{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XFVQCI44NMOVPJC4MJYDA5HECU","short_pith_number":"pith:XFVQCI44","schema_version":"1.0","canonical_sha256":"b96b01239c6b1d57a45c62703074e41503db03071d61df43584842a1ce8c67ea","source":{"kind":"arxiv","id":"2607.18603","version":1},"attestation_state":"computed","paper":{"title":"AutoIndex: Learning Representation Programs for Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Andrew Drozdov, Hanna Jiang, Nithya Rajkumar, Ramya Narayanasamy, Sam O'Nuallain, Shreyas Chaudhari","submitted_at":"2026-07-21T00:32:55Z","abstract_excerpt":"We present AutoIndex, a framework for learning representation programs: executable transformations that map raw documents into the representations exposed to a retrieval system. Rather than tuning retrievers, rerankers, or a small set of preprocessing hyperparameters, AutoIndex searches over programs that slice, enrich, normalize, reweight, or reorganize documents before indexing. At each iteration, AutoIndex performs validation-guided program search, in which agents diagnose failures of the current program and synthesize candidate updates, retaining only updates that improve retrieval quality"},"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":"2607.18603","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-21T00:32:55Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"04d9f92ceededba29ad46f739c28d15ef8bb0ba942317c969b8eda4c0e7d0acf","abstract_canon_sha256":"732371762effe1f0c0201049873584e88738ec11e502a0cce16943bc71e63f82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T00:22:56.262791Z","signature_b64":"w/y830GD4eeZZ9mqjr/uQNq+R7f+TYshQbQCjIFXGlAqUQViWWt16Tb3d0cWmTUWY/DEnBoH4HgF27e1EUcaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b96b01239c6b1d57a45c62703074e41503db03071d61df43584842a1ce8c67ea","last_reissued_at":"2026-07-22T00:22:56.262000Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T00:22:56.262000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoIndex: Learning Representation Programs for Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Andrew Drozdov, Hanna Jiang, Nithya Rajkumar, Ramya Narayanasamy, Sam O'Nuallain, Shreyas Chaudhari","submitted_at":"2026-07-21T00:32:55Z","abstract_excerpt":"We present AutoIndex, a framework for learning representation programs: executable transformations that map raw documents into the representations exposed to a retrieval system. Rather than tuning retrievers, rerankers, or a small set of preprocessing hyperparameters, AutoIndex searches over programs that slice, enrich, normalize, reweight, or reorganize documents before indexing. At each iteration, AutoIndex performs validation-guided program search, in which agents diagnose failures of the current program and synthesize candidate updates, retaining only updates that improve retrieval quality"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18603","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/2607.18603/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":"2607.18603","created_at":"2026-07-22T00:22:56.262434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18603v1","created_at":"2026-07-22T00:22:56.262434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18603","created_at":"2026-07-22T00:22:56.262434+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFVQCI44NMOV","created_at":"2026-07-22T00:22:56.262434+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFVQCI44NMOVPJC4","created_at":"2026-07-22T00:22:56.262434+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFVQCI44","created_at":"2026-07-22T00:22:56.262434+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/XFVQCI44NMOVPJC4MJYDA5HECU","json":"https://pith.science/pith/XFVQCI44NMOVPJC4MJYDA5HECU.json","graph_json":"https://pith.science/api/pith-number/XFVQCI44NMOVPJC4MJYDA5HECU/graph.json","events_json":"https://pith.science/api/pith-number/XFVQCI44NMOVPJC4MJYDA5HECU/events.json","paper":"https://pith.science/paper/XFVQCI44"},"agent_actions":{"view_html":"https://pith.science/pith/XFVQCI44NMOVPJC4MJYDA5HECU","download_json":"https://pith.science/pith/XFVQCI44NMOVPJC4MJYDA5HECU.json","view_paper":"https://pith.science/paper/XFVQCI44","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18603&json=true","fetch_graph":"https://pith.science/api/pith-number/XFVQCI44NMOVPJC4MJYDA5HECU/graph.json","fetch_events":"https://pith.science/api/pith-number/XFVQCI44NMOVPJC4MJYDA5HECU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFVQCI44NMOVPJC4MJYDA5HECU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFVQCI44NMOVPJC4MJYDA5HECU/action/storage_attestation","attest_author":"https://pith.science/pith/XFVQCI44NMOVPJC4MJYDA5HECU/action/author_attestation","sign_citation":"https://pith.science/pith/XFVQCI44NMOVPJC4MJYDA5HECU/action/citation_signature","submit_replication":"https://pith.science/pith/XFVQCI44NMOVPJC4MJYDA5HECU/action/replication_record"}},"created_at":"2026-07-22T00:22:56.262434+00:00","updated_at":"2026-07-22T00:22:56.262434+00:00"}