{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LXW3A2TKAVDL67337AZKB3WHVT","short_pith_number":"pith:LXW3A2TK","schema_version":"1.0","canonical_sha256":"5dedb06a6a0546bf7f7bf832a0eec7acf590c97a4e8188d037855c8909f3e7a4","source":{"kind":"arxiv","id":"2104.06182","version":1},"attestation_state":"computed","paper":{"title":"Understanding Transformers for Bot Detection in Twitter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andres Garcia-Silva, Cristian Berrio, Jose Manuel Gomez-Perez","submitted_at":"2021-04-13T13:32:55Z","abstract_excerpt":"In this paper we shed light on the impact of fine-tuning over social media data in the internal representations of neural language models. We focus on bot detection in Twitter, a key task to mitigate and counteract the automatic spreading of disinformation and bias in social media. We investigate the use of pre-trained language models to tackle the detection of tweets generated by a bot or a human account based exclusively on its content. Unlike the general trend in benchmarks like GLUE, where BERT generally outperforms generative transformers like GPT and GPT-2 for most classification tasks 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":"2104.06182","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-13T13:32:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a05f4b04953dce3ef8b4dfd26834387749bcb21ca21cb9ab344ab14fee6afe5f","abstract_canon_sha256":"e65c4b3ef1a609ceccea9b8f5fb18d79e49c0ffe391a38ff3c71384afb63cfac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:29.779084Z","signature_b64":"LRo8XSZmvJ/jD9nwryfmv2WBiDFV1RDn+pjJCk6WgTMU/hKjYUr6g191aR5dGbmo0esXNiDvLTJJ5m7kCSysDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dedb06a6a0546bf7f7bf832a0eec7acf590c97a4e8188d037855c8909f3e7a4","last_reissued_at":"2026-07-05T02:31:29.778659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:29.778659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Transformers for Bot Detection in Twitter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andres Garcia-Silva, Cristian Berrio, Jose Manuel Gomez-Perez","submitted_at":"2021-04-13T13:32:55Z","abstract_excerpt":"In this paper we shed light on the impact of fine-tuning over social media data in the internal representations of neural language models. We focus on bot detection in Twitter, a key task to mitigate and counteract the automatic spreading of disinformation and bias in social media. We investigate the use of pre-trained language models to tackle the detection of tweets generated by a bot or a human account based exclusively on its content. Unlike the general trend in benchmarks like GLUE, where BERT generally outperforms generative transformers like GPT and GPT-2 for most classification tasks o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06182","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/2104.06182/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":"2104.06182","created_at":"2026-07-05T02:31:29.778725+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.06182v1","created_at":"2026-07-05T02:31:29.778725+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06182","created_at":"2026-07-05T02:31:29.778725+00:00"},{"alias_kind":"pith_short_12","alias_value":"LXW3A2TKAVDL","created_at":"2026-07-05T02:31:29.778725+00:00"},{"alias_kind":"pith_short_16","alias_value":"LXW3A2TKAVDL6733","created_at":"2026-07-05T02:31:29.778725+00:00"},{"alias_kind":"pith_short_8","alias_value":"LXW3A2TK","created_at":"2026-07-05T02:31:29.778725+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.04375","citing_title":"Large Language Models and Social Media Information Integrity: Opportunities, Challenges, and Research Directions","ref_index":62,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LXW3A2TKAVDL67337AZKB3WHVT","json":"https://pith.science/pith/LXW3A2TKAVDL67337AZKB3WHVT.json","graph_json":"https://pith.science/api/pith-number/LXW3A2TKAVDL67337AZKB3WHVT/graph.json","events_json":"https://pith.science/api/pith-number/LXW3A2TKAVDL67337AZKB3WHVT/events.json","paper":"https://pith.science/paper/LXW3A2TK"},"agent_actions":{"view_html":"https://pith.science/pith/LXW3A2TKAVDL67337AZKB3WHVT","download_json":"https://pith.science/pith/LXW3A2TKAVDL67337AZKB3WHVT.json","view_paper":"https://pith.science/paper/LXW3A2TK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.06182&json=true","fetch_graph":"https://pith.science/api/pith-number/LXW3A2TKAVDL67337AZKB3WHVT/graph.json","fetch_events":"https://pith.science/api/pith-number/LXW3A2TKAVDL67337AZKB3WHVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LXW3A2TKAVDL67337AZKB3WHVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LXW3A2TKAVDL67337AZKB3WHVT/action/storage_attestation","attest_author":"https://pith.science/pith/LXW3A2TKAVDL67337AZKB3WHVT/action/author_attestation","sign_citation":"https://pith.science/pith/LXW3A2TKAVDL67337AZKB3WHVT/action/citation_signature","submit_replication":"https://pith.science/pith/LXW3A2TKAVDL67337AZKB3WHVT/action/replication_record"}},"created_at":"2026-07-05T02:31:29.778725+00:00","updated_at":"2026-07-05T02:31:29.778725+00:00"}