{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2HTETY63QD26ELV6SVM4HPTO3D","short_pith_number":"pith:2HTETY63","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"},"canonical_sha256":"d1e649e3db80f5e22ebe9559c3be6ed8f274c5c0b9bcf17aed461281ec70eff3","source":{"kind":"arxiv","id":"2608.00065","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00065","created_at":"2026-08-04T00:32:00Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00065v1","created_at":"2026-08-04T00:32:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00065","created_at":"2026-08-04T00:32:00Z"},{"alias_kind":"pith_short_12","alias_value":"2HTETY63QD26","created_at":"2026-08-04T00:32:00Z"},{"alias_kind":"pith_short_16","alias_value":"2HTETY63QD26ELV6","created_at":"2026-08-04T00:32:00Z"},{"alias_kind":"pith_short_8","alias_value":"2HTETY63","created_at":"2026-08-04T00:32:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2HTETY63QD26ELV6SVM4HPTO3D","target":"record","payload":{"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"},"canonical_sha256":"d1e649e3db80f5e22ebe9559c3be6ed8f274c5c0b9bcf17aed461281ec70eff3","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"},"source_kind":"arxiv","source_id":"2608.00065","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T00:32:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d0iw5/OlHPcpMP/l9m4cmpLyIADAHYnd4ws5P3pfwpSY3SMu7a0XvZ8mWeuhXQ57ufSIv8PXhxtQCdgtlfrCAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:58:59.854037Z"},"content_sha256":"262094750639b4dad6830bce587875571d77f3a7b6c39a233b89f73d9849329e","schema_version":"1.0","event_id":"sha256:262094750639b4dad6830bce587875571d77f3a7b6c39a233b89f73d9849329e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2HTETY63QD26ELV6SVM4HPTO3D","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T00:32:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f2yRKGFaOhlzFkY3+30vu6GL+s1asDgPEwHfT/Um+6rmxeJaC/om1lRoSMqJ5soVJw5JCLoJaL4M04hL45z3DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:58:59.854901Z"},"content_sha256":"630a5ecaeacc66e6dc7db263b21157dcf3d155bc9ed60b6668348007f981cd13","schema_version":"1.0","event_id":"sha256:630a5ecaeacc66e6dc7db263b21157dcf3d155bc9ed60b6668348007f981cd13"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2HTETY63QD26ELV6SVM4HPTO3D/bundle.json","state_url":"https://pith.science/pith/2HTETY63QD26ELV6SVM4HPTO3D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2HTETY63QD26ELV6SVM4HPTO3D/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T09:58:59Z","links":{"resolver":"https://pith.science/pith/2HTETY63QD26ELV6SVM4HPTO3D","bundle":"https://pith.science/pith/2HTETY63QD26ELV6SVM4HPTO3D/bundle.json","state":"https://pith.science/pith/2HTETY63QD26ELV6SVM4HPTO3D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2HTETY63QD26ELV6SVM4HPTO3D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2HTETY63QD26ELV6SVM4HPTO3D","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d24b28e0a08555a3de150cd0e15e6206fb30a3942575ce41d611ecfc80435833","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T01:37:45Z","title_canon_sha256":"5aacdf464cbe09b288ecde1a4bc2b819ac0386e81a6900ab27203cd14baf0240"},"schema_version":"1.0","source":{"id":"2608.00065","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00065","created_at":"2026-08-04T00:32:00Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00065v1","created_at":"2026-08-04T00:32:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00065","created_at":"2026-08-04T00:32:00Z"},{"alias_kind":"pith_short_12","alias_value":"2HTETY63QD26","created_at":"2026-08-04T00:32:00Z"},{"alias_kind":"pith_short_16","alias_value":"2HTETY63QD26ELV6","created_at":"2026-08-04T00:32:00Z"},{"alias_kind":"pith_short_8","alias_value":"2HTETY63","created_at":"2026-08-04T00:32:00Z"}],"graph_snapshots":[{"event_id":"sha256:630a5ecaeacc66e6dc7db263b21157dcf3d155bc9ed60b6668348007f981cd13","target":"graph","created_at":"2026-08-04T00:32:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.00065/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guosheng Dong, Jiangshou Hong, Junyi Hu, Shusen Zhang, Xiangzhi Wang, Xiaojun Yuan, Ye Feng, Zhaoyuan Pan, Ziteng Wang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T01:37:45Z","title":"H+ Embedding: Harmonizing Global and Token-Level Retrieval with Context-Dependent Phrases"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00065","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:262094750639b4dad6830bce587875571d77f3a7b6c39a233b89f73d9849329e","target":"record","created_at":"2026-08-04T00:32:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d24b28e0a08555a3de150cd0e15e6206fb30a3942575ce41d611ecfc80435833","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T01:37:45Z","title_canon_sha256":"5aacdf464cbe09b288ecde1a4bc2b819ac0386e81a6900ab27203cd14baf0240"},"schema_version":"1.0","source":{"id":"2608.00065","kind":"arxiv","version":1}},"canonical_sha256":"d1e649e3db80f5e22ebe9559c3be6ed8f274c5c0b9bcf17aed461281ec70eff3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1e649e3db80f5e22ebe9559c3be6ed8f274c5c0b9bcf17aed461281ec70eff3","first_computed_at":"2026-08-04T00:32:00.734318Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T00:32:00.734318Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ybh6q6zxB5EMzC/V78JJ98DotEIXtrGtvdX0LXw78o1sOi+82BRql4bQrCOIU0aOWx+cooUv9K6kMmahszWAAw==","signature_status":"signed_v1","signed_at":"2026-08-04T00:32:00.735848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00065","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:262094750639b4dad6830bce587875571d77f3a7b6c39a233b89f73d9849329e","sha256:630a5ecaeacc66e6dc7db263b21157dcf3d155bc9ed60b6668348007f981cd13"],"state_sha256":"a98496b16cd4595877e807b62d2598c7e086ef1da326c32e6c35ce56cb6923a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5+7NQ0D7Qo3K30s8tbqyymTpijWMk6SHO0oEGC87Q0B+genH9knxw7DBCCd2ORzk06dORgB2FJ0UcSOqFph9CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:58:59.860257Z","bundle_sha256":"69e9803cbf380aa7dbb4be1b177486af27114f597f819a46de91021bef8f5150"}}