{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WQQP4BIWNPPNNU7VIGZ746HM5Q","short_pith_number":"pith:WQQP4BIW","schema_version":"1.0","canonical_sha256":"b420fe05166bded6d3f541b3fe78ecec0281a914b653fa6cd7efaf4af1474341","source":{"kind":"arxiv","id":"2411.12828","version":1},"attestation_state":"computed","paper":{"title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chris Sypherd, Dylan Cashman, Sonny George","submitted_at":"2024-11-19T19:33:16Z","abstract_excerpt":"Large language model (LLM) agents show promise in an increasing number of domains. In many proposed applications, it is expected that the agent reasons over accumulated experience presented in an input prompt. We propose the OEDD (Operationalize Experience Despite Distraction) corpus, a human-annotator-validated body of scenarios with pre-scripted agent histories where the agent must make a decision based on disparate experiential information in the presence of a distractor. We evaluate three state-of-the-art LLMs (GPT-3.5 Turbo, GPT-4o, and Gemini 1.5 Pro) using a minimal chain-of-thought pro"},"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":"2411.12828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-19T19:33:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9cc56703c12a66bea6f5efafb86adf9d544e74fdf7c7b4b6f49ba3f7c97f995c","abstract_canon_sha256":"1b8be30d3b5b1577b563e4373ff2922b658fde30c0d3bf1d2dc988e2b642c897"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:00.887291Z","signature_b64":"72d8+REte2ZtPQZiucaaYCllmIutlRo35fndHcm7e0gPOMe+ab6+f+fTPq+uoe0rnJClgJIuwb63PugrDv7vAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b420fe05166bded6d3f541b3fe78ecec0281a914b653fa6cd7efaf4af1474341","last_reissued_at":"2026-07-05T09:38:00.886788Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:00.886788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chris Sypherd, Dylan Cashman, Sonny George","submitted_at":"2024-11-19T19:33:16Z","abstract_excerpt":"Large language model (LLM) agents show promise in an increasing number of domains. In many proposed applications, it is expected that the agent reasons over accumulated experience presented in an input prompt. We propose the OEDD (Operationalize Experience Despite Distraction) corpus, a human-annotator-validated body of scenarios with pre-scripted agent histories where the agent must make a decision based on disparate experiential information in the presence of a distractor. We evaluate three state-of-the-art LLMs (GPT-3.5 Turbo, GPT-4o, and Gemini 1.5 Pro) using a minimal chain-of-thought pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12828","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/2411.12828/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":"2411.12828","created_at":"2026-07-05T09:38:00.886849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.12828v1","created_at":"2026-07-05T09:38:00.886849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12828","created_at":"2026-07-05T09:38:00.886849+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQQP4BIWNPPN","created_at":"2026-07-05T09:38:00.886849+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQQP4BIWNPPNNU7V","created_at":"2026-07-05T09:38:00.886849+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQQP4BIW","created_at":"2026-07-05T09:38:00.886849+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WQQP4BIWNPPNNU7VIGZ746HM5Q","json":"https://pith.science/pith/WQQP4BIWNPPNNU7VIGZ746HM5Q.json","graph_json":"https://pith.science/api/pith-number/WQQP4BIWNPPNNU7VIGZ746HM5Q/graph.json","events_json":"https://pith.science/api/pith-number/WQQP4BIWNPPNNU7VIGZ746HM5Q/events.json","paper":"https://pith.science/paper/WQQP4BIW"},"agent_actions":{"view_html":"https://pith.science/pith/WQQP4BIWNPPNNU7VIGZ746HM5Q","download_json":"https://pith.science/pith/WQQP4BIWNPPNNU7VIGZ746HM5Q.json","view_paper":"https://pith.science/paper/WQQP4BIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.12828&json=true","fetch_graph":"https://pith.science/api/pith-number/WQQP4BIWNPPNNU7VIGZ746HM5Q/graph.json","fetch_events":"https://pith.science/api/pith-number/WQQP4BIWNPPNNU7VIGZ746HM5Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQQP4BIWNPPNNU7VIGZ746HM5Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQQP4BIWNPPNNU7VIGZ746HM5Q/action/storage_attestation","attest_author":"https://pith.science/pith/WQQP4BIWNPPNNU7VIGZ746HM5Q/action/author_attestation","sign_citation":"https://pith.science/pith/WQQP4BIWNPPNNU7VIGZ746HM5Q/action/citation_signature","submit_replication":"https://pith.science/pith/WQQP4BIWNPPNNU7VIGZ746HM5Q/action/replication_record"}},"created_at":"2026-07-05T09:38:00.886849+00:00","updated_at":"2026-07-05T09:38:00.886849+00:00"}