{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:STMMUB2CPRU47ZSTR7DYOGEZ7G","short_pith_number":"pith:STMMUB2C","canonical_record":{"source":{"id":"2502.02100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T08:32:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e055a831bdc6b6297b8f37870793ef0f92189e69181fd20faab49e30a30d7a1f","abstract_canon_sha256":"9f11adcdfb6ef0cfba85c1e74df82fe5f6be70ff0fde5bbfa83478eded4b1edf"},"schema_version":"1.0"},"canonical_sha256":"94d8ca07427c69cfe6538fc7871899f986553f4fd3fb1c5b2962bb32aa5ada7c","source":{"kind":"arxiv","id":"2502.02100","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02100","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02100v1","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02100","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"pith_short_12","alias_value":"STMMUB2CPRU4","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"pith_short_16","alias_value":"STMMUB2CPRU47ZST","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"pith_short_8","alias_value":"STMMUB2C","created_at":"2026-07-05T10:09:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:STMMUB2CPRU47ZSTR7DYOGEZ7G","target":"record","payload":{"canonical_record":{"source":{"id":"2502.02100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T08:32:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e055a831bdc6b6297b8f37870793ef0f92189e69181fd20faab49e30a30d7a1f","abstract_canon_sha256":"9f11adcdfb6ef0cfba85c1e74df82fe5f6be70ff0fde5bbfa83478eded4b1edf"},"schema_version":"1.0"},"canonical_sha256":"94d8ca07427c69cfe6538fc7871899f986553f4fd3fb1c5b2962bb32aa5ada7c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:23.746029Z","signature_b64":"QNbKqkRuYGzpU/qUSMXpN7OzoPQgfrgV79K3yyKruivy3H+QuEWllGXlU98xrS2A/Obofq6YpWqbdHhirBDuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94d8ca07427c69cfe6538fc7871899f986553f4fd3fb1c5b2962bb32aa5ada7c","last_reissued_at":"2026-07-05T10:09:23.745588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:23.745588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.02100","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":"2026-07-05T10:09:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YuKrGFyTw+jCpM6K4543GQho1bhtiUuKUEvE7x+a+2dWNIYWXRGe4tfLwsw5uUnu5t2pGXo9Tpk0QHdLkZ1cAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T11:10:36.220272Z"},"content_sha256":"9bf5efba5b4fab8735a99e45172c12fa414e11ca4c52db1670bb8ed84ccb844d","schema_version":"1.0","event_id":"sha256:9bf5efba5b4fab8735a99e45172c12fa414e11ca4c52db1670bb8ed84ccb844d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:STMMUB2CPRU47ZSTR7DYOGEZ7G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Topic Modeling in Marathi","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Raviraj Joshi, Sanket Shinde","submitted_at":"2025-02-04T08:32:08Z","abstract_excerpt":"While topic modeling in English has become a prevalent and well-explored area, venturing into topic modeling for Indic languages remains relatively rare. The limited availability of resources, diverse linguistic structures, and unique challenges posed by Indic languages contribute to the scarcity of research and applications in this domain. Despite the growing interest in natural language processing and machine learning, there exists a noticeable gap in the comprehensive exploration of topic modeling methodologies tailored specifically for languages such as Hindi, Marathi, Tamil, and others. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02100","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/2502.02100/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":"2026-07-05T10:09:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3s0cjYczdkew5dtwo8hbnVtqab22bvBaOXMezFhXc1UF1BMgwRPTiVCG/GpPaDD5im9lh+spk2LjOj/t1VuqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T11:10:36.220652Z"},"content_sha256":"7ef289c48f2f7101ac325cba3e9a2b5710f0792990700f6a057b2130d675ec87","schema_version":"1.0","event_id":"sha256:7ef289c48f2f7101ac325cba3e9a2b5710f0792990700f6a057b2130d675ec87"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/STMMUB2CPRU47ZSTR7DYOGEZ7G/bundle.json","state_url":"https://pith.