{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KZEWYUAQRQEGRTWI5LD65MKBD2","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":"ed121a0b87396301142dac63fc91cf2ec97d8871ef9dbc34651cd3df2a10e49f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-25T23:06:20Z","title_canon_sha256":"ba04b45eb177f302baf153f4db5c6d198063b8a17e51a40e861649dc05d85f51"},"schema_version":"1.0","source":{"id":"2505.19356","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19356","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19356v2","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19356","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"pith_short_12","alias_value":"KZEWYUAQRQEG","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"pith_short_16","alias_value":"KZEWYUAQRQEGRTWI","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"pith_short_8","alias_value":"KZEWYUAQ","created_at":"2026-07-05T11:19:07Z"}],"graph_snapshots":[{"event_id":"sha256:25eec025b312a011d45a379a07c4a15748fde0e26f161721019b05357d1d3653","target":"graph","created_at":"2026-07-05T11:19:07Z","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/2505.19356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural retrieval methods using transformer-based pre-trained language models have advanced multilingual and cross-lingual retrieval. However, their effectiveness for low-resource, morphologically rich languages such as Amharic remains underexplored due to data scarcity and suboptimal tokenization. We address this gap by introducing Amharic-specific dense retrieval models based on pre-trained Amharic BERT and RoBERTa backbones. Our proposed RoBERTa-Base-Amharic-Embed model (110M parameters) achieves a 17.6% relative improvement in MRR@10 and a 9.86% gain in Recall@10 over the strongest multilin","authors_text":"Kidist Amde Mekonnen, Maarten de Rijke, Yosef Worku Alemneh","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-25T23:06:20Z","title":"Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19356","kind":"arxiv","version":2},"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:a6bcf3ba7f58cb49d9e32996e00f4cb409deb6ff51f26d8b4821507af91e03e0","target":"record","created_at":"2026-07-05T11:19:07Z","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":"ed121a0b87396301142dac63fc91cf2ec97d8871ef9dbc34651cd3df2a10e49f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-25T23:06:20Z","title_canon_sha256":"ba04b45eb177f302baf153f4db5c6d198063b8a17e51a40e861649dc05d85f51"},"schema_version":"1.0","source":{"id":"2505.19356","kind":"arxiv","version":2}},"canonical_sha256":"56496c50108c0868cec8eac7eeb1411eb824d09be6588daa28e952bccde30bbd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56496c50108c0868cec8eac7eeb1411eb824d09be6588daa28e952bccde30bbd","first_computed_at":"2026-07-05T11:19:07.470402Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:07.470402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tdRmhKDr2b3P+35p/9ypTFgKEZuuy9s+BX9UN6Mp3+avyi33OPl8FA9p5L2lRTqvjZMeECpurp+NQNbPg1HgCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:07.470850Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19356","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6bcf3ba7f58cb49d9e32996e00f4cb409deb6ff51f26d8b4821507af91e03e0","sha256:25eec025b312a011d45a379a07c4a15748fde0e26f161721019b05357d1d3653"],"state_sha256":"8b4797fd3be84031638c5ab4c3cf7fd537368ad7aa9d7b67eeb1942a0be99f0e"}