{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3MXWWO63AUZYY4CXWN33DHFCO4","short_pith_number":"pith:3MXWWO63","schema_version":"1.0","canonical_sha256":"db2f6b3bdb05338c7057b377b19ca27727b28d9e7b1f3391da7a8944f03bed0c","source":{"kind":"arxiv","id":"2108.00356","version":4},"attestation_state":"computed","paper":{"title":"Improving Social Meaning Detection with Pragmatic Masking and Surrogate Fine-Tuning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chiyu Zhang, Muhammad Abdul-Mageed","submitted_at":"2021-08-01T03:32:21Z","abstract_excerpt":"Masked language models (MLMs) are pre-trained with a denoising objective that is in a mismatch with the objective of downstream fine-tuning. We propose pragmatic masking and surrogate fine-tuning as two complementing strategies that exploit social cues to drive pre-trained representations toward a broad set of concepts useful for a wide class of social meaning tasks. We test our models on $15$ different Twitter datasets for social meaning detection. Our methods achieve $2.34\\%$ $F_1$ over a competitive baseline, while outperforming domain-specific language models pre-trained on large datasets."},"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":"2108.00356","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-01T03:32:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"255c7e713839c2b31767d90586f1d499fb9daaaed17796e373d1ab9c66d7ba8e","abstract_canon_sha256":"236ba3b9a9ba83e6ffb9f6f0e5a48807e743832b37a99b13e5a6e9213df92614"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:07.260870Z","signature_b64":"6JZUjw+whqbszthNIeN8nBN42Ha0eniCwynzGI89swAStkDiXkplZnLb2eDUy41BRTF/q4EzcUSDupM44omgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db2f6b3bdb05338c7057b377b19ca27727b28d9e7b1f3391da7a8944f03bed0c","last_reissued_at":"2026-07-05T04:28:07.260284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:07.260284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Social Meaning Detection with Pragmatic Masking and Surrogate Fine-Tuning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chiyu Zhang, Muhammad Abdul-Mageed","submitted_at":"2021-08-01T03:32:21Z","abstract_excerpt":"Masked language models (MLMs) are pre-trained with a denoising objective that is in a mismatch with the objective of downstream fine-tuning. We propose pragmatic masking and surrogate fine-tuning as two complementing strategies that exploit social cues to drive pre-trained representations toward a broad set of concepts useful for a wide class of social meaning tasks. We test our models on $15$ different Twitter datasets for social meaning detection. Our methods achieve $2.34\\%$ $F_1$ over a competitive baseline, while outperforming domain-specific language models pre-trained on large datasets."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.00356","kind":"arxiv","version":4},"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/2108.00356/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":"2108.00356","created_at":"2026-07-05T04:28:07.260345+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.00356v4","created_at":"2026-07-05T04:28:07.260345+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.00356","created_at":"2026-07-05T04:28:07.260345+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MXWWO63AUZY","created_at":"2026-07-05T04:28:07.260345+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MXWWO63AUZYY4CX","created_at":"2026-07-05T04:28:07.260345+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MXWWO63","created_at":"2026-07-05T04:28:07.260345+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/3MXWWO63AUZYY4CXWN33DHFCO4","json":"https://pith.science/pith/3MXWWO63AUZYY4CXWN33DHFCO4.json","graph_json":"https://pith.science/api/pith-number/3MXWWO63AUZYY4CXWN33DHFCO4/graph.json","events_json":"https://pith.science/api/pith-number/3MXWWO63AUZYY4CXWN33DHFCO4/events.json","paper":"https://pith.science/paper/3MXWWO63"},"agent_actions":{"view_html":"https://pith.science/pith/3MXWWO63AUZYY4CXWN33DHFCO4","download_json":"https://pith.science/pith/3MXWWO63AUZYY4CXWN33DHFCO4.json","view_paper":"https://pith.science/paper/3MXWWO63","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.00356&json=true","fetch_graph":"https://pith.science/api/pith-number/3MXWWO63AUZYY4CXWN33DHFCO4/graph.json","fetch_events":"https://pith.science/api/pith-number/3MXWWO63AUZYY4CXWN33DHFCO4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MXWWO63AUZYY4CXWN33DHFCO4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MXWWO63AUZYY4CXWN33DHFCO4/action/storage_attestation","attest_author":"https://pith.science/pith/3MXWWO63AUZYY4CXWN33DHFCO4/action/author_attestation","sign_citation":"https://pith.science/pith/3MXWWO63AUZYY4CXWN33DHFCO4/action/citation_signature","submit_replication":"https://pith.science/pith/3MXWWO63AUZYY4CXWN33DHFCO4/action/replication_record"}},"created_at":"2026-07-05T04:28:07.260345+00:00","updated_at":"2026-07-05T04:28:07.260345+00:00"}