{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BJ4URPVH5DB7KU2CCUZHKEYZAQ","short_pith_number":"pith:BJ4URPVH","canonical_record":{"source":{"id":"2503.14433","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-18T17:11:09Z","cross_cats_sorted":[],"title_canon_sha256":"e7cd2a40168b9870fe762a44361e791e0d8f69e15ec79a8ac6b81cafda04edf4","abstract_canon_sha256":"653bd9d9761b01160cafbaa1fa5777ca4c640e78ac0fff9b25cec6f4eca339ab"},"schema_version":"1.0"},"canonical_sha256":"0a7948bea7e8c3f5534215327513190419605dea6ca7005951b7f312c84b11f7","source":{"kind":"arxiv","id":"2503.14433","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.14433","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"arxiv_version","alias_value":"2503.14433v2","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14433","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"pith_short_12","alias_value":"BJ4URPVH5DB7","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"pith_short_16","alias_value":"BJ4URPVH5DB7KU2C","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"pith_short_8","alias_value":"BJ4URPVH","created_at":"2026-07-05T11:14:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BJ4URPVH5DB7KU2CCUZHKEYZAQ","target":"record","payload":{"canonical_record":{"source":{"id":"2503.14433","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-18T17:11:09Z","cross_cats_sorted":[],"title_canon_sha256":"e7cd2a40168b9870fe762a44361e791e0d8f69e15ec79a8ac6b81cafda04edf4","abstract_canon_sha256":"653bd9d9761b01160cafbaa1fa5777ca4c640e78ac0fff9b25cec6f4eca339ab"},"schema_version":"1.0"},"canonical_sha256":"0a7948bea7e8c3f5534215327513190419605dea6ca7005951b7f312c84b11f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:28.122123Z","signature_b64":"dfo5XqfvREQ09l/6actzauj5MrApoWUZf9DRTYSwZ9am5U/1nx2XuSbcwylfesz4kAGkvFBtHFK/Uld3uoFbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a7948bea7e8c3f5534215327513190419605dea6ca7005951b7f312c84b11f7","last_reissued_at":"2026-07-05T11:14:28.121624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:28.121624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.14433","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:14:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XyDsyCt0HNGs7Vah08Rco1g+RLktWN6Xh2CTJxQ7guQ74/mFmTmoFPB/A0hJlwvVXbjYtoXfvF9xsAA5QAVcAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:57:08.242215Z"},"content_sha256":"a97ca700934027aa01b87bd6d5b1d2d9f9a86693cb9d0809698eea55745e893e","schema_version":"1.0","event_id":"sha256:a97ca700934027aa01b87bd6d5b1d2d9f9a86693cb9d0809698eea55745e893e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BJ4URPVH5DB7KU2CCUZHKEYZAQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Splintering Nonconcatenative Languages for Better Tokenization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"(2) DICTA), Avi Shmidman (2), Bar Gazit (1), Shaltiel Shmidman (2), Yuval Pinter (1) ((1) Ben-Gurion University of the Negev","submitted_at":"2025-03-18T17:11:09Z","abstract_excerpt":"Common subword tokenization algorithms like BPE and UnigramLM assume that text can be split into meaningful units by concatenative measures alone. This is not true for languages such as Hebrew and Arabic, where morphology is encoded in root-template patterns, or Malay and Georgian, where split affixes are common. We present SPLINTER, a pre-processing step which rearranges text into a linear form that better represents such nonconcatenative morphologies, enabling meaningful contiguous segments to be found by the tokenizer. We demonstrate SPLINTER's merit using both intrinsic measures evaluating"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14433","kind":"arxiv","version":2},"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/2503.14433/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":"2026-07-05T11:14:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vC+KZ1EztSWJF4dFRHw5YPJyuaczxKHve9+jK7KEfKIl67tUwNad0Y4PWEEdsZqnFMGuLes23EsFCv+6D3emBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:57:08.242722Z"},"content_sha256":"595188ef8362e3c80a646d59c34003f108367ed5a50f4b5bf673af892f45eb6d","schema_version":"1.0","event_id":"sha256:595188ef8362e3c80a646d59c34003f108367ed5a50f4b5bf673af892f45eb6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BJ4URPVH5DB7KU2CCUZHKEYZAQ/bundle.json","state_url":