{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WNERSZJQGD7EGMOUC3RIAAHR55","short_pith_number":"pith:WNERSZJQ","schema_version":"1.0","canonical_sha256":"b34919653030fe4331d416e28000f1ef778426cd4421e6fc68a9647941f1ff61","source":{"kind":"arxiv","id":"2505.11908","version":1},"attestation_state":"computed","paper":{"title":"ELITE: Embedding-Less retrieval with Iterative Text Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Wang, Li Ning, Rong Zhou, Siyuan Gao, Zhangyu Wang","submitted_at":"2025-05-17T08:48:43Z","abstract_excerpt":"Large Language Models (LLMs) have achieved impressive progress in natural language processing, but their limited ability to retain long-term context constrains performance on document-level or multi-turn tasks. Retrieval-Augmented Generation (RAG) mitigates this by retrieving relevant information from an external corpus. However, existing RAG systems often rely on embedding-based retrieval trained on corpus-level semantic similarity, which can lead to retrieving content that is semantically similar in form but misaligned with the question's true intent. Furthermore, recent RAG variants constru"},"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":"2505.11908","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-17T08:48:43Z","cross_cats_sorted":[],"title_canon_sha256":"fcfeccfe69a8a2cb9a1a3c765ef1ffc6fbac287161a878de21845bac464b6b3e","abstract_canon_sha256":"be9d10a44eab8bc6688c739b7a425c209920d6dc1e830ed729ccc33a54b6b2f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:54.525777Z","signature_b64":"BJSVbOZDtmYH07pU++cCw0V2qWLZt1ATHiecQGAMnVFe2866sqfJ3qydX109iDGDTXER8UtNwsv/8WblrEpbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b34919653030fe4331d416e28000f1ef778426cd4421e6fc68a9647941f1ff61","last_reissued_at":"2026-07-05T11:04:54.525109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:54.525109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ELITE: Embedding-Less retrieval with Iterative Text Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Wang, Li Ning, Rong Zhou, Siyuan Gao, Zhangyu Wang","submitted_at":"2025-05-17T08:48:43Z","abstract_excerpt":"Large Language Models (LLMs) have achieved impressive progress in natural language processing, but their limited ability to retain long-term context constrains performance on document-level or multi-turn tasks. Retrieval-Augmented Generation (RAG) mitigates this by retrieving relevant information from an external corpus. However, existing RAG systems often rely on embedding-based retrieval trained on corpus-level semantic similarity, which can lead to retrieving content that is semantically similar in form but misaligned with the question's true intent. Furthermore, recent RAG variants constru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11908","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/2505.11908/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":"2505.11908","created_at":"2026-07-05T11:04:54.525177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11908v1","created_at":"2026-07-05T11:04:54.525177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11908","created_at":"2026-07-05T11:04:54.525177+00:00"},{"alias_kind":"pith_short_12","alias_value":"WNERSZJQGD7E","created_at":"2026-07-05T11:04:54.525177+00:00"},{"alias_kind":"pith_short_16","alias_value":"WNERSZJQGD7EGMOU","created_at":"2026-07-05T11:04:54.525177+00:00"},{"alias_kind":"pith_short_8","alias_value":"WNERSZJQ","created_at":"2026-07-05T11:04:54.525177+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/WNERSZJQGD7EGMOUC3RIAAHR55","json":"https://pith.science/pith/WNERSZJQGD7EGMOUC3RIAAHR55.json","graph_json":"https://pith.science/api/pith-number/WNERSZJQGD7EGMOUC3RIAAHR55/graph.json","events_json":"https://pith.science/api/pith-number/WNERSZJQGD7EGMOUC3RIAAHR55/events.json","paper":"https://pith.science/paper/WNERSZJQ"},"agent_actions":{"view_html":"https://pith.science/pith/WNERSZJQGD7EGMOUC3RIAAHR55","download_json":"https://pith.science/pith/WNERSZJQGD7EGMOUC3RIAAHR55.json","view_paper":"https://pith.science/paper/WNERSZJQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11908&json=true","fetch_graph":"https://pith.science/api/pith-number/WNERSZJQGD7EGMOUC3RIAAHR55/graph.json","fetch_events":"https://pith.science/api/pith-number/WNERSZJQGD7EGMOUC3RIAAHR55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WNERSZJQGD7EGMOUC3RIAAHR55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WNERSZJQGD7EGMOUC3RIAAHR55/action/storage_attestation","attest_author":"https://pith.science/pith/WNERSZJQGD7EGMOUC3RIAAHR55/action/author_attestation","sign_citation":"https://pith.science/pith/WNERSZJQGD7EGMOUC3RIAAHR55/action/citation_signature","submit_replication":"https://pith.science/pith/WNERSZJQGD7EGMOUC3RIAAHR55/action/replication_record"}},"created_at":"2026-07-05T11:04:54.525177+00:00","updated_at":"2026-07-05T11:04:54.525177+00:00"}