science/pith/STMMUB2CPRU47ZSTR7DYOGEZ7G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/STMMUB2CPRU47ZSTR7DYOGEZ7G/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":"2026-07-06T11:10:36Z","links":{"resolver":"https://pith.science/pith/STMMUB2CPRU47ZSTR7DYOGEZ7G","bundle":"https://pith.science/pith/STMMUB2CPRU47ZSTR7DYOGEZ7G/bundle.json","state":"https://pith.science/pith/STMMUB2CPRU47ZSTR7DYOGEZ7G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/STMMUB2CPRU47ZSTR7DYOGEZ7G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:STMMUB2CPRU47ZSTR7DYOGEZ7G","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":"9f11adcdfb6ef0cfba85c1e74df82fe5f6be70ff0fde5bbfa83478eded4b1edf","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T08:32:08Z","title_canon_sha256":"e055a831bdc6b6297b8f37870793ef0f92189e69181fd20faab49e30a30d7a1f"},"schema_version":"1.0","source":{"id":"2502.02100","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02100","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02100v1","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02100","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"pith_short_12","alias_value":"STMMUB2CPRU4","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"pith_short_16","alias_value":"STMMUB2CPRU47ZST","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"pith_short_8","alias_value":"STMMUB2C","created_at":"2026-07-05T10:09:23Z"}],"graph_snapshots":[{"event_id":"sha256:7ef289c48f2f7101ac325cba3e9a2b5710f0792990700f6a057b2130d675ec87","target":"graph","created_at":"2026-07-05T10:09:23Z","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/2502.02100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While topic modeling in English has become a prevalent and well-explored area, venturing into topic modeling for Indic languages remains relatively rare. The limited availability of resources, diverse linguistic structures, and unique challenges posed by Indic languages contribute to the scarcity of research and applications in this domain. Despite the growing interest in natural language processing and machine learning, there exists a noticeable gap in the comprehensive exploration of topic modeling methodologies tailored specifically for languages such as Hindi, Marathi, Tamil, and others. I","authors_text":"Raviraj Joshi, Sanket Shinde","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T08:32:08Z","title":"Topic Modeling in Marathi"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02100","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":"sha256:9bf5efba5b4fab8735a99e45172c12fa414e11ca4c52db1670bb8ed84ccb844d","target":"record","created_at":"2026-07-05T10:09:23Z","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":"9f11adcdfb6ef0cfba85c1e74df82fe5f6be70ff0fde5bbfa83478eded4b1edf","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T08:32:08Z","title_canon_sha256":"e055a831bdc6b6297b8f37870793ef0f92189e69181fd20faab49e30a30d7a1f"},"schema_version":"1.0","source":{"id":"2502.02100","kind":"arxiv","version":1}},"canonical_sha256":"94d8ca07427c69cfe6538fc7871899f986553f4fd3fb1c5b2962bb32aa5ada7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94d8ca07427c69cfe6538fc7871899f986553f4fd3fb1c5b2962bb32aa5ada7c","first_computed_at":"2026-07-05T10:09:23.745588Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:23.745588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QNbKqkRuYGzpU/qUSMXpN7OzoPQgfrgV79K3yyKruivy3H+QuEWllGXlU98xrS2A/Obofq6YpWqbdHhirBDuCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:23.746029Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02100","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9bf5efba5b4fab8735a99e45172c12fa414e11ca4c52db1670bb8ed84ccb844d","sha256:7ef289c48f2f7101ac325cba3e9a2b5710f0792990700f6a057b2130d675ec87"],"state_sha256":"0f07f15eaa1a1daf94296dca04d96cb08fd6e232c093e17b5c6943078a9a4a62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AACitz6mweaTILiujiEEE2f4P1D/tS+aB8/viwaDAsZXQUUO/KR7GQdecMotBTGx72JiwepSaymJ3hO/OI0iDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T11:10:36.222574Z","bundle_sha256":"bdca4a10dd0c581bef68f84e0999fe908bd4105b2ccbcf48032e9f8ad01e390d"}}