{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AOQBCISK3S64FCBRBCAHQ5VPHC","short_pith_number":"pith:AOQBCISK","canonical_record":{"source":{"id":"2505.22293","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T12:29:05Z","cross_cats_sorted":[],"title_canon_sha256":"ddcfca575fb45f696fb2f1a49e2c5f818dd313479456e0f8af8c15762a9996fb","abstract_canon_sha256":"9d2ecb819e2b4374ebf69b3e289cc68c92712ced6232fc8211e0f70686530dd4"},"schema_version":"1.0"},"canonical_sha256":"03a011224adcbdc2883108807876af389a5a64f2721b8ef40c31ec26147e83a5","source":{"kind":"arxiv","id":"2505.22293","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22293","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22293v1","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22293","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"pith_short_12","alias_value":"AOQBCISK3S64","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"pith_short_16","alias_value":"AOQBCISK3S64FCBR","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"pith_short_8","alias_value":"AOQBCISK","created_at":"2026-07-05T11:11:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AOQBCISK3S64FCBRBCAHQ5VPHC","target":"record","payload":{"canonical_record":{"source":{"id":"2505.22293","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T12:29:05Z","cross_cats_sorted":[],"title_canon_sha256":"ddcfca575fb45f696fb2f1a49e2c5f818dd313479456e0f8af8c15762a9996fb","abstract_canon_sha256":"9d2ecb819e2b4374ebf69b3e289cc68c92712ced6232fc8211e0f70686530dd4"},"schema_version":"1.0"},"canonical_sha256":"03a011224adcbdc2883108807876af389a5a64f2721b8ef40c31ec26147e83a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:12.664500Z","signature_b64":"Bdd0hCRoEjAlAoB9VpKrDXDYAuoa3pvaEK/3jRzVJhJv1v5gbc5AMdweo6kkXeP2qLO+CdJQNxZ8VHn6oxYJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03a011224adcbdc2883108807876af389a5a64f2721b8ef40c31ec26147e83a5","last_reissued_at":"2026-07-05T11:11:12.663993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:12.663993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.22293","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":"2026-07-05T11:11:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3DJXDSHGLR69HZlFU4Hjo640zuH81mzionTp5i4X+hO3PXIDFd9Yu9lP18r6mlQjxPjDaveNBk+BRmZf5S1MDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:04:57.709179Z"},"content_sha256":"783ff5dbbbe8931742e91d0079da0de12cb9becd3cde06d4e2674164d8d7656b","schema_version":"1.0","event_id":"sha256:783ff5dbbbe8931742e91d0079da0de12cb9becd3cde06d4e2674164d8d7656b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AOQBCISK3S64FCBRBCAHQ5VPHC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compensating for Data with Reasoning: Low-Resource Machine Translation with LLMs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Samuel Frontull, Thomas Str\\\"ohle","submitted_at":"2025-05-28T12:29:05Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated strong capabilities in multilingual machine translation, sometimes even outperforming traditional neural systems. However, previous research has highlighted the challenges of using LLMs, particularly with prompt engineering, for low-resource languages. In this work, we introduce Fragment-Shot Prompting, a novel in-context learning method that segments input and retrieves translation examples based on syntactic coverage, along with Pivoted Fragment-Shot, an extension that enables translation without direct parallel data. We evaluate these methods u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22293","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/2505.22293/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":"2026-07-05T11:11:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1bS9wzisvwYi9+cgNyT2KgEd2eMAI0fGE+X4UW2BsGqkORAkmgNggkxplzul+jbrVT9r7BNiNS0T80o8XUrdAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:04:57.710052Z"},"content_sha256":"512030d19473c28756a4d50521f52903e930068881ce60a9b318a91d3d6aef42","schema_version":"1.0","event_id":"sha256:512030d19473c28756a4d50521f52903e930068881ce60a9b318a91d3d6aef42"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AOQBCISK3S64FCBRBCAHQ5VPHC/bundle.json","state_url