{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NSZ6UGXUR6P4ZV5R5S2GM7HVIH","short_pith_number":"pith:NSZ6UGXU","schema_version":"1.0","canonical_sha256":"6cb3ea1af48f9fccd7b1ecb4667cf541dc1d7f04c15c51e8fcf690af2ff50256","source":{"kind":"arxiv","id":"2509.11057","version":1},"attestation_state":"computed","paper":{"title":"YTCommentVerse: A Multi-Category Multi-Lingual YouTube Comment Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SI","authors_text":"Biswadeep Khan, Hridoy Sankar Dutta","submitted_at":"2025-09-14T02:51:05Z","abstract_excerpt":"In this paper, we introduce YTCommentVerse, a large-scale multilingual and multi-category dataset of YouTube comments. It contains over 32 million comments from 178,000 videos contributed by more than 20 million unique users spanning 15 distinct YouTube content categories such as Music, News, Education and Entertainment. Each comment in the dataset includes video and comment IDs, user channel details, upvotes and category labels. With comments in over 50 languages, YTCommentVerse provides a rich resource for exploring sentiment, toxicity and engagement patterns across diverse cultural and topi"},"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":"2509.11057","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SI","submitted_at":"2025-09-14T02:51:05Z","cross_cats_sorted":[],"title_canon_sha256":"ea6bee6a4b549a5920558d38d426fe07b280d6e8de190a287c7ee46d12d00c8e","abstract_canon_sha256":"1588f6fa6d103e02fee804679ec0fa6832ace13e18940afeec360528c9e9af24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:32.800367Z","signature_b64":"eAl4OyLYRLLQlCLRiCJ/Esu/+1kBlujLdFMT0ILN3ZfgaTZN7dkuL8Eu+IXkm7O01GSl5TTnahjaXqro8rW5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cb3ea1af48f9fccd7b1ecb4667cf541dc1d7f04c15c51e8fcf690af2ff50256","last_reissued_at":"2026-07-05T12:11:32.799822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:32.799822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"YTCommentVerse: A Multi-Category Multi-Lingual YouTube Comment Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SI","authors_text":"Biswadeep Khan, Hridoy Sankar Dutta","submitted_at":"2025-09-14T02:51:05Z","abstract_excerpt":"In this paper, we introduce YTCommentVerse, a large-scale multilingual and multi-category dataset of YouTube comments. It contains over 32 million comments from 178,000 videos contributed by more than 20 million unique users spanning 15 distinct YouTube content categories such as Music, News, Education and Entertainment. Each comment in the dataset includes video and comment IDs, user channel details, upvotes and category labels. With comments in over 50 languages, YTCommentVerse provides a rich resource for exploring sentiment, toxicity and engagement patterns across diverse cultural and topi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.11057","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/2509.11057/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":"2509.11057","created_at":"2026-07-05T12:11:32.799877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.11057v1","created_at":"2026-07-05T12:11:32.799877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.11057","created_at":"2026-07-05T12:11:32.799877+00:00"},{"alias_kind":"pith_short_12","alias_value":"NSZ6UGXUR6P4","created_at":"2026-07-05T12:11:32.799877+00:00"},{"alias_kind":"pith_short_16","alias_value":"NSZ6UGXUR6P4ZV5R","created_at":"2026-07-05T12:11:32.799877+00:00"},{"alias_kind":"pith_short_8","alias_value":"NSZ6UGXU","created_at":"2026-07-05T12:11:32.799877+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/NSZ6UGXUR6P4ZV5R5S2GM7HVIH","json":"https://pith.science/pith/NSZ6UGXUR6P4ZV5R5S2GM7HVIH.json","graph_json":"https://pith.science/api/pith-number/NSZ6UGXUR6P4ZV5R5S2GM7HVIH/graph.json","events_json":"https://pith.science/api/pith-number/NSZ6UGXUR6P4ZV5R5S2GM7HVIH/events.json","paper":"https://pith.science/paper/NSZ6UGXU"},"agent_actions":{"view_html":"https://pith.science/pith/NSZ6UGXUR6P4ZV5R5S2GM7HVIH","download_json":"https://pith.science/pith/NSZ6UGXUR6P4ZV5R5S2GM7HVIH.json","view_paper":"https://pith.science/paper/NSZ6UGXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.11057&json=true","fetch_graph":"https://pith.science/api/pith-number/NSZ6UGXUR6P4ZV5R5S2GM7HVIH/graph.json","fetch_events":"https://pith.science/api/pith-number/NSZ6UGXUR6P4ZV5R5S2GM7HVIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NSZ6UGXUR6P4ZV5R5S2GM7HVIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NSZ6UGXUR6P4ZV5R5S2GM7HVIH/action/storage_attestation","attest_author":"https://pith.science/pith/NSZ6UGXUR6P4ZV5R5S2GM7HVIH/action/author_attestation","sign_citation":"https://pith.science/pith/NSZ6UGXUR6P4ZV5R5S2GM7HVIH/action/citation_signature","submit_replication":"https://pith.science/pith/NSZ6UGXUR6P4ZV5R5S2GM7HVIH/action/replication_record"}},"created_at":"2026-07-05T12:11:32.799877+00:00","updated_at":"2026-07-05T12:11:32.799877+00:00"}