":"2026-07-05T08:20:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11422","created_at":"2026-07-05T08:20:39Z"},{"alias_kind":"pith_short_12","alias_value":"O7GZ4G57JC3I","created_at":"2026-07-05T08:20:39Z"},{"alias_kind":"pith_short_16","alias_value":"O7GZ4G57JC3I5L37","created_at":"2026-07-05T08:20:39Z"},{"alias_kind":"pith_short_8","alias_value":"O7GZ4G57","created_at":"2026-07-05T08:20:39Z"}],"graph_snapshots":[{"event_id":"sha256:e0a7387a122071497b751df36b52629f94870de52c250499914d09190d97cdb7","target":"graph","created_at":"2026-07-05T08:20:39Z","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/2405.11422/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In-context learning enables large language models (LLMs) to perform a variety of tasks, including learning to make reward-maximizing choices in simple bandit tasks. Given their potential use as (autonomous) decision-making agents, it is important to understand how these models perform such reinforcement learning (RL) tasks and the extent to which they are susceptible to biases. Motivated by the fact that, in humans, it has been widely documented that the value of an outcome depends on how it compares to other local outcomes, the present study focuses on whether similar value encoding biases ap","authors_text":"Nicolas Yax, Stefano Palminteri, William M. Hayes","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-19T01:43:52Z","title":"Large Language Models are Biased Reinforcement Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11422","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:f2ff8fd4ddda5efb51e1c1b8e6efbfbcd2a6b5be42281abe14dc56faeb4d3a6e","target":"record","created_at":"2026-07-05T08:20:39Z","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":"09cfeccf29d2fd2805e573f58f71bf7c21eeb3d102c7b01be20ec2019b6e3b32","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-19T01:43:52Z","title_canon_sha256":"5852554dce3c6466ed02a9305228a23e0bbbd2aea58f59210cb38ebe2bedbfd3"},"schema_version":"1.0","source":{"id":"2405.11422","kind":"arxiv","version":1}},"canonical_sha256":"77cd9e1bbf48b68eaf7f04b22b085877384b70b19a7eca1c394616f897c86e48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77cd9e1bbf48b68eaf7f04b22b085877384b70b19a7eca1c394616f897c86e48","first_computed_at":"2026-07-05T08:20:39.148094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:20:39.148094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lLxJb9tOePOGSOxQqvQaYE71HPZ3s5sd8yH5gQlBwm+k76s88wWRLkCPuVBX1iLVOECp5U2hDg8UrvBe6Bn2AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:20:39.148483Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.11422","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2ff8fd4ddda5efb51e1c1b8e6efbfbcd2a6b5be42281abe14dc56faeb4d3a6e","sha256:e0a7387a122071497b751df36b52629f94870de52c250499914d09190d97cdb7"],"state_sha256":"050df6a7119fb1e2567b09e36f1e4dbb02a6e5862f5ef9726a9bfc8a77ca5177"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eIhp38x2ol7JAe9i/l+Kz5rzjJ7Wbs89OeiATVFAdZUQpBLYQ9iIfxVwivF9ejb2CiGAJm4Mem0Onu+bQLLkBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:59:21.343433Z","bundle_sha256":"195abd4710fbab23994159c29844e276dea028458a0e4c01b19b9ddd1cd5f9e2"}}