{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OAFZXP2J3HFWYENHZ6TVFG22MA","short_pith_number":"pith:OAFZXP2J","canonical_record":{"source":{"id":"2501.04858","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-08T22:16:40Z","cross_cats_sorted":[],"title_canon_sha256":"3ca2dc459f9bfcfa3ab074277c8274604e25a270654ab87431463fa45c5e0cd6","abstract_canon_sha256":"1692c60f3de27cdb4cb73eae9f1fb44f9a48c14b8ffa2e2d4cdeff617c191a2c"},"schema_version":"1.0"},"canonical_sha256":"700b9bbf49d9cb6c11a7cfa7529b5a60063bef5c823b7916844b8feb65d2be7d","source":{"kind":"arxiv","id":"2501.04858","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04858","created_at":"2026-07-05T09:58:47Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04858v1","created_at":"2026-07-05T09:58:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04858","created_at":"2026-07-05T09:58:47Z"},{"alias_kind":"pith_short_12","alias_value":"OAFZXP2J3HFW","created_at":"2026-07-05T09:58:47Z"},{"alias_kind":"pith_short_16","alias_value":"OAFZXP2J3HFWYENH","created_at":"2026-07-05T09:58:47Z"},{"alias_kind":"pith_short_8","alias_value":"OAFZXP2J","created_at":"2026-07-05T09:58:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OAFZXP2J3HFWYENHZ6TVFG22MA","target":"record","payload":{"canonical_record":{"source":{"id":"2501.04858","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-08T22:16:40Z","cross_cats_sorted":[],"title_canon_sha256":"3ca2dc459f9bfcfa3ab074277c8274604e25a270654ab87431463fa45c5e0cd6","abstract_canon_sha256":"1692c60f3de27cdb4cb73eae9f1fb44f9a48c14b8ffa2e2d4cdeff617c191a2c"},"schema_version":"1.0"},"canonical_sha256":"700b9bbf49d9cb6c11a7cfa7529b5a60063bef5c823b7916844b8feb65d2be7d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:47.607623Z","signature_b64":"8Xfc3mOttPbQKxEyraW0TdNw8ycwhRaMU0+3REm3zZeasAmhCH6SkPZj42Z2k4gZa9Z3wVjnGcT/bdbJufV/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"700b9bbf49d9cb6c11a7cfa7529b5a60063bef5c823b7916844b8feb65d2be7d","last_reissued_at":"2026-07-05T09:58:47.607163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:47.607163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.04858","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":"2026-07-05T09:58:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nlikz+9VU4LnrclioxOXqiedaaSLnsznKnD8vBOf30B95Th7DAGjeHJyUgmFTcqoM21L+dwMSQXrK+15ZdS9CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T11:07:12.479410Z"},"content_sha256":"59c1ee2982afc74a0c5c062d30a9da2e96933922a7cb27867de4e8963ef36639","schema_version":"1.0","event_id":"sha256:59c1ee2982afc74a0c5c062d30a9da2e96933922a7cb27867de4e8963ef36639"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OAFZXP2J3HFWYENHZ6TVFG22MA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Advancing Retrieval-Augmented Generation for Persian: Development of Language Models, Comprehensive Benchmarks, and Best Practices for Optimization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mohammad Ali Seif Kashani, Mohammad Amin Abbasi, Mohammad Hossein Shalchian, Sara Bourbour Hosseinbeigi, Sina Asghari","submitted_at":"2025-01-08T22:16:40Z","abstract_excerpt":"This paper examines the specific obstacles of constructing Retrieval-Augmented Generation(RAG) systems in low-resource languages, with a focus on Persian's complicated morphology and versatile syntax. The research aims to improve retrieval and generation accuracy by introducing Persian-specific models, namely MatinaRoberta(a masked language model) and MatinaSRoberta(a fine-tuned Sentence-BERT), along with a comprehensive benchmarking framework. Three datasets-general knowledge(PQuad), scientifically specialized texts, and organizational reports, were used to assess these models after they were"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04858","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/2501.04858/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":"2026-07-05T09:58:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bXJMR+94Mo2Z6FT+HaqrQkNjOwduIc1fPaofmurwtwIriC1OEJHpcBraEUtSdfjUAMhCV3dORkJz50w0PNSMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T11:07:12.479943Z"},"content_sha256":"2e672562e519b7abd1986bea676b117c5e2113cd1b458e688a35390fb704df1c","schema_version":"1.0","event_id":"sha256:2e672562e519b7abd1986bea676b117c5e2113cd1b458e688a35390fb704df1c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OAFZXP2J3HFWYENHZ6TVFG22MA/bundle.json","state_url":"https