{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2H3V6QL4PT3TME37JQRI6A6RNF","short_pith_number":"pith:2H3V6QL4","schema_version":"1.0","canonical_sha256":"d1f75f417c7cf736137f4c228f03d1696d03ec254eceffedc3cffd9a790b89ef","source":{"kind":"arxiv","id":"2402.09760","version":1},"attestation_state":"computed","paper":{"title":"Grounding Language Model with Chunking-Free In-Context Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Hongjin Qian, Kelong Mao, Yujia Zhou, Zheng Liu, Zhicheng Dou","submitted_at":"2024-02-15T07:22:04Z","abstract_excerpt":"This paper presents a novel Chunking-Free In-Context (CFIC) retrieval approach, specifically tailored for Retrieval-Augmented Generation (RAG) systems. Traditional RAG systems often struggle with grounding responses using precise evidence text due to the challenges of processing lengthy documents and filtering out irrelevant content. Commonly employed solutions, such as document chunking and adapting language models to handle longer contexts, have their limitations. These methods either disrupt the semantic coherence of the text or fail to effectively address the issues of noise and inaccuracy"},"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":"2402.09760","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T07:22:04Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"6c3a00db7da73f0a4a485733711e767dc35d53e112f9097870b5ab22d740682c","abstract_canon_sha256":"88b4e9f03179c146516691349c49eb50bc8f35716945776fca2ddcbe3f847d02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:36.546978Z","signature_b64":"AUgWC0fgmWW36H0heKZlP/MVm8jbTRayRlhX5ktm5rXJFR7M91AshVsHNaaSzMHZKK1HjnUZvilJfuP5eWRtAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1f75f417c7cf736137f4c228f03d1696d03ec254eceffedc3cffd9a790b89ef","last_reissued_at":"2026-07-05T07:45:36.546541Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:36.546541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounding Language Model with Chunking-Free In-Context Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Hongjin Qian, Kelong Mao, Yujia Zhou, Zheng Liu, Zhicheng Dou","submitted_at":"2024-02-15T07:22:04Z","abstract_excerpt":"This paper presents a novel Chunking-Free In-Context (CFIC) retrieval approach, specifically tailored for Retrieval-Augmented Generation (RAG) systems. Traditional RAG systems often struggle with grounding responses using precise evidence text due to the challenges of processing lengthy documents and filtering out irrelevant content. Commonly employed solutions, such as document chunking and adapting language models to handle longer contexts, have their limitations. These methods either disrupt the semantic coherence of the text or fail to effectively address the issues of noise and inaccuracy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09760","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/2402.09760/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":"2402.09760","created_at":"2026-07-05T07:45:36.546599+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09760v1","created_at":"2026-07-05T07:45:36.546599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09760","created_at":"2026-07-05T07:45:36.546599+00:00"},{"alias_kind":"pith_short_12","alias_value":"2H3V6QL4PT3T","created_at":"2026-07-05T07:45:36.546599+00:00"},{"alias_kind":"pith_short_16","alias_value":"2H3V6QL4PT3TME37","created_at":"2026-07-05T07:45:36.546599+00:00"},{"alias_kind":"pith_short_8","alias_value":"2H3V6QL4","created_at":"2026-07-05T07:45:36.546599+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.19897","citing_title":"Can LLMs Replace Humans During Code Chunking?","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2H3V6QL4PT3TME37JQRI6A6RNF","json":"https://pith.science/pith/2H3V6QL4PT3TME37JQRI6A6RNF.json","graph_json":"https://pith.science/api/pith-number/2H3V6QL4PT3TME37JQRI6A6RNF/graph.json","events_json":"https://pith.science/api/pith-number/2H3V6QL4PT3TME37JQRI6A6RNF/events.json","paper":"https://pith.science/paper/2H3V6QL4"},"agent_actions":{"view_html":"https://pith.science/pith/2H3V6QL4PT3TME37JQRI6A6RNF","download_json":"https://pith.science/pith/2H3V6QL4PT3TME37JQRI6A6RNF.json","view_paper":"https://pith.science/paper/2H3V6QL4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09760&json=true","fetch_graph":"https://pith.science/api/pith-number/2H3V6QL4PT3TME37JQRI6A6RNF/graph.json","fetch_events":"https://pith.science/api/pith-number/2H3V6QL4PT3TME37JQRI6A6RNF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2H3V6QL4PT3TME37JQRI6A6RNF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2H3V6QL4PT3TME37JQRI6A6RNF/action/storage_attestation","attest_author":"https://pith.science/pith/2H3V6QL4PT3TME37JQRI6A6RNF/action/author_attestation","sign_citation":"https://pith.science/pith/2H3V6QL4PT3TME37JQRI6A6RNF/action/citation_signature","submit_replication":"https://pith.science/pith/2H3V6QL4PT3TME37JQRI6A6RNF/action/replication_record"}},"created_at":"2026-07-05T07:45:36.546599+00:00","updated_at":"2026-07-05T07:45:36.546599+00:00"}