{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DTLARONOBYJFTECB5QQCQEGETR","short_pith_number":"pith:DTLARONO","schema_version":"1.0","canonical_sha256":"1cd608b9ae0e12599041ec202810c49c4f3fb4557a050b3e133719c1ef039793","source":{"kind":"arxiv","id":"2508.21003","version":1},"attestation_state":"computed","paper":{"title":"InSQuAD: In-Context Learning for Efficient Retrieval via Submodular Mutual Information to Enforce Quality and Diversity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anay Majee, Rishabh Iyer, Souradeep Nanda","submitted_at":"2025-08-28T17:04:43Z","abstract_excerpt":"In this paper, we introduce InSQuAD, designed to enhance the performance of In-Context Learning (ICL) models through Submodular Mutual Information} (SMI) enforcing Quality and Diversity among in-context exemplars. InSQuAD achieves this through two principal strategies: First, we model the ICL task as a targeted selection problem and introduce a unified selection strategy based on SMIs which mines relevant yet diverse in-context examples encapsulating the notions of quality and diversity. Secondly, we address a common pitfall in existing retrieval models which model query relevance, often overl"},"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":"2508.21003","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-28T17:04:43Z","cross_cats_sorted":[],"title_canon_sha256":"79cc5034fef657d7978162b8f63e1f8baa1fc3722b603c5c48b01f907e4e660f","abstract_canon_sha256":"3e80b4b599f8755f8ede3e0d7802fc59cc2a23b74b04e02568b2f64a035cba18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:15.042066Z","signature_b64":"e8e0T9VOm71MebFeplMF6DBtPt6OruqgAgzYsCFvZdTXoHu06Le/qoGu1pYT6lkgPr7MUwod7whcGwXUvz+/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cd608b9ae0e12599041ec202810c49c4f3fb4557a050b3e133719c1ef039793","last_reissued_at":"2026-07-05T12:01:15.041567Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:15.041567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InSQuAD: In-Context Learning for Efficient Retrieval via Submodular Mutual Information to Enforce Quality and Diversity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anay Majee, Rishabh Iyer, Souradeep Nanda","submitted_at":"2025-08-28T17:04:43Z","abstract_excerpt":"In this paper, we introduce InSQuAD, designed to enhance the performance of In-Context Learning (ICL) models through Submodular Mutual Information} (SMI) enforcing Quality and Diversity among in-context exemplars. InSQuAD achieves this through two principal strategies: First, we model the ICL task as a targeted selection problem and introduce a unified selection strategy based on SMIs which mines relevant yet diverse in-context examples encapsulating the notions of quality and diversity. Secondly, we address a common pitfall in existing retrieval models which model query relevance, often overl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21003","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/2508.21003/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":"2508.21003","created_at":"2026-07-05T12:01:15.041644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.21003v1","created_at":"2026-07-05T12:01:15.041644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21003","created_at":"2026-07-05T12:01:15.041644+00:00"},{"alias_kind":"pith_short_12","alias_value":"DTLARONOBYJF","created_at":"2026-07-05T12:01:15.041644+00:00"},{"alias_kind":"pith_short_16","alias_value":"DTLARONOBYJFTECB","created_at":"2026-07-05T12:01:15.041644+00:00"},{"alias_kind":"pith_short_8","alias_value":"DTLARONO","created_at":"2026-07-05T12:01:15.041644+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/DTLARONOBYJFTECB5QQCQEGETR","json":"https://pith.science/pith/DTLARONOBYJFTECB5QQCQEGETR.json","graph_json":"https://pith.science/api/pith-number/DTLARONOBYJFTECB5QQCQEGETR/graph.json","events_json":"https://pith.science/api/pith-number/DTLARONOBYJFTECB5QQCQEGETR/events.json","paper":"https://pith.science/paper/DTLARONO"},"agent_actions":{"view_html":"https://pith.science/pith/DTLARONOBYJFTECB5QQCQEGETR","download_json":"https://pith.science/pith/DTLARONOBYJFTECB5QQCQEGETR.json","view_paper":"https://pith.science/paper/DTLARONO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.21003&json=true","fetch_graph":"https://pith.science/api/pith-number/DTLARONOBYJFTECB5QQCQEGETR/graph.json","fetch_events":"https://pith.science/api/pith-number/DTLARONOBYJFTECB5QQCQEGETR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DTLARONOBYJFTECB5QQCQEGETR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DTLARONOBYJFTECB5QQCQEGETR/action/storage_attestation","attest_author":"https://pith.science/pith/DTLARONOBYJFTECB5QQCQEGETR/action/author_attestation","sign_citation":"https://pith.science/pith/DTLARONOBYJFTECB5QQCQEGETR/action/citation_signature","submit_replication":"https://pith.science/pith/DTLARONOBYJFTECB5QQCQEGETR/action/replication_record"}},"created_at":"2026-07-05T12:01:15.041644+00:00","updated_at":"2026-07-05T12:01:15.041644+00:00"}