{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GZEHXTI5Z422HJ7OKQGZL3BPWG","short_pith_number":"pith:GZEHXTI5","schema_version":"1.0","canonical_sha256":"36487bcd1dcf35a3a7ee540d95ec2fb187467a9b90bd4022a74c1d559ba6f8af","source":{"kind":"arxiv","id":"2402.11573","version":1},"attestation_state":"computed","paper":{"title":"BGE Landmark Embedding: A Chunking-Free Embedding Method For Retrieval Augmented Long-Context Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kang Liu, Kun Luo, Shitao Xiao, Zheng Liu","submitted_at":"2024-02-18T12:41:01Z","abstract_excerpt":"Large language models (LLMs) call for extension of context to handle many critical applications. However, the existing approaches are prone to expensive costs and inferior quality of context extension. In this work, we proposeExtensible Embedding, which realizes high-quality extension of LLM's context with strong flexibility and cost-effectiveness. Extensible embedding stand as an enhancement of typical token embedding, which represents the information for an extensible scope of context instead of a single token. By leveraging such compact input units of higher information density, the LLM can"},"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":"2402.11573","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T12:41:01Z","cross_cats_sorted":[],"title_canon_sha256":"9fd01714eb58fc1c86594d20ccf0f7325d2cc8f97216ecb7db76b39411b6e4ce","abstract_canon_sha256":"ad861dc484f20ca16cc26dee3d3e733a9c51138e3cf4985e3386cd09dc0c6b06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:41.328252Z","signature_b64":"jfZJrTmjQ01okvjatRme6iJxI2h+lHtA2k0NnMR0Aa6/WXdcIjtHEeN4mZiXHy4lQ3CAURJ+sB8VJd3HJyPZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36487bcd1dcf35a3a7ee540d95ec2fb187467a9b90bd4022a74c1d559ba6f8af","last_reissued_at":"2026-07-05T07:46:41.327805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:41.327805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BGE Landmark Embedding: A Chunking-Free Embedding Method For Retrieval Augmented Long-Context Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kang Liu, Kun Luo, Shitao Xiao, Zheng Liu","submitted_at":"2024-02-18T12:41:01Z","abstract_excerpt":"Large language models (LLMs) call for extension of context to handle many critical applications. However, the existing approaches are prone to expensive costs and inferior quality of context extension. In this work, we proposeExtensible Embedding, which realizes high-quality extension of LLM's context with strong flexibility and cost-effectiveness. Extensible embedding stand as an enhancement of typical token embedding, which represents the information for an extensible scope of context instead of a single token. By leveraging such compact input units of higher information density, the LLM can"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11573","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/2402.11573/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":"2402.11573","created_at":"2026-07-05T07:46:41.327869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11573v1","created_at":"2026-07-05T07:46:41.327869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11573","created_at":"2026-07-05T07:46:41.327869+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZEHXTI5Z422","created_at":"2026-07-05T07:46:41.327869+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZEHXTI5Z422HJ7O","created_at":"2026-07-05T07:46:41.327869+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZEHXTI5","created_at":"2026-07-05T07:46:41.327869+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03236","citing_title":"Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliable Proactive Mobile Agents","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00702","citing_title":"Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GZEHXTI5Z422HJ7OKQGZL3BPWG","json":"https://pith.science/pith/GZEHXTI5Z422HJ7OKQGZL3BPWG.json","graph_json":"https://pith.science/api/pith-number/GZEHXTI5Z422HJ7OKQGZL3BPWG/graph.json","events_json":"https://pith.science/api/pith-number/GZEHXTI5Z422HJ7OKQGZL3BPWG/events.json","paper":"https://pith.science/paper/GZEHXTI5"},"agent_actions":{"view_html":"https://pith.science/pith/GZEHXTI5Z422HJ7OKQGZL3BPWG","download_json":"https://pith.science/pith/GZEHXTI5Z422HJ7OKQGZL3BPWG.json","view_paper":"https://pith.science/paper/GZEHXTI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11573&json=true","fetch_graph":"https://pith.science/api/pith-number/GZEHXTI5Z422HJ7OKQGZL3BPWG/graph.json","fetch_events":"https://pith.science/api/pith-number/GZEHXTI5Z422HJ7OKQGZL3BPWG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZEHXTI5Z422HJ7OKQGZL3BPWG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZEHXTI5Z422HJ7OKQGZL3BPWG/action/storage_attestation","attest_author":"https://pith.science/pith/GZEHXTI5Z422HJ7OKQGZL3BPWG/action/author_attestation","sign_citation":"https://pith.science/pith/GZEHXTI5Z422HJ7OKQGZL3BPWG/action/citation_signature","submit_replication":"https://pith.science/pith/GZEHXTI5Z422HJ7OKQGZL3BPWG/action/replication_record"}},"created_at":"2026-07-05T07:46:41.327869+00:00","updated_at":"2026-07-05T07:46:41.327869+00:00"}