{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GYKMGRMUI42XBVFOCNNG5YJJKO","short_pith_number":"pith:GYKMGRMU","schema_version":"1.0","canonical_sha256":"3614c34594473570d4ae135a6ee12953bf400d7785f47bb9b005196497d34a7b","source":{"kind":"arxiv","id":"2402.18216","version":2},"attestation_state":"computed","paper":{"title":"LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akash Gupta, Ivaxi Sheth, Mario Fritz, Mark Gales, Vyas Raina","submitted_at":"2024-02-28T10:19:05Z","abstract_excerpt":"With the recent emergence of powerful instruction-tuned large language models (LLMs), various helpful conversational Artificial Intelligence (AI) systems have been deployed across many applications. When prompted by users, these AI systems successfully perform a wide range of tasks as part of a conversation. To provide some sort of memory and context, such approaches typically condition their output on the entire conversational history. Although this sensitivity to the conversational history can often lead to improved performance on subsequent tasks, we find that performance can in fact also b"},"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":"2402.18216","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T10:19:05Z","cross_cats_sorted":[],"title_canon_sha256":"f70004b2922997c557e761cc52f917b3441c75eef413078a3ccc5c3d8507c900","abstract_canon_sha256":"20d04f9a1fc48acb6472cff3afbc07c0ef21c2bb7fcaf90d5901e204ce4518d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:26.845276Z","signature_b64":"hXnq04BXLvsTg2zzLEgyDaXGCnZH2ANEq0OdOeZc/WstIGpm0WXlB8qfLvswmniG/Z0DffAQ/BUjt+N5WqFeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3614c34594473570d4ae135a6ee12953bf400d7785f47bb9b005196497d34a7b","last_reissued_at":"2026-07-05T09:19:26.844806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:26.844806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akash Gupta, Ivaxi Sheth, Mario Fritz, Mark Gales, Vyas Raina","submitted_at":"2024-02-28T10:19:05Z","abstract_excerpt":"With the recent emergence of powerful instruction-tuned large language models (LLMs), various helpful conversational Artificial Intelligence (AI) systems have been deployed across many applications. When prompted by users, these AI systems successfully perform a wide range of tasks as part of a conversation. To provide some sort of memory and context, such approaches typically condition their output on the entire conversational history. Although this sensitivity to the conversational history can often lead to improved performance on subsequent tasks, we find that performance can in fact also b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18216","kind":"arxiv","version":2},"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/2402.18216/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":"2402.18216","created_at":"2026-07-05T09:19:26.844863+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18216v2","created_at":"2026-07-05T09:19:26.844863+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18216","created_at":"2026-07-05T09:19:26.844863+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYKMGRMUI42X","created_at":"2026-07-05T09:19:26.844863+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYKMGRMUI42XBVFO","created_at":"2026-07-05T09:19:26.844863+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYKMGRMU","created_at":"2026-07-05T09:19:26.844863+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26396","citing_title":"At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYKMGRMUI42XBVFOCNNG5YJJKO","json":"https://pith.science/pith/GYKMGRMUI42XBVFOCNNG5YJJKO.json","graph_json":"https://pith.science/api/pith-number/GYKMGRMUI42XBVFOCNNG5YJJKO/graph.json","events_json":"https://pith.science/api/pith-number/GYKMGRMUI42XBVFOCNNG5YJJKO/events.json","paper":"https://pith.science/paper/GYKMGRMU"},"agent_actions":{"view_html":"https://pith.science/pith/GYKMGRMUI42XBVFOCNNG5YJJKO","download_json":"https://pith.science/pith/GYKMGRMUI42XBVFOCNNG5YJJKO.json","view_paper":"https://pith.science/paper/GYKMGRMU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18216&json=true","fetch_graph":"https://pith.science/api/pith-number/GYKMGRMUI42XBVFOCNNG5YJJKO/graph.json","fetch_events":"https://pith.science/api/pith-number/GYKMGRMUI42XBVFOCNNG5YJJKO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYKMGRMUI42XBVFOCNNG5YJJKO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYKMGRMUI42XBVFOCNNG5YJJKO/action/storage_attestation","attest_author":"https://pith.science/pith/GYKMGRMUI42XBVFOCNNG5YJJKO/action/author_attestation","sign_citation":"https://pith.science/pith/GYKMGRMUI42XBVFOCNNG5YJJKO/action/citation_signature","submit_replication":"https://pith.science/pith/GYKMGRMUI42XBVFOCNNG5YJJKO/action/replication_record"}},"created_at":"2026-07-05T09:19:26.844863+00:00","updated_at":"2026-07-05T09:19:26.844863+00:00"}