{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5Z7KGHKFFPLY6P5YUREKWTSZHB","short_pith_number":"pith:5Z7KGHKF","schema_version":"1.0","canonical_sha256":"ee7ea31d452bd78f3fb8a448ab4e59387ba5283f48d7667bb67c1d09cf057cb8","source":{"kind":"arxiv","id":"2310.02842","version":3},"attestation_state":"computed","paper":{"title":"Sweeping Heterogeneity with Smart MoPs: Mixture of Prompts for LLM Task Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ahmed Hassan Awadallah, Anastasios Kyrillidis, Chen Dun, Guoqing Zheng, Mirian Hipolito Garcia, Robert Sim","submitted_at":"2023-10-04T14:11:12Z","abstract_excerpt":"Large Language Models (LLMs) have the ability to solve a variety of tasks, such as text summarization and mathematical questions, just out of the box, but they are often trained with a single task in mind. Due to high computational costs, the current trend is to use prompt instruction tuning to better adjust monolithic, pretrained LLMs for new -- but often individual -- downstream tasks. Thus, how one would expand prompt tuning to handle -- concomitantly -- heterogeneous tasks and data distributions is a widely open question. To address this gap, we suggest the use of \\emph{Mixture of Prompts}"},"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":"2310.02842","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T14:11:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c52e25fec02785f0b2e966fdfe6d0981e0c629eddd46f5fdfbe1fc761300efff","abstract_canon_sha256":"e8c011a1f80a8627081022dee786950a1f5660eb60ddf0e6624f63ad2b43b0b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:21.631070Z","signature_b64":"PwTior6+zy7mZdfRfx5ae7qYLT2zarljnnWobBRd3YzlqLOtt4CQ721YtT+KlRlN4Hf5NSFHp9fhY9KXeg+BCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee7ea31d452bd78f3fb8a448ab4e59387ba5283f48d7667bb67c1d09cf057cb8","last_reissued_at":"2026-07-05T10:02:21.630415Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:21.630415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sweeping Heterogeneity with Smart MoPs: Mixture of Prompts for LLM Task Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ahmed Hassan Awadallah, Anastasios Kyrillidis, Chen Dun, Guoqing Zheng, Mirian Hipolito Garcia, Robert Sim","submitted_at":"2023-10-04T14:11:12Z","abstract_excerpt":"Large Language Models (LLMs) have the ability to solve a variety of tasks, such as text summarization and mathematical questions, just out of the box, but they are often trained with a single task in mind. Due to high computational costs, the current trend is to use prompt instruction tuning to better adjust monolithic, pretrained LLMs for new -- but often individual -- downstream tasks. Thus, how one would expand prompt tuning to handle -- concomitantly -- heterogeneous tasks and data distributions is a widely open question. To address this gap, we suggest the use of \\emph{Mixture of Prompts}"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02842","kind":"arxiv","version":3},"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/2310.02842/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":"2310.02842","created_at":"2026-07-05T10:02:21.630513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.02842v3","created_at":"2026-07-05T10:02:21.630513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02842","created_at":"2026-07-05T10:02:21.630513+00:00"},{"alias_kind":"pith_short_12","alias_value":"5Z7KGHKFFPLY","created_at":"2026-07-05T10:02:21.630513+00:00"},{"alias_kind":"pith_short_16","alias_value":"5Z7KGHKFFPLY6P5Y","created_at":"2026-07-05T10:02:21.630513+00:00"},{"alias_kind":"pith_short_8","alias_value":"5Z7KGHKF","created_at":"2026-07-05T10:02:21.630513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20638","citing_title":"RIZZ: Routing Interactions to Near Zero-Interference Zones for Continual Adaptation of Black-Box Agents","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5Z7KGHKFFPLY6P5YUREKWTSZHB","json":"https://pith.science/pith/5Z7KGHKFFPLY6P5YUREKWTSZHB.json","graph_json":"https://pith.science/api/pith-number/5Z7KGHKFFPLY6P5YUREKWTSZHB/graph.json","events_json":"https://pith.science/api/pith-number/5Z7KGHKFFPLY6P5YUREKWTSZHB/events.json","paper":"https://pith.science/paper/5Z7KGHKF"},"agent_actions":{"view_html":"https://pith.science/pith/5Z7KGHKFFPLY6P5YUREKWTSZHB","download_json":"https://pith.science/pith/5Z7KGHKFFPLY6P5YUREKWTSZHB.json","view_paper":"https://pith.science/paper/5Z7KGHKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.02842&json=true","fetch_graph":"https://pith.science/api/pith-number/5Z7KGHKFFPLY6P5YUREKWTSZHB/graph.json","fetch_events":"https://pith.science/api/pith-number/5Z7KGHKFFPLY6P5YUREKWTSZHB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5Z7KGHKFFPLY6P5YUREKWTSZHB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5Z7KGHKFFPLY6P5YUREKWTSZHB/action/storage_attestation","attest_author":"https://pith.science/pith/5Z7KGHKFFPLY6P5YUREKWTSZHB/action/author_attestation","sign_citation":"https://pith.science/pith/5Z7KGHKFFPLY6P5YUREKWTSZHB/action/citation_signature","submit_replication":"https://pith.science/pith/5Z7KGHKFFPLY6P5YUREKWTSZHB/action/replication_record"}},"created_at":"2026-07-05T10:02:21.630513+00:00","updated_at":"2026-07-05T10:02:21.630513+00:00"}