{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QVHTUHMWQINUU6W3WYPBBEXHBP","short_pith_number":"pith:QVHTUHMW","schema_version":"1.0","canonical_sha256":"854f3a1d96821b4a7adbb61e1092e70bc2ba2b3979b6a2bc48ed8b65ce16fbbd","source":{"kind":"arxiv","id":"2101.03382","version":1},"attestation_state":"computed","paper":{"title":"Task Adaptive Pretraining of Transformers for Hostility Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Sayar Ghosh Roy, Tathagata Raha, Ujwal Narayan, Vasudeva Varma, Zubair Abid","submitted_at":"2021-01-09T15:45:26Z","abstract_excerpt":"Identifying adverse and hostile content on the web and more particularly, on social media, has become a problem of paramount interest in recent years. With their ever increasing popularity, fine-tuning of pretrained Transformer-based encoder models with a classifier head are gradually becoming the new baseline for natural language classification tasks. In our work, we explore the gains attributed to Task Adaptive Pretraining (TAPT) prior to fine-tuning of Transformer-based architectures. We specifically study two problems, namely, (a) Coarse binary classification of Hindi Tweets into Hostile o"},"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":"2101.03382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-09T15:45:26Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"38c5da56cc742d9d6ac7deccfb9ae7a71068ea7a2d1f7bcfc1b1024c814b5c6e","abstract_canon_sha256":"f63d627500b4e1e9a97de80788af3e414da3040a72d06539de11a45dc1655995"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:05:49.462555Z","signature_b64":"j06KTwEUuQjQYub0gbU279m84pgdzWpJHlPv7f3GKlk+2MMG4cbJffO/IlXgikdzB61h61FqElLNt1UHt7QmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"854f3a1d96821b4a7adbb61e1092e70bc2ba2b3979b6a2bc48ed8b65ce16fbbd","last_reissued_at":"2026-07-05T02:05:49.462148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:05:49.462148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task Adaptive Pretraining of Transformers for Hostility Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Sayar Ghosh Roy, Tathagata Raha, Ujwal Narayan, Vasudeva Varma, Zubair Abid","submitted_at":"2021-01-09T15:45:26Z","abstract_excerpt":"Identifying adverse and hostile content on the web and more particularly, on social media, has become a problem of paramount interest in recent years. With their ever increasing popularity, fine-tuning of pretrained Transformer-based encoder models with a classifier head are gradually becoming the new baseline for natural language classification tasks. In our work, we explore the gains attributed to Task Adaptive Pretraining (TAPT) prior to fine-tuning of Transformer-based architectures. We specifically study two problems, namely, (a) Coarse binary classification of Hindi Tweets into Hostile o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.03382","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/2101.03382/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":"2101.03382","created_at":"2026-07-05T02:05:49.462207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.03382v1","created_at":"2026-07-05T02:05:49.462207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.03382","created_at":"2026-07-05T02:05:49.462207+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVHTUHMWQINU","created_at":"2026-07-05T02:05:49.462207+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVHTUHMWQINUU6W3","created_at":"2026-07-05T02:05:49.462207+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVHTUHMW","created_at":"2026-07-05T02:05:49.462207+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/QVHTUHMWQINUU6W3WYPBBEXHBP","json":"https://pith.science/pith/QVHTUHMWQINUU6W3WYPBBEXHBP.json","graph_json":"https://pith.science/api/pith-number/QVHTUHMWQINUU6W3WYPBBEXHBP/graph.json","events_json":"https://pith.science/api/pith-number/QVHTUHMWQINUU6W3WYPBBEXHBP/events.json","paper":"https://pith.science/paper/QVHTUHMW"},"agent_actions":{"view_html":"https://pith.science/pith/QVHTUHMWQINUU6W3WYPBBEXHBP","download_json":"https://pith.science/pith/QVHTUHMWQINUU6W3WYPBBEXHBP.json","view_paper":"https://pith.science/paper/QVHTUHMW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.03382&json=true","fetch_graph":"https://pith.science/api/pith-number/QVHTUHMWQINUU6W3WYPBBEXHBP/graph.json","fetch_events":"https://pith.science/api/pith-number/QVHTUHMWQINUU6W3WYPBBEXHBP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVHTUHMWQINUU6W3WYPBBEXHBP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVHTUHMWQINUU6W3WYPBBEXHBP/action/storage_attestation","attest_author":"https://pith.science/pith/QVHTUHMWQINUU6W3WYPBBEXHBP/action/author_attestation","sign_citation":"https://pith.science/pith/QVHTUHMWQINUU6W3WYPBBEXHBP/action/citation_signature","submit_replication":"https://pith.science/pith/QVHTUHMWQINUU6W3WYPBBEXHBP/action/replication_record"}},"created_at":"2026-07-05T02:05:49.462207+00:00","updated_at":"2026-07-05T02:05:49.462207+00:00"}