{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3V46CIZ6UKMA6PUXN4ILX3GIYQ","short_pith_number":"pith:3V46CIZ6","schema_version":"1.0","canonical_sha256":"dd79e1233ea2980f3e976f10bbecc8c42bdfb391df485944ff17f4064147eeaa","source":{"kind":"arxiv","id":"2606.25268","version":1},"attestation_state":"computed","paper":{"title":"Learning Interpretable Text Signals for Structured Responses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.AP","authors_text":"Ben Powell, Cixiao Jiang, Niall MacKay","submitted_at":"2026-06-24T01:08:05Z","abstract_excerpt":"Textual data are often collected alongside structured response variables, but prediction and interpretation are commonly treated as separate tasks. This paper studies rating prediction as an initial case of interpretable text-response modelling, where the aim is to learn textual representations that are both semantically meaningful and aligned with an external response. We propose a joint non-negative matrix factorisation and binomial regression model, in which the document-topic representation is learned from both text reconstruction and rating prediction. Simulation experiments and a real-wo"},"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":"2606.25268","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2026-06-24T01:08:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4bf4dd16017333665156f657bcf553dc39c195ffc3b447caa4afba7916730460","abstract_canon_sha256":"84b5820c873ddf8e18ed14b330c567f90a68621bb30fa428af20261685f06fa4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T00:18:22.574491Z","signature_b64":"Wmi42XYZOrIKssBwe8WYH4/GJalF/4gC52ORZ7AgYEwiOmp29ZsXitwq5Ap4XftP7jva0G3td09OTFFekzSFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd79e1233ea2980f3e976f10bbecc8c42bdfb391df485944ff17f4064147eeaa","last_reissued_at":"2026-06-25T00:18:22.574003Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T00:18:22.574003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Interpretable Text Signals for Structured Responses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.AP","authors_text":"Ben Powell, Cixiao Jiang, Niall MacKay","submitted_at":"2026-06-24T01:08:05Z","abstract_excerpt":"Textual data are often collected alongside structured response variables, but prediction and interpretation are commonly treated as separate tasks. This paper studies rating prediction as an initial case of interpretable text-response modelling, where the aim is to learn textual representations that are both semantically meaningful and aligned with an external response. We propose a joint non-negative matrix factorisation and binomial regression model, in which the document-topic representation is learned from both text reconstruction and rating prediction. Simulation experiments and a real-wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25268","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/2606.25268/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":"2606.25268","created_at":"2026-06-25T00:18:22.574062+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25268v1","created_at":"2026-06-25T00:18:22.574062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25268","created_at":"2026-06-25T00:18:22.574062+00:00"},{"alias_kind":"pith_short_12","alias_value":"3V46CIZ6UKMA","created_at":"2026-06-25T00:18:22.574062+00:00"},{"alias_kind":"pith_short_16","alias_value":"3V46CIZ6UKMA6PUX","created_at":"2026-06-25T00:18:22.574062+00:00"},{"alias_kind":"pith_short_8","alias_value":"3V46CIZ6","created_at":"2026-06-25T00:18:22.574062+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/3V46CIZ6UKMA6PUXN4ILX3GIYQ","json":"https://pith.science/pith/3V46CIZ6UKMA6PUXN4ILX3GIYQ.json","graph_json":"https://pith.science/api/pith-number/3V46CIZ6UKMA6PUXN4ILX3GIYQ/graph.json","events_json":"https://pith.science/api/pith-number/3V46CIZ6UKMA6PUXN4ILX3GIYQ/events.json","paper":"https://pith.science/paper/3V46CIZ6"},"agent_actions":{"view_html":"https://pith.science/pith/3V46CIZ6UKMA6PUXN4ILX3GIYQ","download_json":"https://pith.science/pith/3V46CIZ6UKMA6PUXN4ILX3GIYQ.json","view_paper":"https://pith.science/paper/3V46CIZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25268&json=true","fetch_graph":"https://pith.science/api/pith-number/3V46CIZ6UKMA6PUXN4ILX3GIYQ/graph.json","fetch_events":"https://pith.science/api/pith-number/3V46CIZ6UKMA6PUXN4ILX3GIYQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3V46CIZ6UKMA6PUXN4ILX3GIYQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3V46CIZ6UKMA6PUXN4ILX3GIYQ/action/storage_attestation","attest_author":"https://pith.science/pith/3V46CIZ6UKMA6PUXN4ILX3GIYQ/action/author_attestation","sign_citation":"https://pith.science/pith/3V46CIZ6UKMA6PUXN4ILX3GIYQ/action/citation_signature","submit_replication":"https://pith.science/pith/3V46CIZ6UKMA6PUXN4ILX3GIYQ/action/replication_record"}},"created_at":"2026-06-25T00:18:22.574062+00:00","updated_at":"2026-06-25T00:18:22.574062+00:00"}