{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GP27RNOLDRAJS275PPY6RCQEMW","short_pith_number":"pith:GP27RNOL","schema_version":"1.0","canonical_sha256":"33f5f8b5cb1c40996bfd7bf1e88a0465bbe840c5ec5c9b06a889107386226a8f","source":{"kind":"arxiv","id":"2401.12492","version":3},"attestation_state":"computed","paper":{"title":"Comparing Pre-trained Human Language Models: Is it Better with Human Context as Groups, Individual Traits, or Both?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dirk Hovy, H. Andrew Schwartz, Nikita Soni, Niranjan Balasubramanian","submitted_at":"2024-01-23T05:20:35Z","abstract_excerpt":"Pre-trained language models consider the context of neighboring words and documents but lack any author context of the human generating the text. However, language depends on the author's states, traits, social, situational, and environmental attributes, collectively referred to as human context (Soni et al., 2024). Human-centered natural language processing requires incorporating human context into language models. Currently, two methods exist: pre-training with 1) group-wise attributes (e.g., over-45-year-olds) or 2) individual traits. Group attributes are simple but coarse -- not all 45-yea"},"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":"2401.12492","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-23T05:20:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0fb889d917d6414e23f1c3aab7d502979e8119f88a51af180b06e28a86156a46","abstract_canon_sha256":"08abf8e61ab0c9daec5d704b4895ff71ffd2899e8cb29e13d23f9ba61879055c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:01.955806Z","signature_b64":"qAYI3E5wAxJLvwmJkQXwnhyHrha/v717f9srX7rIWJSLxM6vRtIxsYX3hNlAwWYx0S1XUkwPdUf7TuPLsO7VBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33f5f8b5cb1c40996bfd7bf1e88a0465bbe840c5ec5c9b06a889107386226a8f","last_reissued_at":"2026-07-05T11:39:01.955304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:01.955304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparing Pre-trained Human Language Models: Is it Better with Human Context as Groups, Individual Traits, or Both?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dirk Hovy, H. Andrew Schwartz, Nikita Soni, Niranjan Balasubramanian","submitted_at":"2024-01-23T05:20:35Z","abstract_excerpt":"Pre-trained language models consider the context of neighboring words and documents but lack any author context of the human generating the text. However, language depends on the author's states, traits, social, situational, and environmental attributes, collectively referred to as human context (Soni et al., 2024). Human-centered natural language processing requires incorporating human context into language models. Currently, two methods exist: pre-training with 1) group-wise attributes (e.g., over-45-year-olds) or 2) individual traits. Group attributes are simple but coarse -- not all 45-yea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12492","kind":"arxiv","version":3},"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/2401.12492/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":"2401.12492","created_at":"2026-07-05T11:39:01.955372+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.12492v3","created_at":"2026-07-05T11:39:01.955372+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12492","created_at":"2026-07-05T11:39:01.955372+00:00"},{"alias_kind":"pith_short_12","alias_value":"GP27RNOLDRAJ","created_at":"2026-07-05T11:39:01.955372+00:00"},{"alias_kind":"pith_short_16","alias_value":"GP27RNOLDRAJS275","created_at":"2026-07-05T11:39:01.955372+00:00"},{"alias_kind":"pith_short_8","alias_value":"GP27RNOL","created_at":"2026-07-05T11:39:01.955372+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/GP27RNOLDRAJS275PPY6RCQEMW","json":"https://pith.science/pith/GP27RNOLDRAJS275PPY6RCQEMW.json","graph_json":"https://pith.science/api/pith-number/GP27RNOLDRAJS275PPY6RCQEMW/graph.json","events_json":"https://pith.science/api/pith-number/GP27RNOLDRAJS275PPY6RCQEMW/events.json","paper":"https://pith.science/paper/GP27RNOL"},"agent_actions":{"view_html":"https://pith.science/pith/GP27RNOLDRAJS275PPY6RCQEMW","download_json":"https://pith.science/pith/GP27RNOLDRAJS275PPY6RCQEMW.json","view_paper":"https://pith.science/paper/GP27RNOL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.12492&json=true","fetch_graph":"https://pith.science/api/pith-number/GP27RNOLDRAJS275PPY6RCQEMW/graph.json","fetch_events":"https://pith.science/api/pith-number/GP27RNOLDRAJS275PPY6RCQEMW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GP27RNOLDRAJS275PPY6RCQEMW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GP27RNOLDRAJS275PPY6RCQEMW/action/storage_attestation","attest_author":"https://pith.science/pith/GP27RNOLDRAJS275PPY6RCQEMW/action/author_attestation","sign_citation":"https://pith.science/pith/GP27RNOLDRAJS275PPY6RCQEMW/action/citation_signature","submit_replication":"https://pith.science/pith/GP27RNOLDRAJS275PPY6RCQEMW/action/replication_record"}},"created_at":"2026-07-05T11:39:01.955372+00:00","updated_at":"2026-07-05T11:39:01.955372+00:00"}