{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XN67PDONNH5GZSZ5FBTU2DQKMZ","short_pith_number":"pith:XN67PDON","canonical_record":{"source":{"id":"2406.13560","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T13:48:19Z","cross_cats_sorted":[],"title_canon_sha256":"409a9915de822614696af5872655c73f5f31dc5db86c70b7549c1b898aa0a5af","abstract_canon_sha256":"b523d68798cdd8ecac860819d0434efa955fc396ca6f811851560a45f5a1cea6"},"schema_version":"1.0"},"canonical_sha256":"bb7df78dcd69fa6ccb3d28674d0e0a6669f9e408c5abd65832e9c9ec8fcf2b28","source":{"kind":"arxiv","id":"2406.13560","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.13560","created_at":"2026-07-05T09:15:11Z"},{"alias_kind":"arxiv_version","alias_value":"2406.13560v2","created_at":"2026-07-05T09:15:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13560","created_at":"2026-07-05T09:15:11Z"},{"alias_kind":"pith_short_12","alias_value":"XN67PDONNH5G","created_at":"2026-07-05T09:15:11Z"},{"alias_kind":"pith_short_16","alias_value":"XN67PDONNH5GZSZ5","created_at":"2026-07-05T09:15:11Z"},{"alias_kind":"pith_short_8","alias_value":"XN67PDON","created_at":"2026-07-05T09:15:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XN67PDONNH5GZSZ5FBTU2DQKMZ","target":"record","payload":{"canonical_record":{"source":{"id":"2406.13560","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T13:48:19Z","cross_cats_sorted":[],"title_canon_sha256":"409a9915de822614696af5872655c73f5f31dc5db86c70b7549c1b898aa0a5af","abstract_canon_sha256":"b523d68798cdd8ecac860819d0434efa955fc396ca6f811851560a45f5a1cea6"},"schema_version":"1.0"},"canonical_sha256":"bb7df78dcd69fa6ccb3d28674d0e0a6669f9e408c5abd65832e9c9ec8fcf2b28","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:11.970980Z","signature_b64":"i5CqSybySKQ7ya+si5nFjuykgfAb3HSfahiOOY8TK8flS/xrFt8eTV0VETCG85XCYtEgF8+E09W56+ftH0tbCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb7df78dcd69fa6ccb3d28674d0e0a6669f9e408c5abd65832e9c9ec8fcf2b28","last_reissued_at":"2026-07-05T09:15:11.970570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:11.970570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.13560","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":"2026-07-05T09:15:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kMqG0VwxwJwa3cQVwqIaRdCveDbJBa1OBpQ1oJ0ASdFCBF6LGuifoo4wmyY+lNhOUJrzSIWbyqMDJ/cZQAx8DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:35:08.482746Z"},"content_sha256":"729ba8d72e46bb3c47752485e44b773683dd478f60eda2c5665b3e96c7fae9d4","schema_version":"1.0","event_id":"sha256:729ba8d72e46bb3c47752485e44b773683dd478f60eda2c5665b3e96c7fae9d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XN67PDONNH5GZSZ5FBTU2DQKMZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lexically Grounded Subword Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jind\\v{r}ich Helcl, Jind\\v{r}ich Libovick\\'y","submitted_at":"2024-06-19T13:48:19Z","abstract_excerpt":"We present three innovations in tokenization and subword segmentation. First, we propose to use unsupervised morphological analysis with Morfessor as pre-tokenization. Second, we present an algebraic method for obtaining subword embeddings grounded in a word embedding space. Based on that, we design a novel subword segmentation algorithm that uses the embeddings, ensuring that the procedure considers lexical meaning. Third, we introduce an efficient segmentation algorithm based on a subword bigram model that can be initialized with the lexically aware segmentation method to avoid using Morfess"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13560","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/2406.13560/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":"2026-07-05T09:15:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KuI8BpAqj3o5w3EvbEsZEUzE+zzez7moatstZqoYpTV7H+qNUikRWDeBAZhnd4HIo7CNLKT9UswewSHBIUZSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:35:08.483051Z"},"content_sha256":"7e3b2b7b9325153bb126fc93e350ba78810416272f57cf3f2ebd952f12fd602b","schema_version":"1.0","event_id":"sha256:7e3b2b7b9325153bb126fc93e350ba78810416272f57cf3f2ebd952f12fd602b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XN67PDONNH5GZSZ5FBTU2DQKMZ/bundle.json","state_url":"https://pith.