{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2HTETY63QD26ELV6SVM4HPTO3D","short_pith_number":"pith:2HTETY63","schema_version":"1.0","canonical_sha256":"d1e649e3db80f5e22ebe9559c3be6ed8f274c5c0b9bcf17aed461281ec70eff3","source":{"kind":"arxiv","id":"2608.00065","version":1},"attestation_state":"computed","paper":{"title":"H+ Embedding: Harmonizing Global and Token-Level Retrieval with Context-Dependent Phrases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Guosheng Dong, Jiangshou Hong, Junyi Hu, Shusen Zhang, Xiangzhi Wang, Xiaojun Yuan, Ye Feng, Zhaoyuan Pan, Ziteng Wang","submitted_at":"2026-07-29T01:37:45Z","abstract_excerpt":"Terminology-intensive retrieval, especially in medical settings, depends on preserving multi-word entities, abbreviations, numerical constraints, and compositional concepts. However, existing representations lie at two extremes: single-vector retrievers often over-compress local relevance signals, while token-level late interaction retains every tokenizer subword at substantial indexing, storage, and scoring cost. This mismatch raises a natural question: can context-dependent phrases provide a useful retrieval unit between global vectors and tokens? We introduce H+ Embedding, a unified multi-g"},"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":"2608.00065","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T01:37:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5aacdf464cbe09b288ecde1a4bc2b819ac0386e81a6900ab27203cd14baf0240","abstract_canon_sha256":"d24b28e0a08555a3de150cd0e15e6206fb30a3942575ce41d611ecfc80435833"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:32:00.735848Z","signature_b64":"ybh6q6zxB5EMzC/V78JJ98DotEIXtrGtvdX0LXw78o1sOi+82BRql4bQrCOIU0aOWx+cooUv9K6kMmahszWAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1e649e3db80f5e22ebe9559c3be6ed8f274c5c0b9bcf17aed461281ec70eff3","last_reissued_at":"2026-08-04T00:32:00.734318Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:32:00.734318Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"H+ Embedding: Harmonizing Global and Token-Level Retrieval with Context-Dependent Phrases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Guosheng Dong, Jiangshou Hong, Junyi Hu, Shusen Zhang, Xiangzhi Wang, Xiaojun Yuan, Ye Feng, Zhaoyuan Pan, Ziteng Wang","submitted_at":"2026-07-29T01:37:45Z","abstract_excerpt":"Terminology-intensive retrieval, especially in medical settings, depends on preserving multi-word entities, abbreviations, numerical constraints, and compositional concepts. However, existing representations lie at two extremes: single-vector retrievers often over-compress local relevance signals, while token-level late interaction retains every tokenizer subword at substantial indexing, storage, and scoring cost. This mismatch raises a natural question: can context-dependent phrases provide a useful retrieval unit between global vectors and tokens? We introduce H+ Embedding, a unified multi-g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00065","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/2608.00065/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":"2608.00065","created_at":"2026-08-04T00:32:00.735354+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00065v1","created_at":"2026-08-04T00:32:00.735354+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00065","created_at":"2026-08-04T00:32:00.735354+00:00"},{"alias_kind":"pith_short_12","alias_value":"2HTETY63QD26","created_at":"2026-08-04T00:32:00.735354+00:00"},{"alias_kind":"pith_short_16","alias_value":"2HTETY63QD26ELV6","created_at":"2026-08-04T00:32:00.735354+00:00"},{"alias_kind":"pith_short_8","alias_value":"2HTETY63","created_at":"2026-08-04T00:32:00.735354+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/2HTETY63QD26ELV6SVM4HPTO3D","json":"https://pith.science/pith/2HTETY63QD26ELV6SVM4HPTO3D.json","graph_json":"https://pith.science/api/pith-number/2HTETY63QD26ELV6SVM4HPTO3D/graph.json","events_json":"https://pith.science/api/pith-number/2HTETY63QD26ELV6SVM4HPTO3D/events.json","paper":"https://pith.science/paper/2HTETY63"},"agent_actions":{"view_html":"https://pith.science/pith/2HTETY63QD26ELV6SVM4HPTO3D","download_json":"https://pith.science/pith/2HTETY63QD26ELV6SVM4HPTO3D.json","view_paper":"https://pith.science/paper/2HTETY63","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00065&json=true","fetch_graph":"https://pith.science/api/pith-number/2HTETY63QD26ELV6SVM4HPTO3D/graph.json","fetch_events":"https://pith.science/api/pith-number/2HTETY63QD26ELV6SVM4HPTO3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2HTETY63QD26ELV6SVM4HPTO3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2HTETY63QD26ELV6SVM4HPTO3D/action/storage_attestation","attest_author":"https://pith.science/pith/2HTETY63QD26ELV6SVM4HPTO3D/action/author_attestation","sign_citation":"https://pith.science/pith/2HTETY63QD26ELV6SVM4HPTO3D/action/citation_signature","submit_replication":"https://pith.science/pith/2HTETY63QD26ELV6SVM4HPTO3D/action/replication_record"}},"created_at":"2026-08-04T00:32:00.735354+00:00","updated_at":"2026-08-04T00:32:00.735354+00:00"}