{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YV5NWQLEXB6VWOAM4PFTK5XYXQ","short_pith_number":"pith:YV5NWQLE","canonical_record":{"source":{"id":"2406.11029","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T17:59:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"66f13b4a8e661d8aa9602ec2d8ec32614e252e83049229ad8ab4f63ae4abbbed","abstract_canon_sha256":"cc989326a0f6d4bec028cc08429a105ff3848918c29c9e57a584f9a99c3360bf"},"schema_version":"1.0"},"canonical_sha256":"c57adb4164b87d5b380ce3cb3576f8bc3c9a1815ca756d8a162e778a2270ad89","source":{"kind":"arxiv","id":"2406.11029","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11029","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11029v1","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11029","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"pith_short_12","alias_value":"YV5NWQLEXB6V","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"pith_short_16","alias_value":"YV5NWQLEXB6VWOAM","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"pith_short_8","alias_value":"YV5NWQLE","created_at":"2026-07-05T08:32:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YV5NWQLEXB6VWOAM4PFTK5XYXQ","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11029","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T17:59:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"66f13b4a8e661d8aa9602ec2d8ec32614e252e83049229ad8ab4f63ae4abbbed","abstract_canon_sha256":"cc989326a0f6d4bec028cc08429a105ff3848918c29c9e57a584f9a99c3360bf"},"schema_version":"1.0"},"canonical_sha256":"c57adb4164b87d5b380ce3cb3576f8bc3c9a1815ca756d8a162e778a2270ad89","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:47.868526Z","signature_b64":"C61NoKSNxSnROjvocIC29JACXbnheBtG1ndXGLM2WPCCzvaJmv6PpJncaH4oyBm2RO1WO4idAjJLeSZmjcmaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c57adb4164b87d5b380ce3cb3576f8bc3c9a1815ca756d8a162e778a2270ad89","last_reissued_at":"2026-07-05T08:32:47.868031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:47.868031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11029","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":"2026-07-05T08:32:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ghpp18TIHCFd9R/MoRQ7mgQluTRqQW7QiRKNsFo3OxOMhWCmIbOxL9pxgXO4Cs/Xwpu/zNNQpNp1x1g8aJ9yAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:16:04.894487Z"},"content_sha256":"232a7a04e34c564a40694be812e4a8c8581f6b54521965aeca6033f0e22edbb7","schema_version":"1.0","event_id":"sha256:232a7a04e34c564a40694be812e4a8c8581f6b54521965aeca6033f0e22edbb7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YV5NWQLEXB6VWOAM4PFTK5XYXQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Curating Stopwords in Marathi: A TF-IDF Approach for Improved Text Analysis and Information Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Gaurav Patil, Raviraj Joshi, Rohan Chavan, Vishal Madle","submitted_at":"2024-06-16T17:59:05Z","abstract_excerpt":"Stopwords are commonly used words in a language that are often considered to be of little value in determining the meaning or significance of a document. These words occur frequently in most texts and don't provide much useful information for tasks like sentiment analysis and text classification. English, which is a high-resource language, takes advantage of the availability of stopwords, whereas low-resource Indian languages like Marathi are very limited, standardized, and can be used in available packages, but the number of available words in those packages is low. Our work targets the curat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11029","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/2406.11029/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":"2026-07-05T08:32:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nz2gKwyf+h+9P+7Xg/s0dD/v6Cqxm0orHlamzWvmtnbaRyLsNdw8lZyZUoKBiqRea8t29mkmUIkrvZpRSz+0Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:16:04.894861Z"},"content_sha256":"68effc8fa45cad5e3c882e836451c59f588f3b4951dccc55fef642482a782d07","schema_version":"1.0","event_id":"sha256:68effc8fa45cad5e3c882e836451c59f588f3b4951dccc55fef642482a782d07"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YV5NWQLEXB6VWOAM4PFTK5XYXQ/bundle.json","state_url":"https://pith.science