{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AN2ZG527QZYOPHYWDABJD46LLE","short_pith_number":"pith:AN2ZG527","canonical_record":{"source":{"id":"2508.05628","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T17:59:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0266050de7328d0cf4ae83a65d649f219def29f99a9a4215daa5719a30ff5f79","abstract_canon_sha256":"99da4bbcf90ceda80e422a1f693df3ad30cab4923c582dc7b2b73ce3c939dcb3"},"schema_version":"1.0"},"canonical_sha256":"037593775f8670e79f16180291f3cb59239bb78d8f5f82dce06f1fd3935d67fc","source":{"kind":"arxiv","id":"2508.05628","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.05628","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"arxiv_version","alias_value":"2508.05628v1","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05628","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"pith_short_12","alias_value":"AN2ZG527QZYO","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"pith_short_16","alias_value":"AN2ZG527QZYOPHYW","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"pith_short_8","alias_value":"AN2ZG527","created_at":"2026-07-05T11:50:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AN2ZG527QZYOPHYWDABJD46LLE","target":"record","payload":{"canonical_record":{"source":{"id":"2508.05628","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T17:59:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0266050de7328d0cf4ae83a65d649f219def29f99a9a4215daa5719a30ff5f79","abstract_canon_sha256":"99da4bbcf90ceda80e422a1f693df3ad30cab4923c582dc7b2b73ce3c939dcb3"},"schema_version":"1.0"},"canonical_sha256":"037593775f8670e79f16180291f3cb59239bb78d8f5f82dce06f1fd3935d67fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:22.920939Z","signature_b64":"M+fc0npsLKO3oqGxOltayz4ZqQIPVnfnU9sVr6q/ixNjz3jfJ7qNhIL9I7kfy7Dul3mK6r0G1eSX5Py7HHbeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"037593775f8670e79f16180291f3cb59239bb78d8f5f82dce06f1fd3935d67fc","last_reissued_at":"2026-07-05T11:50:22.920479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:22.920479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.05628","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":"2026-07-05T11:50:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ydIXymuL5SuVdkiYyQV2Rcp5u24W77IlcZfGRJFvNV5oq9ooVfz6/Yadllmvypwb77RnqTywjSPW5XfaunumAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:11:10.373363Z"},"content_sha256":"bcf9b9d98dd14e0287761a1ecac86716846724ead45af12a5186233e0da0b8f6","schema_version":"1.0","event_id":"sha256:bcf9b9d98dd14e0287761a1ecac86716846724ead45af12a5186233e0da0b8f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AN2ZG527QZYOPHYWDABJD46LLE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"H-Net++: Hierarchical Dynamic Chunking for Tokenizer-Free Language Modelling in Morphologically-Rich Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mehrdad Zakershahrak, Samira Ghodratnama","submitted_at":"2025-08-07T17:59:01Z","abstract_excerpt":"Byte-level language models eliminate fragile tokenizers but face computational challenges in morphologically-rich languages (MRLs), where words span many bytes. We propose H-NET++, a hierarchical dynamic-chunking model that learns linguistically-informed segmentation through end-to-end training. Key innovations include: (1) a lightweight Transformer context-mixer (1.9M parameters) for cross-chunk attention, (2) a two-level latent hyper-prior for document-level consistency, (3) specialized handling of orthographic artifacts (e.g. Persian ZWNJ), and (4) curriculum-based training with staged sequ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05628","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/2508.05628/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":"2026-07-05T11:50:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kTTvTnBC69bcaA9N25UPyZmXRkVcSd+Vuc/x/be0+ugmxaWFXuMkHinGBhKNnOub501SZO+YwpBlG7a5Uu0/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:11:10.373747Z"},"content_sha256":"32521a3afeb4c284aad05f31ad0975431584c0020f57212cbbd7029c7e430418","schema_version":"1.0","event_id":"sha256:32521a3afeb4c284aad05f31ad0975431584c0020f57212cbbd7029c7e430418"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AN2ZG527QZYOPHYWDABJD46LLE/bundle.json","state_url":"https://