":"https://pith.science/pith/AOQBCISK3S64FCBRBCAHQ5VPHC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AOQBCISK3S64FCBRBCAHQ5VPHC/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":"2026-08-09T03:04:57Z","links":{"resolver":"https://pith.science/pith/AOQBCISK3S64FCBRBCAHQ5VPHC","bundle":"https://pith.science/pith/AOQBCISK3S64FCBRBCAHQ5VPHC/bundle.json","state":"https://pith.science/pith/AOQBCISK3S64FCBRBCAHQ5VPHC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AOQBCISK3S64FCBRBCAHQ5VPHC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AOQBCISK3S64FCBRBCAHQ5VPHC","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":"9d2ecb819e2b4374ebf69b3e289cc68c92712ced6232fc8211e0f70686530dd4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T12:29:05Z","title_canon_sha256":"ddcfca575fb45f696fb2f1a49e2c5f818dd313479456e0f8af8c15762a9996fb"},"schema_version":"1.0","source":{"id":"2505.22293","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22293","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22293v1","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22293","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"pith_short_12","alias_value":"AOQBCISK3S64","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"pith_short_16","alias_value":"AOQBCISK3S64FCBR","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"pith_short_8","alias_value":"AOQBCISK","created_at":"2026-07-05T11:11:12Z"}],"graph_snapshots":[{"event_id":"sha256:512030d19473c28756a4d50521f52903e930068881ce60a9b318a91d3d6aef42","target":"graph","created_at":"2026-07-05T11:11:12Z","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/2505.22293/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated strong capabilities in multilingual machine translation, sometimes even outperforming traditional neural systems. However, previous research has highlighted the challenges of using LLMs, particularly with prompt engineering, for low-resource languages. In this work, we introduce Fragment-Shot Prompting, a novel in-context learning method that segments input and retrieves translation examples based on syntactic coverage, along with Pivoted Fragment-Shot, an extension that enables translation without direct parallel data. We evaluate these methods u","authors_text":"Samuel Frontull, Thomas Str\\\"ohle","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T12:29:05Z","title":"Compensating for Data with Reasoning: Low-Resource Machine Translation with LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22293","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":"sha256:783ff5dbbbe8931742e91d0079da0de12cb9becd3cde06d4e2674164d8d7656b","target":"record","created_at":"2026-07-05T11:11:12Z","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":"9d2ecb819e2b4374ebf69b3e289cc68c92712ced6232fc8211e0f70686530dd4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T12:29:05Z","title_canon_sha256":"ddcfca575fb45f696fb2f1a49e2c5f818dd313479456e0f8af8c15762a9996fb"},"schema_version":"1.0","source":{"id":"2505.22293","kind":"arxiv","version":1}},"canonical_sha256":"03a011224adcbdc2883108807876af389a5a64f2721b8ef40c31ec26147e83a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03a011224adcbdc2883108807876af389a5a64f2721b8ef40c31ec26147e83a5","first_computed_at":"2026-07-05T11:11:12.663993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:12.663993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bdd0hCRoEjAlAoB9VpKrDXDYAuoa3pvaEK/3jRzVJhJv1v5gbc5AMdweo6kkXeP2qLO+CdJQNxZ8VHn6oxYJCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:12.664500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22293","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:783ff5dbbbe8931742e91d0079da0de12cb9becd3cde06d4e2674164d8d7656b","sha256:512030d19473c28756a4d50521f52903e930068881ce60a9b318a91d3d6aef42"],"state_sha256":"403e5b73d75504e68b060ef1fdba20cc333886aeba4fb970f8957e50189e873f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZZGDlru6PYl1GHqLHbQrEmIs0IpICAxjkJDJHGLLlQefHk9ETueOz2ZebM3CJOzcMsCSejH8+lFdCAYzGoHDAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:04:57.714488Z","bundle_sha256":"45e3f0018189f66c875d697c2dec88a72190f172f8f196b2f89b0b5960f7edd4"}}