/pith/YV5NWQLEXB6VWOAM4PFTK5XYXQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YV5NWQLEXB6VWOAM4PFTK5XYXQ/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":"2026-07-07T06:16:04Z","links":{"resolver":"https://pith.science/pith/YV5NWQLEXB6VWOAM4PFTK5XYXQ","bundle":"https://pith.science/pith/YV5NWQLEXB6VWOAM4PFTK5XYXQ/bundle.json","state":"https://pith.science/pith/YV5NWQLEXB6VWOAM4PFTK5XYXQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YV5NWQLEXB6VWOAM4PFTK5XYXQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YV5NWQLEXB6VWOAM4PFTK5XYXQ","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":"cc989326a0f6d4bec028cc08429a105ff3848918c29c9e57a584f9a99c3360bf","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T17:59:05Z","title_canon_sha256":"66f13b4a8e661d8aa9602ec2d8ec32614e252e83049229ad8ab4f63ae4abbbed"},"schema_version":"1.0","source":{"id":"2406.11029","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11029","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11029v1","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11029","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"pith_short_12","alias_value":"YV5NWQLEXB6V","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"pith_short_16","alias_value":"YV5NWQLEXB6VWOAM","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"pith_short_8","alias_value":"YV5NWQLE","created_at":"2026-07-05T08:32:47Z"}],"graph_snapshots":[{"event_id":"sha256:68effc8fa45cad5e3c882e836451c59f588f3b4951dccc55fef642482a782d07","target":"graph","created_at":"2026-07-05T08:32:47Z","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/2406.11029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stopwords are commonly used words in a language that are often considered to be of little value in determining the meaning or significance of a document. These words occur frequently in most texts and don't provide much useful information for tasks like sentiment analysis and text classification. English, which is a high-resource language, takes advantage of the availability of stopwords, whereas low-resource Indian languages like Marathi are very limited, standardized, and can be used in available packages, but the number of available words in those packages is low. Our work targets the curat","authors_text":"Gaurav Patil, Raviraj Joshi, Rohan Chavan, Vishal Madle","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T17:59:05Z","title":"Curating Stopwords in Marathi: A TF-IDF Approach for Improved Text Analysis and Information Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11029","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":"sha256:232a7a04e34c564a40694be812e4a8c8581f6b54521965aeca6033f0e22edbb7","target":"record","created_at":"2026-07-05T08:32:47Z","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":"cc989326a0f6d4bec028cc08429a105ff3848918c29c9e57a584f9a99c3360bf","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T17:59:05Z","title_canon_sha256":"66f13b4a8e661d8aa9602ec2d8ec32614e252e83049229ad8ab4f63ae4abbbed"},"schema_version":"1.0","source":{"id":"2406.11029","kind":"arxiv","version":1}},"canonical_sha256":"c57adb4164b87d5b380ce3cb3576f8bc3c9a1815ca756d8a162e778a2270ad89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c57adb4164b87d5b380ce3cb3576f8bc3c9a1815ca756d8a162e778a2270ad89","first_computed_at":"2026-07-05T08:32:47.868031Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:47.868031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C61NoKSNxSnROjvocIC29JACXbnheBtG1ndXGLM2WPCCzvaJmv6PpJncaH4oyBm2RO1WO4idAjJLeSZmjcmaDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:47.868526Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11029","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:232a7a04e34c564a40694be812e4a8c8581f6b54521965aeca6033f0e22edbb7","sha256:68effc8fa45cad5e3c882e836451c59f588f3b4951dccc55fef642482a782d07"],"state_sha256":"818ff550aaba6fa5543bc7a5a4b4075cc684436472cb1f7ed860ca00f2ea1671"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sd1BqvuDfKx8UI8AunVTuaAO5FuLU/cgR5dxEfTTgIp8mkAahf5N5eg3ObWjJVPRgL5CZOoZVSY8yOE5zkk9Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:16:04.896864Z","bundle_sha256":"c4349ac4084476cd653ec4363a64166b053bd2f2f868e1edde256dec6c8d3b0e"}}