://pith.science/pith/OAFZXP2J3HFWYENHZ6TVFG22MA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OAFZXP2J3HFWYENHZ6TVFG22MA/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":"2026-08-11T11:07:12Z","links":{"resolver":"https://pith.science/pith/OAFZXP2J3HFWYENHZ6TVFG22MA","bundle":"https://pith.science/pith/OAFZXP2J3HFWYENHZ6TVFG22MA/bundle.json","state":"https://pith.science/pith/OAFZXP2J3HFWYENHZ6TVFG22MA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OAFZXP2J3HFWYENHZ6TVFG22MA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OAFZXP2J3HFWYENHZ6TVFG22MA","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":"1692c60f3de27cdb4cb73eae9f1fb44f9a48c14b8ffa2e2d4cdeff617c191a2c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-08T22:16:40Z","title_canon_sha256":"3ca2dc459f9bfcfa3ab074277c8274604e25a270654ab87431463fa45c5e0cd6"},"schema_version":"1.0","source":{"id":"2501.04858","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04858","created_at":"2026-07-05T09:58:47Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04858v1","created_at":"2026-07-05T09:58:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04858","created_at":"2026-07-05T09:58:47Z"},{"alias_kind":"pith_short_12","alias_value":"OAFZXP2J3HFW","created_at":"2026-07-05T09:58:47Z"},{"alias_kind":"pith_short_16","alias_value":"OAFZXP2J3HFWYENH","created_at":"2026-07-05T09:58:47Z"},{"alias_kind":"pith_short_8","alias_value":"OAFZXP2J","created_at":"2026-07-05T09:58:47Z"}],"graph_snapshots":[{"event_id":"sha256:2e672562e519b7abd1986bea676b117c5e2113cd1b458e688a35390fb704df1c","target":"graph","created_at":"2026-07-05T09:58:47Z","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/2501.04858/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper examines the specific obstacles of constructing Retrieval-Augmented Generation(RAG) systems in low-resource languages, with a focus on Persian's complicated morphology and versatile syntax. The research aims to improve retrieval and generation accuracy by introducing Persian-specific models, namely MatinaRoberta(a masked language model) and MatinaSRoberta(a fine-tuned Sentence-BERT), along with a comprehensive benchmarking framework. Three datasets-general knowledge(PQuad), scientifically specialized texts, and organizational reports, were used to assess these models after they were","authors_text":"Mohammad Ali Seif Kashani, Mohammad Amin Abbasi, Mohammad Hossein Shalchian, Sara Bourbour Hosseinbeigi, Sina Asghari","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-08T22:16:40Z","title":"Advancing Retrieval-Augmented Generation for Persian: Development of Language Models, Comprehensive Benchmarks, and Best Practices for Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04858","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":"sha256:59c1ee2982afc74a0c5c062d30a9da2e96933922a7cb27867de4e8963ef36639","target":"record","created_at":"2026-07-05T09:58:47Z","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":"1692c60f3de27cdb4cb73eae9f1fb44f9a48c14b8ffa2e2d4cdeff617c191a2c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-08T22:16:40Z","title_canon_sha256":"3ca2dc459f9bfcfa3ab074277c8274604e25a270654ab87431463fa45c5e0cd6"},"schema_version":"1.0","source":{"id":"2501.04858","kind":"arxiv","version":1}},"canonical_sha256":"700b9bbf49d9cb6c11a7cfa7529b5a60063bef5c823b7916844b8feb65d2be7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"700b9bbf49d9cb6c11a7cfa7529b5a60063bef5c823b7916844b8feb65d2be7d","first_computed_at":"2026-07-05T09:58:47.607163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:47.607163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Xfc3mOttPbQKxEyraW0TdNw8ycwhRaMU0+3REm3zZeasAmhCH6SkPZj42Z2k4gZa9Z3wVjnGcT/bdbJufV/DA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:47.607623Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.04858","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59c1ee2982afc74a0c5c062d30a9da2e96933922a7cb27867de4e8963ef36639","sha256:2e672562e519b7abd1986bea676b117c5e2113cd1b458e688a35390fb704df1c"],"state_sha256":"3a5a985d8531f6491a8663645fe357ba5a8ffd1cc5f68dabb65920668d4e7a18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Grt2f0p9Ck8GwB90HKVdfUJEsNLdCuMnupm5fNQBoRKz28kiSp1lVoDYSVCGNpnJ4XpZSkFcAJPILfTqpWFbDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T11:07:12.483748Z","bundle_sha256":"49fcf6b1b93cd719e05a9611c8ce515084ab7f105ef421c971e1cba469a3df12"}}