{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JBKCM2VYWRB3AF4QZUN5RKR7I2","short_pith_number":"pith:JBKCM2VY","schema_version":"1.0","canonical_sha256":"4854266ab8b443b01790cd1bd8aa3f46944599716b66d59b23326d1d8d0cb678","source":{"kind":"arxiv","id":"2606.08466","version":1},"attestation_state":"computed","paper":{"title":"ToolRec: Calibrated Preference Alignment for Query Recommendation in On-Device Assistants","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Boyang Zhang, Hong Huang, Lingkui Chen, Lizhong Wang, Ruike Zhang, Zihan Luo, Ziniu Chen","submitted_at":"2026-06-07T06:06:38Z","abstract_excerpt":"Large Language Models (LLMs) have significantly advanced generative query recommendation. However, existing alignment methods primarily focus on standard chatbot scenarios, falling short in on-device intelligent assistants where users predominantly expect the rapid invocation of system-level tools. Moreover, directly aligning LLMs with real-world click logs introduces severe noise due to varying user activity levels and the failure to emphasize execution-oriented queries. To address these challenges, we propose ToolRec, a calibrated preference alignment framework tailored for on-device query r"},"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":"2606.08466","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-07T06:06:38Z","cross_cats_sorted":[],"title_canon_sha256":"03980271e69d5c85a316c4e6ccee48a5a2335241b1fef91a99718ca0c0bdeace","abstract_canon_sha256":"f0827afffed37a4644bd5d9cdfa7cf3dcaf08172e0a05d05b5268f5f7fc679cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:37.361086Z","signature_b64":"WFmnXC7fFuxzZrsSwV+wm1F/yH5x/eLMy4HZeGGsYJvmp1LL2TMwPceEmCzJJMgnAcx5G88v3XyGXtCNdszIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4854266ab8b443b01790cd1bd8aa3f46944599716b66d59b23326d1d8d0cb678","last_reissued_at":"2026-06-09T01:05:37.360618Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:37.360618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ToolRec: Calibrated Preference Alignment for Query Recommendation in On-Device Assistants","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Boyang Zhang, Hong Huang, Lingkui Chen, Lizhong Wang, Ruike Zhang, Zihan Luo, Ziniu Chen","submitted_at":"2026-06-07T06:06:38Z","abstract_excerpt":"Large Language Models (LLMs) have significantly advanced generative query recommendation. However, existing alignment methods primarily focus on standard chatbot scenarios, falling short in on-device intelligent assistants where users predominantly expect the rapid invocation of system-level tools. Moreover, directly aligning LLMs with real-world click logs introduces severe noise due to varying user activity levels and the failure to emphasize execution-oriented queries. To address these challenges, we propose ToolRec, a calibrated preference alignment framework tailored for on-device query r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08466","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/2606.08466/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":"2606.08466","created_at":"2026-06-09T01:05:37.360685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08466v1","created_at":"2026-06-09T01:05:37.360685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08466","created_at":"2026-06-09T01:05:37.360685+00:00"},{"alias_kind":"pith_short_12","alias_value":"JBKCM2VYWRB3","created_at":"2026-06-09T01:05:37.360685+00:00"},{"alias_kind":"pith_short_16","alias_value":"JBKCM2VYWRB3AF4Q","created_at":"2026-06-09T01:05:37.360685+00:00"},{"alias_kind":"pith_short_8","alias_value":"JBKCM2VY","created_at":"2026-06-09T01:05:37.360685+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/JBKCM2VYWRB3AF4QZUN5RKR7I2","json":"https://pith.science/pith/JBKCM2VYWRB3AF4QZUN5RKR7I2.json","graph_json":"https://pith.science/api/pith-number/JBKCM2VYWRB3AF4QZUN5RKR7I2/graph.json","events_json":"https://pith.science/api/pith-number/JBKCM2VYWRB3AF4QZUN5RKR7I2/events.json","paper":"https://pith.science/paper/JBKCM2VY"},"agent_actions":{"view_html":"https://pith.science/pith/JBKCM2VYWRB3AF4QZUN5RKR7I2","download_json":"https://pith.science/pith/JBKCM2VYWRB3AF4QZUN5RKR7I2.json","view_paper":"https://pith.science/paper/JBKCM2VY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08466&json=true","fetch_graph":"https://pith.science/api/pith-number/JBKCM2VYWRB3AF4QZUN5RKR7I2/graph.json","fetch_events":"https://pith.science/api/pith-number/JBKCM2VYWRB3AF4QZUN5RKR7I2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JBKCM2VYWRB3AF4QZUN5RKR7I2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JBKCM2VYWRB3AF4QZUN5RKR7I2/action/storage_attestation","attest_author":"https://pith.science/pith/JBKCM2VYWRB3AF4QZUN5RKR7I2/action/author_attestation","sign_citation":"https://pith.science/pith/JBKCM2VYWRB3AF4QZUN5RKR7I2/action/citation_signature","submit_replication":"https://pith.science/pith/JBKCM2VYWRB3AF4QZUN5RKR7I2/action/replication_record"}},"created_at":"2026-06-09T01:05:37.360685+00:00","updated_at":"2026-06-09T01:05:37.360685+00:00"}