{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HBGJBHJBL2ATWVL4GRLHWININV","short_pith_number":"pith:HBGJBHJB","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"},"canonical_sha256":"384c909d215e813b557c34567b21a86d6a118ec58dbd1ef01d078a9dcdf4404f","source":{"kind":"arxiv","id":"2605.22099","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22099","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22099v1","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22099","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"pith_short_12","alias_value":"HBGJBHJBL2AT","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"pith_short_16","alias_value":"HBGJBHJBL2ATWVL4","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"pith_short_8","alias_value":"HBGJBHJB","created_at":"2026-05-22T01:04:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HBGJBHJBL2ATWVL4GRLHWININV","target":"record","payload":{"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"},"canonical_sha256":"384c909d215e813b557c34567b21a86d6a118ec58dbd1ef01d078a9dcdf4404f","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"},"source_kind":"arxiv","source_id":"2605.22099","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:04:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mG0mLUVT4d0paqIyvsSnGQyHHO/WZtSwLrDw/5qVwg6y1NV7nI7gH7+JEI/s03fwvta45xn6ZoMTzl2XGaeVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T23:52:03.124883Z"},"content_sha256":"8b86b7ca4d402011e5168c22498a03706ea90efa34465c3d6b63e99015a2b0dc","schema_version":"1.0","event_id":"sha256:8b86b7ca4d402011e5168c22498a03706ea90efa34465c3d6b63e99015a2b0dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HBGJBHJBL2ATWVL4GRLHWININV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:04:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NlOgmvBB2OGOYrizTzAlC2cvy1FE5XaTUA9V6Md2B7AgW3uigGfXwwPJm7nos1q1qBdKsCf8t1pWtb79kYQFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T23:52:03.125526Z"},"content_sha256":"4082631e6ef6225d8e25754d7eb378ba7662b03c7b02b4379b41e558c404ef00","schema_version":"1.0","event_id":"sha256:4082631e6ef6225d8e25754d7eb378ba7662b03c7b02b4379b41e558c404ef00"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HBGJBHJBL2ATWVL4GRLHWININV/bundle.json","state_url":"https://pith.science/pith/HBGJBHJBL2ATWVL4GRLHWININV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HBGJBHJBL2ATWVL4GRLHWININV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T23:52:03Z","links":{"resolver":"https://pith.science/pith/HBGJBHJBL2ATWVL4GRLHWININV","bundle":"https://pith.science/pith/HBGJBHJBL2ATWVL4GRLHWININV/bundle.json","state":"https://pith.science/pith/HBGJBHJBL2ATWVL4GRLHWININV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HBGJBHJBL2ATWVL4GRLHWININV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HBGJBHJBL2ATWVL4GRLHWININV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"84e2c809abaa73560c21ef36b7f96c91cb99f5e354d261bebdf85405f9c654fe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T07:36:01Z","title_canon_sha256":"566c2e3737f80851efa8afa97bb80cf46eb981ce7c9ed3af15179b39abf2e99c"},"schema_version":"1.0","source":{"id":"2605.22099","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22099","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22099v1","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22099","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"pith_short_12","alias_value":"HBGJBHJBL2AT","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"pith_short_16","alias_value":"HBGJBHJBL2ATWVL4","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"pith_short_8","alias_value":"HBGJBHJB","created_at":"2026-05-22T01:04:25Z"}],"graph_snapshots":[{"event_id":"sha256:4082631e6ef6225d8e25754d7eb378ba7662b03c7b02b4379b41e558c404ef00","target":"graph","created_at":"2026-05-22T01:04:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.22099/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kimleang Ly, Phannet Pov, Ratanaktepi Chhor, Saksonita Khoeurn, Sereiwathna Ros, Wan-Sup Cho","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T07:36:01Z","title":"A Comparative Study of Language Models for Khmer Retrieval-Augmented Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22099","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8b86b7ca4d402011e5168c22498a03706ea90efa34465c3d6b63e99015a2b0dc","target":"record","created_at":"2026-05-22T01:04:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"84e2c809abaa73560c21ef36b7f96c91cb99f5e354d261bebdf85405f9c654fe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T07:36:01Z","title_canon_sha256":"566c2e3737f80851efa8afa97bb80cf46eb981ce7c9ed3af15179b39abf2e99c"},"schema_version":"1.0","source":{"id":"2605.22099","kind":"arxiv","version":1}},"canonical_sha256":"384c909d215e813b557c34567b21a86d6a118ec58dbd1ef01d078a9dcdf4404f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"384c909d215e813b557c34567b21a86d6a118ec58dbd1ef01d078a9dcdf4404f","first_computed_at":"2026-05-22T01:04:25.650408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:25.650408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PiJGfsb1B2QHZCyB/gF2mRhg4GVV2tK6db4BlEi8E4fBz9+on/LrX0uqDCyHV0ifaqX1OoAngp6mJx6FTL5YAg==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:25.651152Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22099","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b86b7ca4d402011e5168c22498a03706ea90efa34465c3d6b63e99015a2b0dc","sha256:4082631e6ef6225d8e25754d7eb378ba7662b03c7b02b4379b41e558c404ef00"],"state_sha256":"45b80b86001fb1cae723d79d33535b01b181a3c72a6db6366951246289f1a1f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7wilXGCBpeD90/Lan8T+KW6QraNsIpW9iLxwrx0igvRc2YEy0VGCoYQRHs7Hos218XBdV62kSF81CFn01esvAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T23:52:03.128649Z","bundle_sha256":"56727cfc4f094c572dcd5cba1d5c0ba05aa3d2010fd089d80ac150da2bb3412d"}}