{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:S47D2X7VPX44WSRTUO7GXBQRFW","short_pith_number":"pith:S47D2X7V","canonical_record":{"source":{"id":"2607.22456","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-24T16:14:37Z","cross_cats_sorted":[],"title_canon_sha256":"8f2e2bb9ee11db02b58eb450e407f0a731cc00dcecc9431895c6bf9dbcf59645","abstract_canon_sha256":"81cec9a91c32a191f0273980b0a75f15d22ca382c6b73369ce9218874679e196"},"schema_version":"1.0"},"canonical_sha256":"973e3d5ff57df9cb4a33a3be6b86112dbac5866837b93e9f3c85a4f87abc42e7","source":{"kind":"arxiv","id":"2607.22456","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22456","created_at":"2026-07-27T01:21:22Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22456v1","created_at":"2026-07-27T01:21:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22456","created_at":"2026-07-27T01:21:22Z"},{"alias_kind":"pith_short_12","alias_value":"S47D2X7VPX44","created_at":"2026-07-27T01:21:22Z"},{"alias_kind":"pith_short_16","alias_value":"S47D2X7VPX44WSRT","created_at":"2026-07-27T01:21:22Z"},{"alias_kind":"pith_short_8","alias_value":"S47D2X7V","created_at":"2026-07-27T01:21:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:S47D2X7VPX44WSRTUO7GXBQRFW","target":"record","payload":{"canonical_record":{"source":{"id":"2607.22456","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-24T16:14:37Z","cross_cats_sorted":[],"title_canon_sha256":"8f2e2bb9ee11db02b58eb450e407f0a731cc00dcecc9431895c6bf9dbcf59645","abstract_canon_sha256":"81cec9a91c32a191f0273980b0a75f15d22ca382c6b73369ce9218874679e196"},"schema_version":"1.0"},"canonical_sha256":"973e3d5ff57df9cb4a33a3be6b86112dbac5866837b93e9f3c85a4f87abc42e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:21:22.026156Z","signature_b64":"URggnahcV33Lh5mZHTMfSQxWVyHsBEUpA4JOwI1gSeNyxH6Cr/CD3ed6NKytG1bst58+OOE8qVXpugxJVRaACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"973e3d5ff57df9cb4a33a3be6b86112dbac5866837b93e9f3c85a4f87abc42e7","last_reissued_at":"2026-07-27T01:21:22.025304Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:21:22.025304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.22456","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":"2026-07-27T01:21:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L2JwFNCGdCobgyDQucXMuYUg1W3X5JGZTKXUHbnnWjbCBxDHpN/q93+8+YIrajx2H0vuHJVVIiok7n3IWbCfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:12:54.924833Z"},"content_sha256":"a1b63afabe9b09c5644bd07b7ac2ca5977c03f08cd805c91246335a85328009d","schema_version":"1.0","event_id":"sha256:a1b63afabe9b09c5644bd07b7ac2ca5977c03f08cd805c91246335a85328009d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:S47D2X7VPX44WSRTUO7GXBQRFW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"grapheme-kit: Grapheme-Level Metrics and Text Processing for Multilingual NLP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashini Kavindya, Izzath Nisfer, Menan Velayuthan, Ovindu Atukorala, Purushoth Velayuthan","submitted_at":"2026-07-24T16:14:37Z","abstract_excerpt":"Existing lexical distance, similarity, and evaluation metrics operate on Unicode code points, which can misrepresent errors in writing systems where a single grapheme is represented by multiple Unicode code points. We introduce grapheme-kit, an open-source Python library that extends these metrics to operate on grapheme clusters instead. The library also provides improved grapheme processing for Tamil and Sinhala, including accurate grapheme cluster identification and grapheme composition/decomposition utilities. Through an OCR case study, we demonstrate that grapheme-level metrics provide a m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22456","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/2607.22456/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":"2026-07-27T01:21:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wSZPnQESuYeUh2ara0/qNZ1xCZ6BXXeNaN1sRMTjRvtiWRQeyyCniRS8r4rztdXFPXC3/eGaTjUjyUm6SOJSAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:12:54.925342Z"},"content_sha256":"91809d596eebc318e85cbc81d8a0669c2117c1c2412305e371f28a126b12a0da","schema_version":"1.0","event_id":"sha256:91809d596eebc318e85cbc81d8a0669c2117c1c2412305e371f28a126b12a0da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S47D2X7VPX44WSRTUO7GXBQRFW/bundle.json","state_url":"https://pith.science