{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4V27FCUP3D4B3ALCMAMHQYE3BA","short_pith_number":"pith:4V27FCUP","schema_version":"1.0","canonical_sha256":"e575f28a8fd8f81d8162601878609b083f91c1c322fe576589fbad9aefe424f2","source":{"kind":"arxiv","id":"2408.15399","version":1},"attestation_state":"computed","paper":{"title":"A Statistical Framework for Data-dependent Retrieval-Augmented Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Ankit Singh Rawat, Manzil Zaheer, Soumya Basu","submitted_at":"2024-08-27T20:51:06Z","abstract_excerpt":"Modern ML systems increasingly augment input instances with additional relevant information to enhance final prediction. Despite growing interest in such retrieval-augmented models, their fundamental properties and training are not well understood. We propose a statistical framework to study such models with two components: 1) a {\\em retriever} to identify the relevant information out of a large corpus via a data-dependent metric; and 2) a {\\em predictor} that consumes the input instances along with the retrieved information to make the final predictions. We present a principled method for end"},"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":"2408.15399","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-27T20:51:06Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"085f28770fc8b03c7ed2a44dbe98cd38dadf72472d574a2230d06e63987feb58","abstract_canon_sha256":"1ba4cf704338a0f5fb9fd0371820ae192b187bd581a3ad14c0c284cf92aa7d91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:11.216141Z","signature_b64":"FJtQ1WWjMcJ1YA5thoJ8CHpkH4u/Fjqv+MV+wvnKuwtsAqsI6MLkBxzxrl1EJqpu1SgfCsi2dKE2tie7C3CQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e575f28a8fd8f81d8162601878609b083f91c1c322fe576589fbad9aefe424f2","last_reissued_at":"2026-07-05T09:00:11.215634Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:11.215634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Statistical Framework for Data-dependent Retrieval-Augmented Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Ankit Singh Rawat, Manzil Zaheer, Soumya Basu","submitted_at":"2024-08-27T20:51:06Z","abstract_excerpt":"Modern ML systems increasingly augment input instances with additional relevant information to enhance final prediction. Despite growing interest in such retrieval-augmented models, their fundamental properties and training are not well understood. We propose a statistical framework to study such models with two components: 1) a {\\em retriever} to identify the relevant information out of a large corpus via a data-dependent metric; and 2) a {\\em predictor} that consumes the input instances along with the retrieved information to make the final predictions. We present a principled method for end"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15399","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/2408.15399/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":"2408.15399","created_at":"2026-07-05T09:00:11.215693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15399v1","created_at":"2026-07-05T09:00:11.215693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15399","created_at":"2026-07-05T09:00:11.215693+00:00"},{"alias_kind":"pith_short_12","alias_value":"4V27FCUP3D4B","created_at":"2026-07-05T09:00:11.215693+00:00"},{"alias_kind":"pith_short_16","alias_value":"4V27FCUP3D4B3ALC","created_at":"2026-07-05T09:00:11.215693+00:00"},{"alias_kind":"pith_short_8","alias_value":"4V27FCUP","created_at":"2026-07-05T09:00:11.215693+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/4V27FCUP3D4B3ALCMAMHQYE3BA","json":"https://pith.science/pith/4V27FCUP3D4B3ALCMAMHQYE3BA.json","graph_json":"https://pith.science/api/pith-number/4V27FCUP3D4B3ALCMAMHQYE3BA/graph.json","events_json":"https://pith.science/api/pith-number/4V27FCUP3D4B3ALCMAMHQYE3BA/events.json","paper":"https://pith.science/paper/4V27FCUP"},"agent_actions":{"view_html":"https://pith.science/pith/4V27FCUP3D4B3ALCMAMHQYE3BA","download_json":"https://pith.science/pith/4V27FCUP3D4B3ALCMAMHQYE3BA.json","view_paper":"https://pith.science/paper/4V27FCUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15399&json=true","fetch_graph":"https://pith.science/api/pith-number/4V27FCUP3D4B3ALCMAMHQYE3BA/graph.json","fetch_events":"https://pith.science/api/pith-number/4V27FCUP3D4B3ALCMAMHQYE3BA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4V27FCUP3D4B3ALCMAMHQYE3BA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4V27FCUP3D4B3ALCMAMHQYE3BA/action/storage_attestation","attest_author":"https://pith.science/pith/4V27FCUP3D4B3ALCMAMHQYE3BA/action/author_attestation","sign_citation":"https://pith.science/pith/4V27FCUP3D4B3ALCMAMHQYE3BA/action/citation_signature","submit_replication":"https://pith.science/pith/4V27FCUP3D4B3ALCMAMHQYE3BA/action/replication_record"}},"created_at":"2026-07-05T09:00:11.215693+00:00","updated_at":"2026-07-05T09:00:11.215693+00:00"}