{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:H6GHLVQBDHMZT5PGE5JELZ4ABV","short_pith_number":"pith:H6GHLVQB","canonical_record":{"source":{"id":"2607.09598","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T16:54:38Z","cross_cats_sorted":[],"title_canon_sha256":"72bbd0ed84ec5ac361d8242dc71dfb67a717bf2f341f5e9ec41cabf66245da77","abstract_canon_sha256":"75c0de02754778fee3c85d8973a009eac584f3b2bcede9896e4c4d41ededf9b3"},"schema_version":"1.0"},"canonical_sha256":"3f8c75d60119d999f5e6275245e7800d60943e6972e248193f4ccb2903f6a9e3","source":{"kind":"arxiv","id":"2607.09598","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09598","created_at":"2026-07-13T01:20:22Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09598v1","created_at":"2026-07-13T01:20:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09598","created_at":"2026-07-13T01:20:22Z"},{"alias_kind":"pith_short_12","alias_value":"H6GHLVQBDHMZ","created_at":"2026-07-13T01:20:22Z"},{"alias_kind":"pith_short_16","alias_value":"H6GHLVQBDHMZT5PG","created_at":"2026-07-13T01:20:22Z"},{"alias_kind":"pith_short_8","alias_value":"H6GHLVQB","created_at":"2026-07-13T01:20:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:H6GHLVQBDHMZT5PGE5JELZ4ABV","target":"record","payload":{"canonical_record":{"source":{"id":"2607.09598","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T16:54:38Z","cross_cats_sorted":[],"title_canon_sha256":"72bbd0ed84ec5ac361d8242dc71dfb67a717bf2f341f5e9ec41cabf66245da77","abstract_canon_sha256":"75c0de02754778fee3c85d8973a009eac584f3b2bcede9896e4c4d41ededf9b3"},"schema_version":"1.0"},"canonical_sha256":"3f8c75d60119d999f5e6275245e7800d60943e6972e248193f4ccb2903f6a9e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:20:22.741100Z","signature_b64":"ll0YXZwge9GpxchWS1qruJz/q1w27+EUCRfTqBAe/9ycPc0i4If3U8emjLjAWpRWczN9r/gOtYLRxtXzxJqCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f8c75d60119d999f5e6275245e7800d60943e6972e248193f4ccb2903f6a9e3","last_reissued_at":"2026-07-13T01:20:22.739602Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:20:22.739602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.09598","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":"2026-07-13T01:20:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uLZWhcFyYlbt9DJHWZRwsw5jF6CWAeIncQtSA9HOv+aYXisnjGg4YGJeO3HHbCqVedlzZDGEx+RlNccUmF2DCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T05:09:05.145984Z"},"content_sha256":"b5ce511d5569aa0e68f1b4913fbfa92b0f92c60b604362b1553644d826f67a43","schema_version":"1.0","event_id":"sha256:b5ce511d5569aa0e68f1b4913fbfa92b0f92c60b604362b1553644d826f67a43"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:H6GHLVQBDHMZT5PGE5JELZ4ABV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tokenizer Transplantation: Mitigating Autoregressive Collapse in Edge-Efficient Bengali ASR","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Md. Abdur Rahman, Sanjid Hasan","submitted_at":"2026-07-10T16:54:38Z","abstract_excerpt":"Lightweight speech recognition models are critical for edge deployment, yet highly optimized architectures like Moonshine often fail on morphologically rich, non-Latin languages such as Bengali. This study identifies the root cause of this failure as the model's English-centric byte-level tokenizer, which fragments Bengali words into high-fertility byte chains and triggers catastrophic autoregressive collapse during inference. To resolve this, a novel vocabulary transplantation pipeline is proposed to replace the decoder vocabulary with the native-script BanglaBERT WordPiece vocabulary and res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09598","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/2607.09598/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":"2026-07-13T01:20:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mSDNtru2tlZCAtmzJbKVhhOEljqdncMiLjiRjDZWspfOL6E8t/z6MLTBVxHPtNxOB4iCceKFzzIf+RA7ugmsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T05:09:05.146354Z"},"content_sha256":"37aeb8c38700ad3b31093b09457b65077f3788f5a65d3aef821ee76d4c0d9922","schema_version":"1.0","event_id":"sha256:37aeb8c38700ad3b31093b09457b65077f3788f5a65d3aef821ee76d4c0d9922"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:H6GHLVQBDHMZT5PGE5JELZ4ABV","target":"integrity","payload":{"note":"URL 'https://github.com/Sanjidh090/moonshin' returned status 404 (Not Found) at last check.","snippet":null,"arxiv_id":"2607.09598","detector":"external_links","evidence":{"url":"https://github.com/Sanjidh090/moonshin","final_url":"https://github.com/Sanjidh090/moonshin","host_kind":"github","status_code":404,"status_text":"Not