{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NJQEKCXJV76GFIXRJKAWTYMYXT","short_pith_number":"pith:NJQEKCXJ","canonical_record":{"source":{"id":"2412.15471","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T00:56:13Z","cross_cats_sorted":[],"title_canon_sha256":"6b7ff5f714186856a003837dd4a2ffbab668248033ec97d4bbaee1b629b3484f","abstract_canon_sha256":"0790604b36f3c591f05f1a33aeff5bc0c65b3f3b25d61ca2fbfc908c98d1651d"},"schema_version":"1.0"},"canonical_sha256":"6a60450ae9affc62a2f14a8169e198bcdc0ec2420a655f6a90117b21626ba6ac","source":{"kind":"arxiv","id":"2412.15471","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15471","created_at":"2026-07-05T09:53:47Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15471v2","created_at":"2026-07-05T09:53:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15471","created_at":"2026-07-05T09:53:47Z"},{"alias_kind":"pith_short_12","alias_value":"NJQEKCXJV76G","created_at":"2026-07-05T09:53:47Z"},{"alias_kind":"pith_short_16","alias_value":"NJQEKCXJV76GFIXR","created_at":"2026-07-05T09:53:47Z"},{"alias_kind":"pith_short_8","alias_value":"NJQEKCXJ","created_at":"2026-07-05T09:53:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NJQEKCXJV76GFIXRJKAWTYMYXT","target":"record","payload":{"canonical_record":{"source":{"id":"2412.15471","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T00:56:13Z","cross_cats_sorted":[],"title_canon_sha256":"6b7ff5f714186856a003837dd4a2ffbab668248033ec97d4bbaee1b629b3484f","abstract_canon_sha256":"0790604b36f3c591f05f1a33aeff5bc0c65b3f3b25d61ca2fbfc908c98d1651d"},"schema_version":"1.0"},"canonical_sha256":"6a60450ae9affc62a2f14a8169e198bcdc0ec2420a655f6a90117b21626ba6ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:47.285769Z","signature_b64":"RnyfPUaShE2sja/abJ7hblXbwL/5DFl0ETqmdwAZM1Afr2AUDn1YD4M5gMmzRZocxrxCYeO1e6X8dhfF7lMOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a60450ae9affc62a2f14a8169e198bcdc0ec2420a655f6a90117b21626ba6ac","last_reissued_at":"2026-07-05T09:53:47.285270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:47.285270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.15471","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":"2026-07-05T09:53:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"njQTqziTengJCurSqvGv9f/KX3vkoXAnYDtYrjFfsFOy+FS0EKu0u7uH4b/AAXhkv1hFIYnBBI5WN27XJ3vcDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T06:12:56.487183Z"},"content_sha256":"ddedf6ba939f781e0bb873065b9c6d95764c43eda475c934c4a54bbc243a5bf2","schema_version":"1.0","event_id":"sha256:ddedf6ba939f781e0bb873065b9c6d95764c43eda475c934c4a54bbc243a5bf2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NJQEKCXJV76GFIXRJKAWTYMYXT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Review of the Marathi Natural Language Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Asang Dani, Shailesh R Sathe","submitted_at":"2024-12-20T00:56:13Z","abstract_excerpt":"Marathi is one of the most widely used languages in the world. One might expect that the latest advances in NLP research in languages like English reach such a large community. However, NLP advancements in English didn't immediately reach Indian languages like Marathi. There were several reasons for this. They included diversity of scripts used, lack of (publicly available) resources like tokenization strategies, high quality datasets \\& benchmarks, and evaluation metrics. In addition to this, the morphologically rich nature of Marathi, made NLP tasks challenging. Advances in Neural Network (N"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15471","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/2412.15471/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":"2026-07-05T09:53:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jLhvS3GDzzXQx9giL0sJkvgYYNZIonowMKa0zNJx3MqqZEf3Jst+Qr/H5EQVYyMHP/mHvmPV+/hq6F5YxKTICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T06:12:56.487746Z"},"content_sha256":"bad78430050699d4d2e1bef8893560c6f7a4add2bb1e60d4e331db79c4e6634e","schema_version":"1.0","event_id":"sha256:bad78430050699d4d2e1bef8893560c6f7a4add2bb1e60d4e331db79c4e6634e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NJQEKCXJV76GFIXRJKAWTYMYXT/bundle.json","state_url":"https://