science/pith/XN67PDONNH5GZSZ5FBTU2DQKMZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XN67PDONNH5GZSZ5FBTU2DQKMZ/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":"2026-08-17T14:35:08Z","links":{"resolver":"https://pith.science/pith/XN67PDONNH5GZSZ5FBTU2DQKMZ","bundle":"https://pith.science/pith/XN67PDONNH5GZSZ5FBTU2DQKMZ/bundle.json","state":"https://pith.science/pith/XN67PDONNH5GZSZ5FBTU2DQKMZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XN67PDONNH5GZSZ5FBTU2DQKMZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XN67PDONNH5GZSZ5FBTU2DQKMZ","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":"b523d68798cdd8ecac860819d0434efa955fc396ca6f811851560a45f5a1cea6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T13:48:19Z","title_canon_sha256":"409a9915de822614696af5872655c73f5f31dc5db86c70b7549c1b898aa0a5af"},"schema_version":"1.0","source":{"id":"2406.13560","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.13560","created_at":"2026-07-05T09:15:11Z"},{"alias_kind":"arxiv_version","alias_value":"2406.13560v2","created_at":"2026-07-05T09:15:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13560","created_at":"2026-07-05T09:15:11Z"},{"alias_kind":"pith_short_12","alias_value":"XN67PDONNH5G","created_at":"2026-07-05T09:15:11Z"},{"alias_kind":"pith_short_16","alias_value":"XN67PDONNH5GZSZ5","created_at":"2026-07-05T09:15:11Z"},{"alias_kind":"pith_short_8","alias_value":"XN67PDON","created_at":"2026-07-05T09:15:11Z"}],"graph_snapshots":[{"event_id":"sha256:7e3b2b7b9325153bb126fc93e350ba78810416272f57cf3f2ebd952f12fd602b","target":"graph","created_at":"2026-07-05T09:15:11Z","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/2406.13560/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present three innovations in tokenization and subword segmentation. First, we propose to use unsupervised morphological analysis with Morfessor as pre-tokenization. Second, we present an algebraic method for obtaining subword embeddings grounded in a word embedding space. Based on that, we design a novel subword segmentation algorithm that uses the embeddings, ensuring that the procedure considers lexical meaning. Third, we introduce an efficient segmentation algorithm based on a subword bigram model that can be initialized with the lexically aware segmentation method to avoid using Morfess","authors_text":"Jind\\v{r}ich Helcl, Jind\\v{r}ich Libovick\\'y","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T13:48:19Z","title":"Lexically Grounded Subword Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13560","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":"sha256:729ba8d72e46bb3c47752485e44b773683dd478f60eda2c5665b3e96c7fae9d4","target":"record","created_at":"2026-07-05T09:15:11Z","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":"b523d68798cdd8ecac860819d0434efa955fc396ca6f811851560a45f5a1cea6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T13:48:19Z","title_canon_sha256":"409a9915de822614696af5872655c73f5f31dc5db86c70b7549c1b898aa0a5af"},"schema_version":"1.0","source":{"id":"2406.13560","kind":"arxiv","version":2}},"canonical_sha256":"bb7df78dcd69fa6ccb3d28674d0e0a6669f9e408c5abd65832e9c9ec8fcf2b28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb7df78dcd69fa6ccb3d28674d0e0a6669f9e408c5abd65832e9c9ec8fcf2b28","first_computed_at":"2026-07-05T09:15:11.970570Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:11.970570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i5CqSybySKQ7ya+si5nFjuykgfAb3HSfahiOOY8TK8flS/xrFt8eTV0VETCG85XCYtEgF8+E09W56+ftH0tbCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:11.970980Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.13560","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:729ba8d72e46bb3c47752485e44b773683dd478f60eda2c5665b3e96c7fae9d4","sha256:7e3b2b7b9325153bb126fc93e350ba78810416272f57cf3f2ebd952f12fd602b"],"state_sha256":"65b6c10722e0f34929326999c7e0dd63df262f222064d32b4b8d96b23931f15e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+ej2Qn5WuLMt212xSGcxHLVkzPuPwvjT0gVBnMusGQHlJwmM0CRu2BwmsqNYWe4igG3nlOG3N89/BcMcwzyyDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T14:35:08.485747Z","bundle_sha256":"991cea461f2d45e0ea5f6741a59f143a504234d9606cc1c0364791e45447857c"}}