{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:S5KLBRALZRFVFPDR5IIN4GWHH5","short_pith_number":"pith:S5KLBRAL","schema_version":"1.0","canonical_sha256":"9754b0c40bcc4b52bc71ea10de1ac73f4a6f223cc22dd9393232fa532825f06f","source":{"kind":"arxiv","id":"2601.07988","version":2},"attestation_state":"computed","paper":{"title":"From Word Sequences to Behavioral Sequences: Adapting Modeling and Evaluation Paradigms for Longitudinal NLP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adithya V Ganesan, Benjamin J Luft, H Andrew Schwartz, Oscar NE Kjell, Roman Kotov, Ryan L Boyd, Scott Feltman, Vasudha Varadarajan, Whitney R Ringwald","submitted_at":"2026-01-12T20:38:36Z","abstract_excerpt":"While NLP typically treats documents as independent and unordered samples, in longitudinal studies, this assumption rarely holds: documents are nested within authors and ordered in time, forming person-indexed, time-ordered $\\textit{behavioral sequences}$. Here, we demonstrate the need for and propose a longitudinal modeling and evaluation paradigm that consequently updates four parts of the NLP pipeline: (1) evaluation splits aligned to generalization over people ($\\textit{cross-sectional}$) and/or time ($\\textit{prospective}$); (2) accuracy metrics separating between-person differences from "},"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":"2601.07988","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-12T20:38:36Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"64ecc353b40856f2f7a8d74332521ac3ca7b3b3e5cde982888f7f75718a6c7cf","abstract_canon_sha256":"6a920bfe1dc3cd2056a3e4a031df00a8e5fb1ba445f05fe180dadace77183777"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:14.597790Z","signature_b64":"NI8722JnL4FDbWDXyyvK4GWa2xXdPct07fNVp2926BLWXciuVbCLuu3WahDeZEzku11AgoOeuVB2UFBF6MK0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9754b0c40bcc4b52bc71ea10de1ac73f4a6f223cc22dd9393232fa532825f06f","last_reissued_at":"2026-06-30T02:17:14.597196Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:14.597196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Word Sequences to Behavioral Sequences: Adapting Modeling and Evaluation Paradigms for Longitudinal NLP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adithya V Ganesan, Benjamin J Luft, H Andrew Schwartz, Oscar NE Kjell, Roman Kotov, Ryan L Boyd, Scott Feltman, Vasudha Varadarajan, Whitney R Ringwald","submitted_at":"2026-01-12T20:38:36Z","abstract_excerpt":"While NLP typically treats documents as independent and unordered samples, in longitudinal studies, this assumption rarely holds: documents are nested within authors and ordered in time, forming person-indexed, time-ordered $\\textit{behavioral sequences}$. Here, we demonstrate the need for and propose a longitudinal modeling and evaluation paradigm that consequently updates four parts of the NLP pipeline: (1) evaluation splits aligned to generalization over people ($\\textit{cross-sectional}$) and/or time ($\\textit{prospective}$); (2) accuracy metrics separating between-person differences from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.07988","kind":"arxiv","version":2},"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/2601.07988/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":"2601.07988","created_at":"2026-06-30T02:17:14.597274+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.07988v2","created_at":"2026-06-30T02:17:14.597274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.07988","created_at":"2026-06-30T02:17:14.597274+00:00"},{"alias_kind":"pith_short_12","alias_value":"S5KLBRALZRFV","created_at":"2026-06-30T02:17:14.597274+00:00"},{"alias_kind":"pith_short_16","alias_value":"S5KLBRALZRFVFPDR","created_at":"2026-06-30T02:17:14.597274+00:00"},{"alias_kind":"pith_short_8","alias_value":"S5KLBRAL","created_at":"2026-06-30T02:17:14.597274+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/S5KLBRALZRFVFPDR5IIN4GWHH5","json":"https://pith.science/pith/S5KLBRALZRFVFPDR5IIN4GWHH5.json","graph_json":"https://pith.science/api/pith-number/S5KLBRALZRFVFPDR5IIN4GWHH5/graph.json","events_json":"https://pith.science/api/pith-number/S5KLBRALZRFVFPDR5IIN4GWHH5/events.json","paper":"https://pith.science/paper/S5KLBRAL"},"agent_actions":{"view_html":"https://pith.science/pith/S5KLBRALZRFVFPDR5IIN4GWHH5","download_json":"https://pith.science/pith/S5KLBRALZRFVFPDR5IIN4GWHH5.json","view_paper":"https://pith.science/paper/S5KLBRAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.07988&json=true","fetch_graph":"https://pith.science/api/pith-number/S5KLBRALZRFVFPDR5IIN4GWHH5/graph.json","fetch_events":"https://pith.science/api/pith-number/S5KLBRALZRFVFPDR5IIN4GWHH5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S5KLBRALZRFVFPDR5IIN4GWHH5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S5KLBRALZRFVFPDR5IIN4GWHH5/action/storage_attestation","attest_author":"https://pith.science/pith/S5KLBRALZRFVFPDR5IIN4GWHH5/action/author_attestation","sign_citation":"https://pith.science/pith/S5KLBRALZRFVFPDR5IIN4GWHH5/action/citation_signature","submit_replication":"https://pith.science/pith/S5KLBRALZRFVFPDR5IIN4GWHH5/action/replication_record"}},"created_at":"2026-06-30T02:17:14.597274+00:00","updated_at":"2026-06-30T02:17:14.597274+00:00"}