{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FYRWB25JUOIBGZFSZEAK2CXGTK","short_pith_number":"pith:FYRWB25J","schema_version":"1.0","canonical_sha256":"2e2360eba9a3901364b2c900ad0ae69aaa81dd9f245843d60c34df952faef2c2","source":{"kind":"arxiv","id":"2211.01837","version":2},"attestation_state":"computed","paper":{"title":"Latent Prompt Tuning for Text Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Si-Qing Chen, Xingxing Zhang, Xun Wang, Yubo Zhang","submitted_at":"2022-11-03T14:18:48Z","abstract_excerpt":"Prompts with different control signals (e.g., length, keywords, etc.) can be used to control text summarization. When control signals are available, they can control the properties of generated summaries and potentially improve summarization quality (since more information are given). Unfortunately, control signals are not already available during inference time. In this paper, we propose Lotus (shorthand for Latent Prompt Tuning for Summarization), which is a single model that can be applied in both controlled and uncontrolled (without control signals) modes. During training, Lotus learns lat"},"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":"2211.01837","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-03T14:18:48Z","cross_cats_sorted":[],"title_canon_sha256":"95878862268636f37dbd73255855bac78305801604ad6252547a9129e84dc997","abstract_canon_sha256":"c03349be7489573be1944db1fa24b26e7d0c56f26409a75ca6b05722faa7178c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:10.413077Z","signature_b64":"uEGbKmlv/PqKJ0YURE/UNaOgqxS+E8Th0TWVHwt+zQF4vcgZNWG3B88P9RnUb2wG5Uc3+ERa9nFcWi+zNuekDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e2360eba9a3901364b2c900ad0ae69aaa81dd9f245843d60c34df952faef2c2","last_reissued_at":"2026-07-05T05:26:10.412636Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:10.412636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Prompt Tuning for Text Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Si-Qing Chen, Xingxing Zhang, Xun Wang, Yubo Zhang","submitted_at":"2022-11-03T14:18:48Z","abstract_excerpt":"Prompts with different control signals (e.g., length, keywords, etc.) can be used to control text summarization. When control signals are available, they can control the properties of generated summaries and potentially improve summarization quality (since more information are given). Unfortunately, control signals are not already available during inference time. In this paper, we propose Lotus (shorthand for Latent Prompt Tuning for Summarization), which is a single model that can be applied in both controlled and uncontrolled (without control signals) modes. During training, Lotus learns lat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01837","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/2211.01837/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":"2211.01837","created_at":"2026-07-05T05:26:10.412693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.01837v2","created_at":"2026-07-05T05:26:10.412693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01837","created_at":"2026-07-05T05:26:10.412693+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYRWB25JUOIB","created_at":"2026-07-05T05:26:10.412693+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYRWB25JUOIBGZFS","created_at":"2026-07-05T05:26:10.412693+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYRWB25J","created_at":"2026-07-05T05:26:10.412693+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.14033","citing_title":"Hansel: Output Length Controlling Framework for Large Language Models","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FYRWB25JUOIBGZFSZEAK2CXGTK","json":"https://pith.science/pith/FYRWB25JUOIBGZFSZEAK2CXGTK.json","graph_json":"https://pith.science/api/pith-number/FYRWB25JUOIBGZFSZEAK2CXGTK/graph.json","events_json":"https://pith.science/api/pith-number/FYRWB25JUOIBGZFSZEAK2CXGTK/events.json","paper":"https://pith.science/paper/FYRWB25J"},"agent_actions":{"view_html":"https://pith.science/pith/FYRWB25JUOIBGZFSZEAK2CXGTK","download_json":"https://pith.science/pith/FYRWB25JUOIBGZFSZEAK2CXGTK.json","view_paper":"https://pith.science/paper/FYRWB25J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.01837&json=true","fetch_graph":"https://pith.science/api/pith-number/FYRWB25JUOIBGZFSZEAK2CXGTK/graph.json","fetch_events":"https://pith.science/api/pith-number/FYRWB25JUOIBGZFSZEAK2CXGTK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYRWB25JUOIBGZFSZEAK2CXGTK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYRWB25JUOIBGZFSZEAK2CXGTK/action/storage_attestation","attest_author":"https://pith.science/pith/FYRWB25JUOIBGZFSZEAK2CXGTK/action/author_attestation","sign_citation":"https://pith.science/pith/FYRWB25JUOIBGZFSZEAK2CXGTK/action/citation_signature","submit_replication":"https://pith.science/pith/FYRWB25JUOIBGZFSZEAK2CXGTK/action/replication_record"}},"created_at":"2026-07-05T05:26:10.412693+00:00","updated_at":"2026-07-05T05:26:10.412693+00:00"}