{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OCCJ7EIXUYIHOJV6CQEJVYI3RS","short_pith_number":"pith:OCCJ7EIX","schema_version":"1.0","canonical_sha256":"70849f9117a6107726be14089ae11b8cb0806f5c61bf56c0e4f8bd623f3ee9e6","source":{"kind":"arxiv","id":"2204.04413","version":2},"attestation_state":"computed","paper":{"title":"PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Boxing Chen, Heyan Huang, Jiawei Li, Xiaochen Liu, Yang Gao, Yinan Hu, Yu Bai","submitted_at":"2022-04-09T07:40:52Z","abstract_excerpt":"Few-shot abstractive summarization has become a challenging task in natural language generation. To support it, we designed a novel soft prompts architecture coupled with a prompt pre-training plus fine-tuning paradigm that is effective and tunes only extremely light parameters. The soft prompts include continuous input embeddings across an encoder and a decoder to fit the structure of the generation models. Importantly, a novel inner-prompt placed in the text is introduced to capture document-level information. The aim is to devote attention to understanding the document that better prompts t"},"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":"2204.04413","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-09T07:40:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"066fc2e030c655719fd09bcc097552ee4798f20f56a68f6d688f8c38b673d629","abstract_canon_sha256":"7fa0b894c246883710e460084f7be1348eb7a3161b6b955bcc15b4aa0d9e12cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:00.054727Z","signature_b64":"caYazZ3DMfASbTHc/8aQvVrUGyu2QQN0KdmNgLV0cQRDPmFiQu+eAjcfyfGOty406gjG3bZNHhzvZx7LlqVlCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70849f9117a6107726be14089ae11b8cb0806f5c61bf56c0e4f8bd623f3ee9e6","last_reissued_at":"2026-07-05T05:03:00.054299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:00.054299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Boxing Chen, Heyan Huang, Jiawei Li, Xiaochen Liu, Yang Gao, Yinan Hu, Yu Bai","submitted_at":"2022-04-09T07:40:52Z","abstract_excerpt":"Few-shot abstractive summarization has become a challenging task in natural language generation. To support it, we designed a novel soft prompts architecture coupled with a prompt pre-training plus fine-tuning paradigm that is effective and tunes only extremely light parameters. The soft prompts include continuous input embeddings across an encoder and a decoder to fit the structure of the generation models. Importantly, a novel inner-prompt placed in the text is introduced to capture document-level information. The aim is to devote attention to understanding the document that better prompts t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.04413","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/2204.04413/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":"2204.04413","created_at":"2026-07-05T05:03:00.054368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.04413v2","created_at":"2026-07-05T05:03:00.054368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.04413","created_at":"2026-07-05T05:03:00.054368+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCCJ7EIXUYIH","created_at":"2026-07-05T05:03:00.054368+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCCJ7EIXUYIHOJV6","created_at":"2026-07-05T05:03:00.054368+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCCJ7EIX","created_at":"2026-07-05T05:03:00.054368+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/OCCJ7EIXUYIHOJV6CQEJVYI3RS","json":"https://pith.science/pith/OCCJ7EIXUYIHOJV6CQEJVYI3RS.json","graph_json":"https://pith.science/api/pith-number/OCCJ7EIXUYIHOJV6CQEJVYI3RS/graph.json","events_json":"https://pith.science/api/pith-number/OCCJ7EIXUYIHOJV6CQEJVYI3RS/events.json","paper":"https://pith.science/paper/OCCJ7EIX"},"agent_actions":{"view_html":"https://pith.science/pith/OCCJ7EIXUYIHOJV6CQEJVYI3RS","download_json":"https://pith.science/pith/OCCJ7EIXUYIHOJV6CQEJVYI3RS.json","view_paper":"https://pith.science/paper/OCCJ7EIX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.04413&json=true","fetch_graph":"https://pith.science/api/pith-number/OCCJ7EIXUYIHOJV6CQEJVYI3RS/graph.json","fetch_events":"https://pith.science/api/pith-number/OCCJ7EIXUYIHOJV6CQEJVYI3RS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCCJ7EIXUYIHOJV6CQEJVYI3RS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCCJ7EIXUYIHOJV6CQEJVYI3RS/action/storage_attestation","attest_author":"https://pith.science/pith/OCCJ7EIXUYIHOJV6CQEJVYI3RS/action/author_attestation","sign_citation":"https://pith.science/pith/OCCJ7EIXUYIHOJV6CQEJVYI3RS/action/citation_signature","submit_replication":"https://pith.science/pith/OCCJ7EIXUYIHOJV6CQEJVYI3RS/action/replication_record"}},"created_at":"2026-07-05T05:03:00.054368+00:00","updated_at":"2026-07-05T05:03:00.054368+00:00"}