{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:36T5TW76LIF7JQBELT4UFEBGAI","short_pith_number":"pith:36T5TW76","schema_version":"1.0","canonical_sha256":"dfa7d9dbfe5a0bf4c0245cf9429026023878f9cbab630c0d4b56bf40421ae442","source":{"kind":"arxiv","id":"2307.16645","version":1},"attestation_state":"computed","paper":{"title":"Scaling Sentence Embeddings with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deqing Wang, Fuzhen Zhuang, Shaohan Huang, Ting Jiang, Zhongzhi Luan","submitted_at":"2023-07-31T13:26:03Z","abstract_excerpt":"Large language models (LLMs) have recently garnered significant interest. With in-context learning, LLMs achieve impressive results in various natural language tasks. However, the application of LLMs to sentence embeddings remains an area of ongoing research. In this work, we propose an in-context learning-based method aimed at improving sentence embeddings performance. Our approach involves adapting the previous prompt-based representation method for autoregressive models, constructing a demonstration set that enables LLMs to perform in-context learning, and scaling up the LLMs to different m"},"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":"2307.16645","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-31T13:26:03Z","cross_cats_sorted":[],"title_canon_sha256":"827a856fb83cfe0540cd262dad01877e5562b2ea22f899337ae877850961cf74","abstract_canon_sha256":"85df21cb1fab96a02c5ea4a104a2e75d6ffce2a76560099cbe727806db293914"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:36:06.407592Z","signature_b64":"J/GD2UzAT/0CJ9c1AZh3zuE5KJWTYGc0oH2aLVeT8iPtU6NVyRuU1lmjc619WTBtNNQYP3C9STiSDT8Xv66CAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfa7d9dbfe5a0bf4c0245cf9429026023878f9cbab630c0d4b56bf40421ae442","last_reissued_at":"2026-07-05T06:36:06.407203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:36:06.407203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Sentence Embeddings with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deqing Wang, Fuzhen Zhuang, Shaohan Huang, Ting Jiang, Zhongzhi Luan","submitted_at":"2023-07-31T13:26:03Z","abstract_excerpt":"Large language models (LLMs) have recently garnered significant interest. With in-context learning, LLMs achieve impressive results in various natural language tasks. However, the application of LLMs to sentence embeddings remains an area of ongoing research. In this work, we propose an in-context learning-based method aimed at improving sentence embeddings performance. Our approach involves adapting the previous prompt-based representation method for autoregressive models, constructing a demonstration set that enables LLMs to perform in-context learning, and scaling up the LLMs to different m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16645","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/2307.16645/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":"2307.16645","created_at":"2026-07-05T06:36:06.407251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.16645v1","created_at":"2026-07-05T06:36:06.407251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16645","created_at":"2026-07-05T06:36:06.407251+00:00"},{"alias_kind":"pith_short_12","alias_value":"36T5TW76LIF7","created_at":"2026-07-05T06:36:06.407251+00:00"},{"alias_kind":"pith_short_16","alias_value":"36T5TW76LIF7JQBE","created_at":"2026-07-05T06:36:06.407251+00:00"},{"alias_kind":"pith_short_8","alias_value":"36T5TW76","created_at":"2026-07-05T06:36:06.407251+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20280","citing_title":"ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24621","citing_title":"FreeRet: MLLMs as Training-Free Retrievers","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2407.12580","citing_title":"E5-V: Universal Embeddings with Multimodal Large Language Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25273","citing_title":"Combating Visual Neglect and Semantic Drift in Large Multimodal Models for Enhanced Cross-Modal Retrieval","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18146","citing_title":"Modular Representation Compression: Adapting LLMs for Efficient and Effective Recommendations","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07834","citing_title":"GenAI Powered Dynamic Causal Inference with Unstructured Data","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/36T5TW76LIF7JQBELT4UFEBGAI","json":"https://pith.science/pith/36T5TW76LIF7JQBELT4UFEBGAI.json","graph_json":"https://pith.science/api/pith-number/36T5TW76LIF7JQBELT4UFEBGAI/graph.json","events_json":"https://pith.science/api/pith-number/36T5TW76LIF7JQBELT4UFEBGAI/events.json","paper":"https://pith.science/paper/36T5TW76"},"agent_actions":{"view_html":"https://pith.science/pith/36T5TW76LIF7JQBELT4UFEBGAI","download_json":"https://pith.science/pith/36T5TW76LIF7JQBELT4UFEBGAI.json","view_paper":"https://pith.science/paper/36T5TW76","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.16645&json=true","fetch_graph":"https://pith.science/api/pith-number/36T5TW76LIF7JQBELT4UFEBGAI/graph.json","fetch_events":"https://pith.science/api/pith-number/36T5TW76LIF7JQBELT4UFEBGAI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36T5TW76LIF7JQBELT4UFEBGAI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36T5TW76LIF7JQBELT4UFEBGAI/action/storage_attestation","attest_author":"https://pith.science/pith/36T5TW76LIF7JQBELT4UFEBGAI/action/author_attestation","sign_citation":"https://pith.science/pith/36T5TW76LIF7JQBELT4UFEBGAI/action/citation_signature","submit_replication":"https://pith.science/pith/36T5TW76LIF7JQBELT4UFEBGAI/action/replication_record"}},"created_at":"2026-07-05T06:36:06.407251+00:00","updated_at":"2026-07-05T06:36:06.407251+00:00"}