{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:W5VUIU24H5FWJXQ2QQ2UCMYMDQ","short_pith_number":"pith:W5VUIU24","schema_version":"1.0","canonical_sha256":"b76b44535c3f4b64de1a843541330c1c1f225d636ba1ebfb66c231c73e1ad690","source":{"kind":"arxiv","id":"2212.02924","version":1},"attestation_state":"computed","paper":{"title":"Controlled Text Generation using T5 based Encoder-Decoder Soft Prompt Tuning and Analysis of the Utility of Generated Text in AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Damith Chamalke Senadeera, Julia Ive","submitted_at":"2022-12-06T12:31:53Z","abstract_excerpt":"Controlled text generation is a very important task in the arena of natural language processing due to its promising applications. In order to achieve this task we mainly introduce the novel soft prompt tuning method of using soft prompts at both encoder and decoder levels together in a T5 model and investigate the performance as the behaviour of an additional soft prompt related to the decoder of a T5 model in controlled text generation remained unexplored. Then we also investigate the feasibility of steering the output of this extended soft prompted T5 model at decoder level and finally anal"},"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":"2212.02924","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-06T12:31:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"98fd4cc5e19e58f60ccc14d8d6d6745da3ac7057125636f7a88d934f073fdb1d","abstract_canon_sha256":"6ed1d7d18844a592226ac4796b166d0b199d27bd998e00215ed95d6e1061401f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:35.872149Z","signature_b64":"NE1IZLDNZb9zl8h86DFUgAieIm4zrduOW235Y1pjRuJTpcMDdHSWUEymwoiPhOnSUyrSpHdpnUA4jzzSQXonDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b76b44535c3f4b64de1a843541330c1c1f225d636ba1ebfb66c231c73e1ad690","last_reissued_at":"2026-07-05T05:22:35.871794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:35.871794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controlled Text Generation using T5 based Encoder-Decoder Soft Prompt Tuning and Analysis of the Utility of Generated Text in AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Damith Chamalke Senadeera, Julia Ive","submitted_at":"2022-12-06T12:31:53Z","abstract_excerpt":"Controlled text generation is a very important task in the arena of natural language processing due to its promising applications. In order to achieve this task we mainly introduce the novel soft prompt tuning method of using soft prompts at both encoder and decoder levels together in a T5 model and investigate the performance as the behaviour of an additional soft prompt related to the decoder of a T5 model in controlled text generation remained unexplored. Then we also investigate the feasibility of steering the output of this extended soft prompted T5 model at decoder level and finally anal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.02924","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/2212.02924/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":"2212.02924","created_at":"2026-07-05T05:22:35.871852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.02924v1","created_at":"2026-07-05T05:22:35.871852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.02924","created_at":"2026-07-05T05:22:35.871852+00:00"},{"alias_kind":"pith_short_12","alias_value":"W5VUIU24H5FW","created_at":"2026-07-05T05:22:35.871852+00:00"},{"alias_kind":"pith_short_16","alias_value":"W5VUIU24H5FWJXQ2","created_at":"2026-07-05T05:22:35.871852+00:00"},{"alias_kind":"pith_short_8","alias_value":"W5VUIU24","created_at":"2026-07-05T05:22:35.871852+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24319","citing_title":"HiCaM: A Hierarchical-Causal Modification Framework for Long-Form Text Modification","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W5VUIU24H5FWJXQ2QQ2UCMYMDQ","json":"https://pith.science/pith/W5VUIU24H5FWJXQ2QQ2UCMYMDQ.json","graph_json":"https://pith.science/api/pith-number/W5VUIU24H5FWJXQ2QQ2UCMYMDQ/graph.json","events_json":"https://pith.science/api/pith-number/W5VUIU24H5FWJXQ2QQ2UCMYMDQ/events.json","paper":"https://pith.science/paper/W5VUIU24"},"agent_actions":{"view_html":"https://pith.science/pith/W5VUIU24H5FWJXQ2QQ2UCMYMDQ","download_json":"https://pith.science/pith/W5VUIU24H5FWJXQ2QQ2UCMYMDQ.json","view_paper":"https://pith.science/paper/W5VUIU24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.02924&json=true","fetch_graph":"https://pith.science/api/pith-number/W5VUIU24H5FWJXQ2QQ2UCMYMDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/W5VUIU24H5FWJXQ2QQ2UCMYMDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W5VUIU24H5FWJXQ2QQ2UCMYMDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W5VUIU24H5FWJXQ2QQ2UCMYMDQ/action/storage_attestation","attest_author":"https://pith.science/pith/W5VUIU24H5FWJXQ2QQ2UCMYMDQ/action/author_attestation","sign_citation":"https://pith.science/pith/W5VUIU24H5FWJXQ2QQ2UCMYMDQ/action/citation_signature","submit_replication":"https://pith.science/pith/W5VUIU24H5FWJXQ2QQ2UCMYMDQ/action/replication_record"}},"created_at":"2026-07-05T05:22:35.871852+00:00","updated_at":"2026-07-05T05:22:35.871852+00:00"}