{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TXAUUGXTYJOAVNWP6DGYIWDHTZ","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":"0795e511740c72ea4e04afd40cc13e830b9c9ccf021d99dd85931f7131336435","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-16T08:43:01Z","title_canon_sha256":"3e8846d19b2b787459b172fa9418d9d894a88af412677d7d4baaa904fd1ae6e1"},"schema_version":"1.0","source":{"id":"2605.16881","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16881","created_at":"2026-05-20T00:03:28Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16881v1","created_at":"2026-05-20T00:03:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16881","created_at":"2026-05-20T00:03:28Z"},{"alias_kind":"pith_short_12","alias_value":"TXAUUGXTYJOA","created_at":"2026-05-20T00:03:28Z"},{"alias_kind":"pith_short_16","alias_value":"TXAUUGXTYJOAVNWP","created_at":"2026-05-20T00:03:28Z"},{"alias_kind":"pith_short_8","alias_value":"TXAUUGXT","created_at":"2026-05-20T00:03:28Z"}],"graph_snapshots":[{"event_id":"sha256:2ac2a71e891e1859828aeffb4c280e3c5f90e65a04fc9e8e9704d36de4bd0813","target":"graph","created_at":"2026-05-20T00:03:28Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The broader contribution is methodological: PaliBench shows how existing scholarly translations can be transformed into evaluation infrastructure for interpretive textual traditions without treating any single translation as definitive."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that LLM-assisted alignment of independently segmented translations, automated verification, passage-level quality filtering, and deduplication produce a reliable, unbiased multi-reference dataset that faithfully captures interpretive variation across the three human translations."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PaliBench is a multi-reference benchmark for Pali-to-English translation built from 1,700 aligned passages of the Sutta Pitaka using three scholarly translations to evaluate LLMs with complementary metrics."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"PaliBench shows how to build multi-reference benchmarks for classical language translation from existing scholarly translations without treating any one as definitive."}],"snapshot_sha256":"58a6c0f7a21424a960cfbd7892599353d3251e75083bc22cbd4a62c325eb2266"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"a397278901d037335e7feeb6e0cb92d53f6b97b85feaac29efa1dbd07ca5fcf6"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.183659Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T21:11:37.242047Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.290631Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.368031Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16881/integrity.json","findings":[],"snapshot_sha256":"27727e008c155e263c2cb1bea3eb3dca9234344b9017291595d27597933d4c6c","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Digital humanities projects increasingly rely on machine translation and large language models to widen access to classical, religious, and otherwise under-translated textual traditions. Yet standard translation benchmarks are poorly suited to such materials: they typically compare a system output against a single reference translation, even though classical texts often support multiple faithful renderings that differ in terminology, register, and interpretation. This article introduces PaliBench, both a benchmark for Pali-to-English translation and a reusable method for constructing multi-ref","authors_text":"M\\'at\\'e Metzger, Nadnapang Phophichit","cross_cats":[],"headline":"PaliBench shows how to build multi-reference benchmarks for classical language translation from existing scholarly translations without treating any one as definitive.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-16T08:43:01Z","title":"PaliBench: A Multi-Reference Blueprint for Classical Language Translation Benchmarks"},"references":{"count":38,"internal_anchors":0,"resolved_work":38,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Frequently Asked Questions About Access to Insight , year =","work_id":"4f19a98b-41ca-46b4-ba08-5fd55274d8ee","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Nature , volume =","work_id":"687d6744-5f52-4fd0-b593-bfce152bc37e","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Bamman, David and Burns, Patrick J. , title =. 2020 , note =","work_id":"aaacc914-b24d-41cf-bac1-19774e5001fd","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Bodhi, Bhikkhu , title =","work_id":"b79a5572-9912-43db-83bb-e35cbc5a950f","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"The Middle Length Discourses of the Buddha: A Translation of the Majjhima Nik","work_id":"508e12a3-1de2-43be-9e27-19b166d8e7b9","year":null}],"snapshot_sha256":"9cc3e6aadbd7ec74d67e34bae28e00ec98a5e498b2aa2408700f1810e6ddf924"},"source":{"id":"2605.16881","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T21:00:33.716397Z","id":"f679905b-abc4-48e4-ac5c-d71639a7d3c4","model_set":{"reader":"grok-4.3"},"one_line_summary":"PaliBench is a multi-reference benchmark for Pali-to-English translation built from 1,700 aligned passages of the Sutta Pitaka using three scholarly translations to evaluate LLMs with complementary metrics.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"PaliBench shows how to build multi-reference benchmarks for classical language translation from existing scholarly translations without treating any one as definitive.","strongest_claim":"The broader contribution is methodological: PaliBench shows how existing scholarly translations can be transformed into evaluation infrastructure for interpretive textual traditions without treating any single translation as definitive.","weakest_assumption":"The assumption that LLM-assisted alignment of independently segmented translations, automated verification, passage-level quality filtering, and deduplication produce a reliable, unbiased multi-reference dataset that faithfully captures interpretive variation across the three human translations."}},"verdict_id":"f679905b-abc4-48e4-ac5c-d71639a7d3c4"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d11e5e040edf86158ced5b4a99dbfd9096277abf9b8fab24467325bb1c0ed484","target":"record","created_at":"2026-05-20T00:03:28Z","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":"0795e511740c72ea4e04afd40cc13e830b9c9ccf021d99dd85931f7131336435","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-16T08:43:01Z","title_canon_sha256":"3e8846d19b2b787459b172fa9418d9d894a88af412677d7d4baaa904fd1ae6e1"},"schema_version":"1.0","source":{"id":"2605.16881","kind":"arxiv","version":1}},"canonical_sha256":"9dc14a1af3c25c0ab6cff0cd8458679e7bbc13a27ce1709e4e12dea71aee4c90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9dc14a1af3c25c0ab6cff0cd8458679e7bbc13a27ce1709e4e12dea71aee4c90","first_computed_at":"2026-05-20T00:03:28.006165Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:28.006165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y8oJX38pKqMae6a6/OaiD7a58sxsq0+EW4IwAmK/3C8lSD0r90fXWe5kcNrPZE7po4OJn8Azwgvwf1M3qnDhAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:28.007020Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16881","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d11e5e040edf86158ced5b4a99dbfd9096277abf9b8fab24467325bb1c0ed484","sha256:2ac2a71e891e1859828aeffb4c280e3c5f90e65a04fc9e8e9704d36de4bd0813"],"state_sha256":"25729868ec550469152fd1132440f92722b5e1d83ada9f668158d83fc48d120c"}