{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:K4CHZBZR7LXIE645XZ3ZEEOOJ4","short_pith_number":"pith:K4CHZBZR","schema_version":"1.0","canonical_sha256":"57047c8731faee827b9dbe779211ce4f08b4442a9971f407bda4a547caeefdc2","source":{"kind":"arxiv","id":"2004.14884","version":3},"attestation_state":"computed","paper":{"title":"Few-Shot Learning for Opinion Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arthur Bra\\v{z}inskas, Ivan Titov, Mirella Lapata","submitted_at":"2020-04-30T15:37:38Z","abstract_excerpt":"Opinion summarization is the automatic creation of text reflecting subjective information expressed in multiple documents, such as user reviews of a product. The task is practically important and has attracted a lot of attention. However, due to the high cost of summary production, datasets large enough for training supervised models are lacking. Instead, the task has been traditionally approached with extractive methods that learn to select text fragments in an unsupervised or weakly-supervised way. Recently, it has been shown that abstractive summaries, potentially more fluent and better at "},"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":"2004.14884","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-30T15:37:38Z","cross_cats_sorted":["cs.CL","cs.NE","stat.ML"],"title_canon_sha256":"69c3ad304629846bdfad4d00c51771fe55a0b577a0937a2011b299bdbe6755a2","abstract_canon_sha256":"d35de951db8cc6afd4209c5a0dd4c483e984514bb51b5ede43140a6cfe2354c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:53.361738Z","signature_b64":"dpR8l3EvQBoHKEnVEHe6r7efzUMP1O4A14DuWxM9/LdoIpDkqHYWxAP2wTEi4Tt/3GcSpYKWn2NDfNiurzlNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57047c8731faee827b9dbe779211ce4f08b4442a9971f407bda4a547caeefdc2","last_reissued_at":"2026-07-05T01:41:53.361339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:53.361339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-Shot Learning for Opinion Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arthur Bra\\v{z}inskas, Ivan Titov, Mirella Lapata","submitted_at":"2020-04-30T15:37:38Z","abstract_excerpt":"Opinion summarization is the automatic creation of text reflecting subjective information expressed in multiple documents, such as user reviews of a product. The task is practically important and has attracted a lot of attention. However, due to the high cost of summary production, datasets large enough for training supervised models are lacking. Instead, the task has been traditionally approached with extractive methods that learn to select text fragments in an unsupervised or weakly-supervised way. Recently, it has been shown that abstractive summaries, potentially more fluent and better at "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14884","kind":"arxiv","version":3},"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/2004.14884/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":"2004.14884","created_at":"2026-07-05T01:41:53.361398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.14884v3","created_at":"2026-07-05T01:41:53.361398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14884","created_at":"2026-07-05T01:41:53.361398+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4CHZBZR7LXI","created_at":"2026-07-05T01:41:53.361398+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4CHZBZR7LXIE645","created_at":"2026-07-05T01:41:53.361398+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4CHZBZR","created_at":"2026-07-05T01:41:53.361398+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04751","citing_title":"LLMs as Architects and Critics for Multi-Source Opinion Summarization","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K4CHZBZR7LXIE645XZ3ZEEOOJ4","json":"https://pith.science/pith/K4CHZBZR7LXIE645XZ3ZEEOOJ4.json","graph_json":"https://pith.science/api/pith-number/K4CHZBZR7LXIE645XZ3ZEEOOJ4/graph.json","events_json":"https://pith.science/api/pith-number/K4CHZBZR7LXIE645XZ3ZEEOOJ4/events.json","paper":"https://pith.science/paper/K4CHZBZR"},"agent_actions":{"view_html":"https://pith.science/pith/K4CHZBZR7LXIE645XZ3ZEEOOJ4","download_json":"https://pith.science/pith/K4CHZBZR7LXIE645XZ3ZEEOOJ4.json","view_paper":"https://pith.science/paper/K4CHZBZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.14884&json=true","fetch_graph":"https://pith.science/api/pith-number/K4CHZBZR7LXIE645XZ3ZEEOOJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/K4CHZBZR7LXIE645XZ3ZEEOOJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4CHZBZR7LXIE645XZ3ZEEOOJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4CHZBZR7LXIE645XZ3ZEEOOJ4/action/storage_attestation","attest_author":"https://pith.science/pith/K4CHZBZR7LXIE645XZ3ZEEOOJ4/action/author_attestation","sign_citation":"https://pith.science/pith/K4CHZBZR7LXIE645XZ3ZEEOOJ4/action/citation_signature","submit_replication":"https://pith.science/pith/K4CHZBZR7LXIE645XZ3ZEEOOJ4/action/replication_record"}},"created_at":"2026-07-05T01:41:53.361398+00:00","updated_at":"2026-07-05T01:41:53.361398+00:00"}