pith.science/pith/NJQEKCXJV76GFIXRJKAWTYMYXT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NJQEKCXJV76GFIXRJKAWTYMYXT/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":"2026-08-21T06:12:56Z","links":{"resolver":"https://pith.science/pith/NJQEKCXJV76GFIXRJKAWTYMYXT","bundle":"https://pith.science/pith/NJQEKCXJV76GFIXRJKAWTYMYXT/bundle.json","state":"https://pith.science/pith/NJQEKCXJV76GFIXRJKAWTYMYXT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NJQEKCXJV76GFIXRJKAWTYMYXT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NJQEKCXJV76GFIXRJKAWTYMYXT","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":"0790604b36f3c591f05f1a33aeff5bc0c65b3f3b25d61ca2fbfc908c98d1651d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T00:56:13Z","title_canon_sha256":"6b7ff5f714186856a003837dd4a2ffbab668248033ec97d4bbaee1b629b3484f"},"schema_version":"1.0","source":{"id":"2412.15471","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15471","created_at":"2026-07-05T09:53:47Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15471v2","created_at":"2026-07-05T09:53:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15471","created_at":"2026-07-05T09:53:47Z"},{"alias_kind":"pith_short_12","alias_value":"NJQEKCXJV76G","created_at":"2026-07-05T09:53:47Z"},{"alias_kind":"pith_short_16","alias_value":"NJQEKCXJV76GFIXR","created_at":"2026-07-05T09:53:47Z"},{"alias_kind":"pith_short_8","alias_value":"NJQEKCXJ","created_at":"2026-07-05T09:53:47Z"}],"graph_snapshots":[{"event_id":"sha256:bad78430050699d4d2e1bef8893560c6f7a4add2bb1e60d4e331db79c4e6634e","target":"graph","created_at":"2026-07-05T09:53:47Z","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/2412.15471/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Marathi is one of the most widely used languages in the world. One might expect that the latest advances in NLP research in languages like English reach such a large community. However, NLP advancements in English didn't immediately reach Indian languages like Marathi. There were several reasons for this. They included diversity of scripts used, lack of (publicly available) resources like tokenization strategies, high quality datasets \\& benchmarks, and evaluation metrics. In addition to this, the morphologically rich nature of Marathi, made NLP tasks challenging. Advances in Neural Network (N","authors_text":"Asang Dani, Shailesh R Sathe","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T00:56:13Z","title":"A Review of the Marathi Natural Language Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15471","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:ddedf6ba939f781e0bb873065b9c6d95764c43eda475c934c4a54bbc243a5bf2","target":"record","created_at":"2026-07-05T09:53:47Z","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":"0790604b36f3c591f05f1a33aeff5bc0c65b3f3b25d61ca2fbfc908c98d1651d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T00:56:13Z","title_canon_sha256":"6b7ff5f714186856a003837dd4a2ffbab668248033ec97d4bbaee1b629b3484f"},"schema_version":"1.0","source":{"id":"2412.15471","kind":"arxiv","version":2}},"canonical_sha256":"6a60450ae9affc62a2f14a8169e198bcdc0ec2420a655f6a90117b21626ba6ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a60450ae9affc62a2f14a8169e198bcdc0ec2420a655f6a90117b21626ba6ac","first_computed_at":"2026-07-05T09:53:47.285270Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:47.285270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RnyfPUaShE2sja/abJ7hblXbwL/5DFl0ETqmdwAZM1Afr2AUDn1YD4M5gMmzRZocxrxCYeO1e6X8dhfF7lMOBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:47.285769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15471","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ddedf6ba939f781e0bb873065b9c6d95764c43eda475c934c4a54bbc243a5bf2","sha256:bad78430050699d4d2e1bef8893560c6f7a4add2bb1e60d4e331db79c4e6634e"],"state_sha256":"7a7c2c484dac45910cdbc90f574c1ee0f1b99008777d7c90074ff6be390652c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9We1DG6Ulxe3wujl95gGK8ajxMXvDtLVy27I80EXUWq1P7HBBEe+9moYh4fdGAXbO7WctAMUDB+Vt648RsFNBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T06:12:56.492032Z","bundle_sha256":"3f7e0fb52e2998643201b67c7791e8b9aeba40aa47a001fa9a70827a6e645ed9"}}