{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4AUCRGN2RLLSHUP325XPDY4SMR","short_pith_number":"pith:4AUCRGN2","schema_version":"1.0","canonical_sha256":"e0282899ba8ad723d1fbd76ef1e392647d205bb4aa5a827ff014fcbd847c9b25","source":{"kind":"arxiv","id":"2608.12569","version":1},"attestation_state":"computed","paper":{"title":"Test-Time Optimization of Query Embeddings with Ranking Aware Reward Maximization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jiaxing Wu, Tianyu Chen","submitted_at":"2026-08-12T20:24:57Z","abstract_excerpt":"Dense retrievers rank documents using vector similarity between a frozen encoder and a precomputed index. While test-time ranking rewards from a reranker or LLM judge can improve results, existing methods discard this signal after a single query. Updating the retriever's weights makes rewards reusable, but this requires parameter access, which is unavailable for closed-source models, and is computationally prohibitive. We propose TTT-Embed (Test-Time Tuning of Embeddings), a framework that distills ranking rewards into a lightweight, learned vector within the output embedding space of a frozen"},"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":"2608.12569","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-12T20:24:57Z","cross_cats_sorted":[],"title_canon_sha256":"e490ce405ef5722fd799da810d01f7d9664b3f2c2407c22f02c92087f37453ed","abstract_canon_sha256":"195c7a0d38e6c4db10a4e6d4019fbd3203b1c893adff1657b47f0846a61e899a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T00:45:11.696662Z","signature_b64":"sPSdkax5EY7utyA5A1UfoFfIyQfOtQ7QOoPx+KbNcVROurWrUmbh98eVHmfDx66iM5d3B2kRYLzAOro9G4ciCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0282899ba8ad723d1fbd76ef1e392647d205bb4aa5a827ff014fcbd847c9b25","last_reissued_at":"2026-08-14T00:45:11.685494Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T00:45:11.685494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Test-Time Optimization of Query Embeddings with Ranking Aware Reward Maximization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jiaxing Wu, Tianyu Chen","submitted_at":"2026-08-12T20:24:57Z","abstract_excerpt":"Dense retrievers rank documents using vector similarity between a frozen encoder and a precomputed index. While test-time ranking rewards from a reranker or LLM judge can improve results, existing methods discard this signal after a single query. Updating the retriever's weights makes rewards reusable, but this requires parameter access, which is unavailable for closed-source models, and is computationally prohibitive. We propose TTT-Embed (Test-Time Tuning of Embeddings), a framework that distills ranking rewards into a lightweight, learned vector within the output embedding space of a frozen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12569","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/2608.12569/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":"2608.12569","created_at":"2026-08-14T00:45:11.688187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.12569v1","created_at":"2026-08-14T00:45:11.688187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12569","created_at":"2026-08-14T00:45:11.688187+00:00"},{"alias_kind":"pith_short_12","alias_value":"4AUCRGN2RLLS","created_at":"2026-08-14T00:45:11.688187+00:00"},{"alias_kind":"pith_short_16","alias_value":"4AUCRGN2RLLSHUP3","created_at":"2026-08-14T00:45:11.688187+00:00"},{"alias_kind":"pith_short_8","alias_value":"4AUCRGN2","created_at":"2026-08-14T00:45:11.688187+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/4AUCRGN2RLLSHUP325XPDY4SMR","json":"https://pith.science/pith/4AUCRGN2RLLSHUP325XPDY4SMR.json","graph_json":"https://pith.science/api/pith-number/4AUCRGN2RLLSHUP325XPDY4SMR/graph.json","events_json":"https://pith.science/api/pith-number/4AUCRGN2RLLSHUP325XPDY4SMR/events.json","paper":"https://pith.science/paper/4AUCRGN2"},"agent_actions":{"view_html":"https://pith.science/pith/4AUCRGN2RLLSHUP325XPDY4SMR","download_json":"https://pith.science/pith/4AUCRGN2RLLSHUP325XPDY4SMR.json","view_paper":"https://pith.science/paper/4AUCRGN2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.12569&json=true","fetch_graph":"https://pith.science/api/pith-number/4AUCRGN2RLLSHUP325XPDY4SMR/graph.json","fetch_events":"https://pith.science/api/pith-number/4AUCRGN2RLLSHUP325XPDY4SMR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4AUCRGN2RLLSHUP325XPDY4SMR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4AUCRGN2RLLSHUP325XPDY4SMR/action/storage_attestation","attest_author":"https://pith.science/pith/4AUCRGN2RLLSHUP325XPDY4SMR/action/author_attestation","sign_citation":"https://pith.science/pith/4AUCRGN2RLLSHUP325XPDY4SMR/action/citation_signature","submit_replication":"https://pith.science/pith/4AUCRGN2RLLSHUP325XPDY4SMR/action/replication_record"}},"created_at":"2026-08-14T00:45:11.688187+00:00","updated_at":"2026-08-14T00:45:11.688187+00:00"}