{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HBGJBHJBL2ATWVL4GRLHWININV","short_pith_number":"pith:HBGJBHJB","schema_version":"1.0","canonical_sha256":"384c909d215e813b557c34567b21a86d6a118ec58dbd1ef01d078a9dcdf4404f","source":{"kind":"arxiv","id":"2605.22099","version":1},"attestation_state":"computed","paper":{"title":"A Comparative Study of Language Models for Khmer Retrieval-Augmented Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kimleang Ly, Phannet Pov, Ratanaktepi Chhor, Saksonita Khoeurn, Sereiwathna Ros, Wan-Sup Cho","submitted_at":"2026-05-21T07:36:01Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for grounding large language model (LLM) outputs in retrieved evidence, thereby reducing hallucination and improving factual accuracy. Its efficacy, however, remains largely unexamined for low-resource, non-Latin-script languages such as Khmer. In this paper, we present a RAG-based question answering system for Khmer-language telecom-domain documents. We conduct a two-phase comparative evaluation. First, we benchmark three embedding models: BGE-M3 (567M), Jina-Embeddings-v3 (570M), and Qwen3-Embedding (597M), for dense re"},"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":"2605.22099","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T07:36:01Z","cross_cats_sorted":[],"title_canon_sha256":"566c2e3737f80851efa8afa97bb80cf46eb981ce7c9ed3af15179b39abf2e99c","abstract_canon_sha256":"84e2c809abaa73560c21ef36b7f96c91cb99f5e354d261bebdf85405f9c654fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:25.651152Z","signature_b64":"PiJGfsb1B2QHZCyB/gF2mRhg4GVV2tK6db4BlEi8E4fBz9+on/LrX0uqDCyHV0ifaqX1OoAngp6mJx6FTL5YAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"384c909d215e813b557c34567b21a86d6a118ec58dbd1ef01d078a9dcdf4404f","last_reissued_at":"2026-05-22T01:04:25.650408Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:25.650408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparative Study of Language Models for Khmer Retrieval-Augmented Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kimleang Ly, Phannet Pov, Ratanaktepi Chhor, Saksonita Khoeurn, Sereiwathna Ros, Wan-Sup Cho","submitted_at":"2026-05-21T07:36:01Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for grounding large language model (LLM) outputs in retrieved evidence, thereby reducing hallucination and improving factual accuracy. Its efficacy, however, remains largely unexamined for low-resource, non-Latin-script languages such as Khmer. In this paper, we present a RAG-based question answering system for Khmer-language telecom-domain documents. We conduct a two-phase comparative evaluation. First, we benchmark three embedding models: BGE-M3 (567M), Jina-Embeddings-v3 (570M), and Qwen3-Embedding (597M), for dense re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22099","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/2605.22099/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":"2605.22099","created_at":"2026-05-22T01:04:25.650533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22099v1","created_at":"2026-05-22T01:04:25.650533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22099","created_at":"2026-05-22T01:04:25.650533+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBGJBHJBL2AT","created_at":"2026-05-22T01:04:25.650533+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBGJBHJBL2ATWVL4","created_at":"2026-05-22T01:04:25.650533+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBGJBHJB","created_at":"2026-05-22T01:04:25.650533+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/HBGJBHJBL2ATWVL4GRLHWININV","json":"https://pith.science/pith/HBGJBHJBL2ATWVL4GRLHWININV.json","graph_json":"https://pith.science/api/pith-number/HBGJBHJBL2ATWVL4GRLHWININV/graph.json","events_json":"https://pith.science/api/pith-number/HBGJBHJBL2ATWVL4GRLHWININV/events.json","paper":"https://pith.science/paper/HBGJBHJB"},"agent_actions":{"view_html":"https://pith.science/pith/HBGJBHJBL2ATWVL4GRLHWININV","download_json":"https://pith.science/pith/HBGJBHJBL2ATWVL4GRLHWININV.json","view_paper":"https://pith.science/paper/HBGJBHJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22099&json=true","fetch_graph":"https://pith.science/api/pith-number/HBGJBHJBL2ATWVL4GRLHWININV/graph.json","fetch_events":"https://pith.science/api/pith-number/HBGJBHJBL2ATWVL4GRLHWININV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBGJBHJBL2ATWVL4GRLHWININV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBGJBHJBL2ATWVL4GRLHWININV/action/storage_attestation","attest_author":"https://pith.science/pith/HBGJBHJBL2ATWVL4GRLHWININV/action/author_attestation","sign_citation":"https://pith.science/pith/HBGJBHJBL2ATWVL4GRLHWININV/action/citation_signature","submit_replication":"https://pith.science/pith/HBGJBHJBL2ATWVL4GRLHWININV/action/replication_record"}},"created_at":"2026-05-22T01:04:25.650533+00:00","updated_at":"2026-05-22T01:04:25.650533+00:00"}