Found","verdict_class":"incontrovertible","checked_at_unix":1783920964.840224},"severity":"critical","ref_index":null,"audited_at":"2026-07-13T05:36:05.083655Z","event_type":"pith.integrity.v1","detected_doi":null,"detector_url":"https://pith.science/pith-integrity-protocol#external_links","external_url":"https://github.com/Sanjidh090/moonshin","finding_type":"dead_code_link","evidence_hash":"378514b73ac7ebb21e10648b155f7b3a6f7ee8b4ecd4a78cf559d64bfdbe46b8","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":12955,"payload_sha256":"5dd61e6c074ce0de96ab373b4e95beffe72bb934c0c93bac2ef9238339782db6","signature_b64":"Q+XzniqFq7yz7r1UmUsF8FIYFyrjwt81UHF/9OG5LNFBbDniN13VfYWHdvPrqCBE1qOGpuI/xgwypkBrNnQBCQ==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-13T05:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"btL4kMcjJ6fN8qZLoaxVyVUDOUfD1tK89mNzaKhSts8iO0fKvCmZgq4W6j4oIm4QBjLL7vrgODFZtAHaZzwHAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T05:09:05.148076Z"},"content_sha256":"9dcc1dbd8aca94d26aeb5e8dc54bf6a00cde7fc7dcf00d1a7fed77de40623571","schema_version":"1.0","event_id":"sha256:9dcc1dbd8aca94d26aeb5e8dc54bf6a00cde7fc7dcf00d1a7fed77de40623571"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H6GHLVQBDHMZT5PGE5JELZ4ABV/bundle.json","state_url":"https://pith.science/pith/H6GHLVQBDHMZT5PGE5JELZ4ABV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H6GHLVQBDHMZT5PGE5JELZ4ABV/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":"2026-08-23T05:09:05Z","links":{"resolver":"https://pith.science/pith/H6GHLVQBDHMZT5PGE5JELZ4ABV","bundle":"https://pith.science/pith/H6GHLVQBDHMZT5PGE5JELZ4ABV/bundle.json","state":"https://pith.science/pith/H6GHLVQBDHMZT5PGE5JELZ4ABV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H6GHLVQBDHMZT5PGE5JELZ4ABV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:H6GHLVQBDHMZT5PGE5JELZ4ABV","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"75c0de02754778fee3c85d8973a009eac584f3b2bcede9896e4c4d41ededf9b3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T16:54:38Z","title_canon_sha256":"72bbd0ed84ec5ac361d8242dc71dfb67a717bf2f341f5e9ec41cabf66245da77"},"schema_version":"1.0","source":{"id":"2607.09598","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09598","created_at":"2026-07-13T01:20:22Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09598v1","created_at":"2026-07-13T01:20:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09598","created_at":"2026-07-13T01:20:22Z"},{"alias_kind":"pith_short_12","alias_value":"H6GHLVQBDHMZ","created_at":"2026-07-13T01:20:22Z"},{"alias_kind":"pith_short_16","alias_value":"H6GHLVQBDHMZT5PG","created_at":"2026-07-13T01:20:22Z"},{"alias_kind":"pith_short_8","alias_value":"H6GHLVQB","created_at":"2026-07-13T01:20:22Z"}],"graph_snapshots":[{"event_id":"sha256:37aeb8c38700ad3b31093b09457b65077f3788f5a65d3aef821ee76d4c0d9922","target":"graph","created_at":"2026-07-13T01:20:22Z","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/2607.09598/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Lightweight speech recognition models are critical for edge deployment, yet highly optimized architectures like Moonshine often fail on morphologically rich, non-Latin languages such as Bengali. This study identifies the root cause of this failure as the model's English-centric byte-level tokenizer, which fragments Bengali words into high-fertility byte chains and triggers catastrophic autoregressive collapse during inference. To resolve this, a novel vocabulary transplantation pipeline is proposed to replace the decoder vocabulary with the native-script BanglaBERT WordPiece vocabulary and res","authors_text":"Md. Abdur Rahman, Sanjid Hasan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T16:54:38Z","title":"Tokenizer Transplantation: Mitigating Autoregressive Collapse in Edge-Efficient Bengali ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09598","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:b5ce511d5569aa0e68f1b4913fbfa92b0f92c60b604362b1553644d826f67a43","target":"record","created_at":"2026-07-13T01:20:22Z","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":"75c0de02754778fee3c85d8973a009eac584f3b2bcede9896e4c4d41ededf9b3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T16:54:38Z","title_canon_sha256":"72bbd0ed84ec5ac361d8242dc71dfb67a717bf2f341f5e9ec41cabf66245da77"},"schema_version":"1.0","source":{"id":"2607.09598","kind":"arxiv","version":1}},"canonical_sha256":"3f8c75d60119d999f5e6275245e7800d60943e6972e248193f4ccb2903f6a9e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f8c75d60119d999f5e6275245e7800d60943e6972e248193f4ccb2903f6a9e3","first_computed_at":"2026-07-13T01:20:22.739602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T01:20:22.739602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ll0YXZwge9GpxchWS1qruJz/q1w27+EUCRfTqBAe/9ycPc0i4If3U8emjLjAWpRWczN9r/gOtYLRxtXzxJqCAQ==","signature_status":"signed_v1","signed_at":"2026-07-13T01:20:22.741100Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.09598","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5ce511d5569aa0e68f1b4913fbfa92b0f92c60b604362b1553644d826f67a43","sha256:37aeb8c38700ad3b31093b09457b65077f3788f5a65d3aef821ee76d4c0d9922","sha256:9dcc1dbd8aca94d26aeb5e8dc54bf6a00cde7fc7dcf00d1a7fed77de40623571"],"state_sha256":"88b87fc3ccc7bc284d8a7afcf6583980e1c8816304224c959d3cdd29182a00fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eO+WkIhM7t9nOwYZyoXuRN0PBSQUhAMkag+zaZY0wkWfhBsotbiPj7P5ac39ZjsYG+AgLm5y6gALAOde2Bj/Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T05:09:05.149511Z","bundle_sha256":"e1edcde0fccdc392bf5c14c967eab1e0d728785bef20abf215baf3e2aa67627c"}}