/pith/S47D2X7VPX44WSRTUO7GXBQRFW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S47D2X7VPX44WSRTUO7GXBQRFW/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":"2026-08-10T03:12:54Z","links":{"resolver":"https://pith.science/pith/S47D2X7VPX44WSRTUO7GXBQRFW","bundle":"https://pith.science/pith/S47D2X7VPX44WSRTUO7GXBQRFW/bundle.json","state":"https://pith.science/pith/S47D2X7VPX44WSRTUO7GXBQRFW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S47D2X7VPX44WSRTUO7GXBQRFW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:S47D2X7VPX44WSRTUO7GXBQRFW","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":"81cec9a91c32a191f0273980b0a75f15d22ca382c6b73369ce9218874679e196","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-24T16:14:37Z","title_canon_sha256":"8f2e2bb9ee11db02b58eb450e407f0a731cc00dcecc9431895c6bf9dbcf59645"},"schema_version":"1.0","source":{"id":"2607.22456","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22456","created_at":"2026-07-27T01:21:22Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22456v1","created_at":"2026-07-27T01:21:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22456","created_at":"2026-07-27T01:21:22Z"},{"alias_kind":"pith_short_12","alias_value":"S47D2X7VPX44","created_at":"2026-07-27T01:21:22Z"},{"alias_kind":"pith_short_16","alias_value":"S47D2X7VPX44WSRT","created_at":"2026-07-27T01:21:22Z"},{"alias_kind":"pith_short_8","alias_value":"S47D2X7V","created_at":"2026-07-27T01:21:22Z"}],"graph_snapshots":[{"event_id":"sha256:91809d596eebc318e85cbc81d8a0669c2117c1c2412305e371f28a126b12a0da","target":"graph","created_at":"2026-07-27T01:21:22Z","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/2607.22456/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing lexical distance, similarity, and evaluation metrics operate on Unicode code points, which can misrepresent errors in writing systems where a single grapheme is represented by multiple Unicode code points. We introduce grapheme-kit, an open-source Python library that extends these metrics to operate on grapheme clusters instead. The library also provides improved grapheme processing for Tamil and Sinhala, including accurate grapheme cluster identification and grapheme composition/decomposition utilities. Through an OCR case study, we demonstrate that grapheme-level metrics provide a m","authors_text":"Ashini Kavindya, Izzath Nisfer, Menan Velayuthan, Ovindu Atukorala, Purushoth Velayuthan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-24T16:14:37Z","title":"grapheme-kit: Grapheme-Level Metrics and Text Processing for Multilingual NLP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22456","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:a1b63afabe9b09c5644bd07b7ac2ca5977c03f08cd805c91246335a85328009d","target":"record","created_at":"2026-07-27T01:21:22Z","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":"81cec9a91c32a191f0273980b0a75f15d22ca382c6b73369ce9218874679e196","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-24T16:14:37Z","title_canon_sha256":"8f2e2bb9ee11db02b58eb450e407f0a731cc00dcecc9431895c6bf9dbcf59645"},"schema_version":"1.0","source":{"id":"2607.22456","kind":"arxiv","version":1}},"canonical_sha256":"973e3d5ff57df9cb4a33a3be6b86112dbac5866837b93e9f3c85a4f87abc42e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"973e3d5ff57df9cb4a33a3be6b86112dbac5866837b93e9f3c85a4f87abc42e7","first_computed_at":"2026-07-27T01:21:22.025304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T01:21:22.025304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"URggnahcV33Lh5mZHTMfSQxWVyHsBEUpA4JOwI1gSeNyxH6Cr/CD3ed6NKytG1bst58+OOE8qVXpugxJVRaACg==","signature_status":"signed_v1","signed_at":"2026-07-27T01:21:22.026156Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22456","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1b63afabe9b09c5644bd07b7ac2ca5977c03f08cd805c91246335a85328009d","sha256:91809d596eebc318e85cbc81d8a0669c2117c1c2412305e371f28a126b12a0da"],"state_sha256":"218345ddb14c29425e80edf66ba136caacee1314ebd5956f706eb936ee91469d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J2b1mKXLRjdb/fsuo7YKiG61nPFYKp8X5PflpKZVNHDZKjpXUES02ydDtjbKk3NPNQ8aUQykGFW8AgrFzXUMDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T03:12:54.930568Z","bundle_sha256":"1dcab4edca2fe92ad2a960318f9014acc4d2f77193a2e2672fcb1ffdf2c6ba11"}}