pith.science/pith/AN2ZG527QZYOPHYWDABJD46LLE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AN2ZG527QZYOPHYWDABJD46LLE/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":"2026-07-07T15:11:10Z","links":{"resolver":"https://pith.science/pith/AN2ZG527QZYOPHYWDABJD46LLE","bundle":"https://pith.science/pith/AN2ZG527QZYOPHYWDABJD46LLE/bundle.json","state":"https://pith.science/pith/AN2ZG527QZYOPHYWDABJD46LLE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AN2ZG527QZYOPHYWDABJD46LLE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AN2ZG527QZYOPHYWDABJD46LLE","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":"99da4bbcf90ceda80e422a1f693df3ad30cab4923c582dc7b2b73ce3c939dcb3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T17:59:01Z","title_canon_sha256":"0266050de7328d0cf4ae83a65d649f219def29f99a9a4215daa5719a30ff5f79"},"schema_version":"1.0","source":{"id":"2508.05628","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.05628","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"arxiv_version","alias_value":"2508.05628v1","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05628","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"pith_short_12","alias_value":"AN2ZG527QZYO","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"pith_short_16","alias_value":"AN2ZG527QZYOPHYW","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"pith_short_8","alias_value":"AN2ZG527","created_at":"2026-07-05T11:50:22Z"}],"graph_snapshots":[{"event_id":"sha256:32521a3afeb4c284aad05f31ad0975431584c0020f57212cbbd7029c7e430418","target":"graph","created_at":"2026-07-05T11:50:22Z","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/2508.05628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Byte-level language models eliminate fragile tokenizers but face computational challenges in morphologically-rich languages (MRLs), where words span many bytes. We propose H-NET++, a hierarchical dynamic-chunking model that learns linguistically-informed segmentation through end-to-end training. Key innovations include: (1) a lightweight Transformer context-mixer (1.9M parameters) for cross-chunk attention, (2) a two-level latent hyper-prior for document-level consistency, (3) specialized handling of orthographic artifacts (e.g. Persian ZWNJ), and (4) curriculum-based training with staged sequ","authors_text":"Mehrdad Zakershahrak, Samira Ghodratnama","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T17:59:01Z","title":"H-Net++: Hierarchical Dynamic Chunking for Tokenizer-Free Language Modelling in Morphologically-Rich Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05628","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:bcf9b9d98dd14e0287761a1ecac86716846724ead45af12a5186233e0da0b8f6","target":"record","created_at":"2026-07-05T11:50:22Z","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":"99da4bbcf90ceda80e422a1f693df3ad30cab4923c582dc7b2b73ce3c939dcb3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T17:59:01Z","title_canon_sha256":"0266050de7328d0cf4ae83a65d649f219def29f99a9a4215daa5719a30ff5f79"},"schema_version":"1.0","source":{"id":"2508.05628","kind":"arxiv","version":1}},"canonical_sha256":"037593775f8670e79f16180291f3cb59239bb78d8f5f82dce06f1fd3935d67fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"037593775f8670e79f16180291f3cb59239bb78d8f5f82dce06f1fd3935d67fc","first_computed_at":"2026-07-05T11:50:22.920479Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:22.920479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M+fc0npsLKO3oqGxOltayz4ZqQIPVnfnU9sVr6q/ixNjz3jfJ7qNhIL9I7kfy7Dul3mK6r0G1eSX5Py7HHbeDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:22.920939Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.05628","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcf9b9d98dd14e0287761a1ecac86716846724ead45af12a5186233e0da0b8f6","sha256:32521a3afeb4c284aad05f31ad0975431584c0020f57212cbbd7029c7e430418"],"state_sha256":"19a8a760a7c74bf40613945101d213e2b602453a0f0294018d6f2f4b4f12cbcf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Imxll1tKuHY9Ey1yka3H9oMIukHdkQOH3tmjMHEwjIS4CyuoJh+wL4iGLNwnwKAe1mcDW7L9HWWU4+fJtSmUBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:11:10.375701Z","bundle_sha256":"18cf3ce9235248c41919d9fd602d74491dc8afdb094b932271ede290793123ad"}}