{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AEWYS2RVL3REEYXTZI7DSCHVHW","short_pith_number":"pith:AEWYS2RV","schema_version":"1.0","canonical_sha256":"012d896a355ee24262f3ca3e3908f53db32eb3ce1b11109444cdd37dbef9c6b6","source":{"kind":"arxiv","id":"2605.24989","version":1},"attestation_state":"computed","paper":{"title":"Selective Test-Time Compute Scaling for Click-Through Rate Prediction via Uncertainty-Triggered Feature Path Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Jinxin Hu, Moyu Zhang, Xiaoyi Zeng, Yujun Jin, Yun Chen, Yu Zhang","submitted_at":"2026-05-24T10:29:10Z","abstract_excerpt":"Scaling test-time compute has proven highly effective for language models, yet this opportunity remains largely unexplored for industrial Click-Through Rate (CTR) prediction. CTR models suffer from a fundamental asymmetry: feature combinations well-represented in training yield confident predictions, while sparsely observed ones produce unreliable outputs. Existing training-phase solutions such as adaptive gating learn a fixed selection function subject to the same sparsity, offering no per-instance recourse at deployment.We propose UTTSI (Uncertainty-Triggered Test-Time Selective Inference), "},"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":"2605.24989","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-24T10:29:10Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"fec1d035e3624f76f01c961ffd65ca0108e82a626fd9d9c68716964f347f71d9","abstract_canon_sha256":"6cc60b2b03a138984a1ad6226edaecf322370ea4266503c5c1d82debef5a8d23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:04:09.567986Z","signature_b64":"B0gQ4o4S/cMw/iP2YNaNPhT7S/OAfe+Mbu/zlRA7z3Qf/kvtXwH5V1pNLeXf0lekAcF6YYHjPazk6LzNIxJwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"012d896a355ee24262f3ca3e3908f53db32eb3ce1b11109444cdd37dbef9c6b6","last_reissued_at":"2026-05-26T01:04:09.567226Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:04:09.567226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Selective Test-Time Compute Scaling for Click-Through Rate Prediction via Uncertainty-Triggered Feature Path Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Jinxin Hu, Moyu Zhang, Xiaoyi Zeng, Yujun Jin, Yun Chen, Yu Zhang","submitted_at":"2026-05-24T10:29:10Z","abstract_excerpt":"Scaling test-time compute has proven highly effective for language models, yet this opportunity remains largely unexplored for industrial Click-Through Rate (CTR) prediction. CTR models suffer from a fundamental asymmetry: feature combinations well-represented in training yield confident predictions, while sparsely observed ones produce unreliable outputs. Existing training-phase solutions such as adaptive gating learn a fixed selection function subject to the same sparsity, offering no per-instance recourse at deployment.We propose UTTSI (Uncertainty-Triggered Test-Time Selective Inference), "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24989","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/2605.24989/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":"2605.24989","created_at":"2026-05-26T01:04:09.567368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24989v1","created_at":"2026-05-26T01:04:09.567368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24989","created_at":"2026-05-26T01:04:09.567368+00:00"},{"alias_kind":"pith_short_12","alias_value":"AEWYS2RVL3RE","created_at":"2026-05-26T01:04:09.567368+00:00"},{"alias_kind":"pith_short_16","alias_value":"AEWYS2RVL3REEYXT","created_at":"2026-05-26T01:04:09.567368+00:00"},{"alias_kind":"pith_short_8","alias_value":"AEWYS2RV","created_at":"2026-05-26T01:04:09.567368+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/AEWYS2RVL3REEYXTZI7DSCHVHW","json":"https://pith.science/pith/AEWYS2RVL3REEYXTZI7DSCHVHW.json","graph_json":"https://pith.science/api/pith-number/AEWYS2RVL3REEYXTZI7DSCHVHW/graph.json","events_json":"https://pith.science/api/pith-number/AEWYS2RVL3REEYXTZI7DSCHVHW/events.json","paper":"https://pith.science/paper/AEWYS2RV"},"agent_actions":{"view_html":"https://pith.science/pith/AEWYS2RVL3REEYXTZI7DSCHVHW","download_json":"https://pith.science/pith/AEWYS2RVL3REEYXTZI7DSCHVHW.json","view_paper":"https://pith.science/paper/AEWYS2RV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24989&json=true","fetch_graph":"https://pith.science/api/pith-number/AEWYS2RVL3REEYXTZI7DSCHVHW/graph.json","fetch_events":"https://pith.science/api/pith-number/AEWYS2RVL3REEYXTZI7DSCHVHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AEWYS2RVL3REEYXTZI7DSCHVHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AEWYS2RVL3REEYXTZI7DSCHVHW/action/storage_attestation","attest_author":"https://pith.science/pith/AEWYS2RVL3REEYXTZI7DSCHVHW/action/author_attestation","sign_citation":"https://pith.science/pith/AEWYS2RVL3REEYXTZI7DSCHVHW/action/citation_signature","submit_replication":"https://pith.science/pith/AEWYS2RVL3REEYXTZI7DSCHVHW/action/replication_record"}},"created_at":"2026-05-26T01:04:09.567368+00:00","updated_at":"2026-05-26T01:04:09.567368+00:00"}