{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:U2HR7NIPJA4JKCKDPQNMNIMQNO","short_pith_number":"pith:U2HR7NIP","schema_version":"1.0","canonical_sha256":"a68f1fb50f48389509437c1ac6a1906ba360994eded16526749bfefc8536901c","source":{"kind":"arxiv","id":"2606.25674","version":1},"attestation_state":"computed","paper":{"title":"BitNet Text Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Dongyan Zhao, Furu Wei, Huishuai Zhang, Liang Wang, Nan Yang, Shaohan Huang, Ting Song, Xin Huang, Xun Wu, Yan Xia, Zhen Li","submitted_at":"2026-06-24T10:37:01Z","abstract_excerpt":"LLM-based text embedders have substantially improved retrieval and semantic representation quality, but their deployment remains costly: large backbone models slow down embedding inference, while high-dimensional full-precision embeddings impose substantial storage and bandwidth overhead on large-scale indexes. In this paper, we present BITEMBED, an extreme low-bit framework for LLM-based text embedding that jointly targets encoding efficiency and vector storage. BITEMBED converts pretrained LLM backbones into BitNet-style embedding encoders with ternary weights, quantized activations, and lig"},"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":"2606.25674","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T10:37:01Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"41480044e4fcdff44c0e7586fa2f1e45cdfa7aca5a0539099bee13a850ec1637","abstract_canon_sha256":"91c41fbb7e542cec00552e491f94dbc2fcd9d57a14bd2c140c064fe4d5a6195e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:12.509239Z","signature_b64":"g3v1a4IgWB+TtdDzPZ2KimLWk1j5ji6SXobdkdSgL8PNT9njNLf14wpITkMmUQ3mPt9pbKetkWq+7AnpQiHqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a68f1fb50f48389509437c1ac6a1906ba360994eded16526749bfefc8536901c","last_reissued_at":"2026-06-25T01:18:12.508847Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:12.508847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BitNet Text Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Dongyan Zhao, Furu Wei, Huishuai Zhang, Liang Wang, Nan Yang, Shaohan Huang, Ting Song, Xin Huang, Xun Wu, Yan Xia, Zhen Li","submitted_at":"2026-06-24T10:37:01Z","abstract_excerpt":"LLM-based text embedders have substantially improved retrieval and semantic representation quality, but their deployment remains costly: large backbone models slow down embedding inference, while high-dimensional full-precision embeddings impose substantial storage and bandwidth overhead on large-scale indexes. In this paper, we present BITEMBED, an extreme low-bit framework for LLM-based text embedding that jointly targets encoding efficiency and vector storage. BITEMBED converts pretrained LLM backbones into BitNet-style embedding encoders with ternary weights, quantized activations, and lig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25674","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/2606.25674/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":"2606.25674","created_at":"2026-06-25T01:18:12.508912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25674v1","created_at":"2026-06-25T01:18:12.508912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25674","created_at":"2026-06-25T01:18:12.508912+00:00"},{"alias_kind":"pith_short_12","alias_value":"U2HR7NIPJA4J","created_at":"2026-06-25T01:18:12.508912+00:00"},{"alias_kind":"pith_short_16","alias_value":"U2HR7NIPJA4JKCKD","created_at":"2026-06-25T01:18:12.508912+00:00"},{"alias_kind":"pith_short_8","alias_value":"U2HR7NIP","created_at":"2026-06-25T01:18:12.508912+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/U2HR7NIPJA4JKCKDPQNMNIMQNO","json":"https://pith.science/pith/U2HR7NIPJA4JKCKDPQNMNIMQNO.json","graph_json":"https://pith.science/api/pith-number/U2HR7NIPJA4JKCKDPQNMNIMQNO/graph.json","events_json":"https://pith.science/api/pith-number/U2HR7NIPJA4JKCKDPQNMNIMQNO/events.json","paper":"https://pith.science/paper/U2HR7NIP"},"agent_actions":{"view_html":"https://pith.science/pith/U2HR7NIPJA4JKCKDPQNMNIMQNO","download_json":"https://pith.science/pith/U2HR7NIPJA4JKCKDPQNMNIMQNO.json","view_paper":"https://pith.science/paper/U2HR7NIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25674&json=true","fetch_graph":"https://pith.science/api/pith-number/U2HR7NIPJA4JKCKDPQNMNIMQNO/graph.json","fetch_events":"https://pith.science/api/pith-number/U2HR7NIPJA4JKCKDPQNMNIMQNO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U2HR7NIPJA4JKCKDPQNMNIMQNO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U2HR7NIPJA4JKCKDPQNMNIMQNO/action/storage_attestation","attest_author":"https://pith.science/pith/U2HR7NIPJA4JKCKDPQNMNIMQNO/action/author_attestation","sign_citation":"https://pith.science/pith/U2HR7NIPJA4JKCKDPQNMNIMQNO/action/citation_signature","submit_replication":"https://pith.science/pith/U2HR7NIPJA4JKCKDPQNMNIMQNO/action/replication_record"}},"created_at":"2026-06-25T01:18:12.508912+00:00","updated_at":"2026-06-25T01:18:12.508912+00:00"}