{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RACX2KG4SWLGSKMPRU64F7P7TR","short_pith_number":"pith:RACX2KG4","schema_version":"1.0","canonical_sha256":"88057d28dc959669298f8d3dc2fdff9c693918f12e555adac902d899c0a5c30c","source":{"kind":"arxiv","id":"2501.05260","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Plagiarism Detection in Marathi with a Weighted Ensemble of TF-IDF and BERT Embeddings for Low-Resource Language Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aditya Choudhary, Atharva Mutsaddi","submitted_at":"2025-01-09T14:14:18Z","abstract_excerpt":"Plagiarism involves using another person's work or concepts without proper attribution, presenting them as original creations. With the growing amount of data communicated in regional languages such as Marathi -- one of India's regional languages -- it is crucial to design robust plagiarism detection systems tailored for low-resource languages. Language models like Bidirectional Encoder Representations from Transformers (BERT) have demonstrated exceptional capability in text representation and feature extraction, making them essential tools for semantic analysis and plagiarism detection. Howev"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.05260","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T14:14:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"36f9612b61a6153ddcd13a9236cd7270fc4340a8def74c1c0fe068e005e51fd8","abstract_canon_sha256":"8cd9b0d46c1f99c75259e39557c96cd464d8cbac59e94c6b35d52f7422dc0ac8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:07.268050Z","signature_b64":"rHyvPhURjytq6kssk+hvGOijRZTQpNWLzk3K+5R3n6/NR8vUP7rM3N8Msw9O1BVqIHnSW6R0awp+tZYJ03jFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88057d28dc959669298f8d3dc2fdff9c693918f12e555adac902d899c0a5c30c","last_reissued_at":"2026-07-05T09:59:07.267702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:07.267702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Plagiarism Detection in Marathi with a Weighted Ensemble of TF-IDF and BERT Embeddings for Low-Resource Language Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aditya Choudhary, Atharva Mutsaddi","submitted_at":"2025-01-09T14:14:18Z","abstract_excerpt":"Plagiarism involves using another person's work or concepts without proper attribution, presenting them as original creations. With the growing amount of data communicated in regional languages such as Marathi -- one of India's regional languages -- it is crucial to design robust plagiarism detection systems tailored for low-resource languages. Language models like Bidirectional Encoder Representations from Transformers (BERT) have demonstrated exceptional capability in text representation and feature extraction, making them essential tools for semantic analysis and plagiarism detection. Howev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05260","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/2501.05260/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.05260","created_at":"2026-07-05T09:59:07.267759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05260v1","created_at":"2026-07-05T09:59:07.267759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05260","created_at":"2026-07-05T09:59:07.267759+00:00"},{"alias_kind":"pith_short_12","alias_value":"RACX2KG4SWLG","created_at":"2026-07-05T09:59:07.267759+00:00"},{"alias_kind":"pith_short_16","alias_value":"RACX2KG4SWLGSKMP","created_at":"2026-07-05T09:59:07.267759+00:00"},{"alias_kind":"pith_short_8","alias_value":"RACX2KG4","created_at":"2026-07-05T09:59:07.267759+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RACX2KG4SWLGSKMPRU64F7P7TR","json":"https://pith.science/pith/RACX2KG4SWLGSKMPRU64F7P7TR.json","graph_json":"https://pith.science/api/pith-number/RACX2KG4SWLGSKMPRU64F7P7TR/graph.json","events_json":"https://pith.science/api/pith-number/RACX2KG4SWLGSKMPRU64F7P7TR/events.json","paper":"https://pith.science/paper/RACX2KG4"},"agent_actions":{"view_html":"https://pith.science/pith/RACX2KG4SWLGSKMPRU64F7P7TR","download_json":"https://pith.science/pith/RACX2KG4SWLGSKMPRU64F7P7TR.json","view_paper":"https://pith.science/paper/RACX2KG4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05260&json=true","fetch_graph":"https://pith.science/api/pith-number/RACX2KG4SWLGSKMPRU64F7P7TR/graph.json","fetch_events":"https://pith.science/api/pith-number/RACX2KG4SWLGSKMPRU64F7P7TR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RACX2KG4SWLGSKMPRU64F7P7TR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RACX2KG4SWLGSKMPRU64F7P7TR/action/storage_attestation","attest_author":"https://pith.science/pith/RACX2KG4SWLGSKMPRU64F7P7TR/action/author_attestation","sign_citation":"https://pith.science/pith/RACX2KG4SWLGSKMPRU64F7P7TR/action/citation_signature","submit_replication":"https://pith.science/pith/RACX2KG4SWLGSKMPRU64F7P7TR/action/replication_record"}},"created_at":"2026-07-05T09:59:07.267759+00:00","updated_at":"2026-07-05T09:59:07.267759+00:00"}