"https://pith.science/pith/BJ4URPVH5DB7KU2CCUZHKEYZAQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BJ4URPVH5DB7KU2CCUZHKEYZAQ/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":"2026-08-08T15:57:08Z","links":{"resolver":"https://pith.science/pith/BJ4URPVH5DB7KU2CCUZHKEYZAQ","bundle":"https://pith.science/pith/BJ4URPVH5DB7KU2CCUZHKEYZAQ/bundle.json","state":"https://pith.science/pith/BJ4URPVH5DB7KU2CCUZHKEYZAQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BJ4URPVH5DB7KU2CCUZHKEYZAQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BJ4URPVH5DB7KU2CCUZHKEYZAQ","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":"653bd9d9761b01160cafbaa1fa5777ca4c640e78ac0fff9b25cec6f4eca339ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-18T17:11:09Z","title_canon_sha256":"e7cd2a40168b9870fe762a44361e791e0d8f69e15ec79a8ac6b81cafda04edf4"},"schema_version":"1.0","source":{"id":"2503.14433","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.14433","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"arxiv_version","alias_value":"2503.14433v2","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14433","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"pith_short_12","alias_value":"BJ4URPVH5DB7","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"pith_short_16","alias_value":"BJ4URPVH5DB7KU2C","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"pith_short_8","alias_value":"BJ4URPVH","created_at":"2026-07-05T11:14:28Z"}],"graph_snapshots":[{"event_id":"sha256:595188ef8362e3c80a646d59c34003f108367ed5a50f4b5bf673af892f45eb6d","target":"graph","created_at":"2026-07-05T11:14:28Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.14433/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Common subword tokenization algorithms like BPE and UnigramLM assume that text can be split into meaningful units by concatenative measures alone. This is not true for languages such as Hebrew and Arabic, where morphology is encoded in root-template patterns, or Malay and Georgian, where split affixes are common. We present SPLINTER, a pre-processing step which rearranges text into a linear form that better represents such nonconcatenative morphologies, enabling meaningful contiguous segments to be found by the tokenizer. We demonstrate SPLINTER's merit using both intrinsic measures evaluating","authors_text":"(2) DICTA), Avi Shmidman (2), Bar Gazit (1), Shaltiel Shmidman (2), Yuval Pinter (1) ((1) Ben-Gurion University of the Negev","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-18T17:11:09Z","title":"Splintering Nonconcatenative Languages for Better Tokenization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14433","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:a97ca700934027aa01b87bd6d5b1d2d9f9a86693cb9d0809698eea55745e893e","target":"record","created_at":"2026-07-05T11:14:28Z","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":"653bd9d9761b01160cafbaa1fa5777ca4c640e78ac0fff9b25cec6f4eca339ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-18T17:11:09Z","title_canon_sha256":"e7cd2a40168b9870fe762a44361e791e0d8f69e15ec79a8ac6b81cafda04edf4"},"schema_version":"1.0","source":{"id":"2503.14433","kind":"arxiv","version":2}},"canonical_sha256":"0a7948bea7e8c3f5534215327513190419605dea6ca7005951b7f312c84b11f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a7948bea7e8c3f5534215327513190419605dea6ca7005951b7f312c84b11f7","first_computed_at":"2026-07-05T11:14:28.121624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:28.121624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dfo5XqfvREQ09l/6actzauj5MrApoWUZf9DRTYSwZ9am5U/1nx2XuSbcwylfesz4kAGkvFBtHFK/Uld3uoFbDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:28.122123Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.14433","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a97ca700934027aa01b87bd6d5b1d2d9f9a86693cb9d0809698eea55745e893e","sha256:595188ef8362e3c80a646d59c34003f108367ed5a50f4b5bf673af892f45eb6d"],"state_sha256":"22a2de17deff4476eb1d359aa33b8ead28d1955c5ddf0f493985c65e51da00fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XmN+aAJ4xUlDRd+EoYFD9ikZbXs34R3c0VV3FMQFPO5S7fNg/9dyQhCMXHEQZ9sHK+zuwK+xOy3KwI4/SVAPAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T15:57:08.246880Z","bundle_sha256":"bb012407c402986f0ef7e0ce2b8382817d1285ab3073a73b78cb2a2e3b2463d6"}}