{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AZ6FODH67H4X2TYGNTEQ72QGEB","short_pith_number":"pith:AZ6FODH6","schema_version":"1.0","canonical_sha256":"067c570cfef9f97d4f066cc90fea062050e1515c3d304b468afd2b2e35c96ced","source":{"kind":"arxiv","id":"2301.03252","version":1},"attestation_state":"computed","paper":{"title":"Active Learning for Abstractive Text Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akim Tsvigun, Alexander Panchenko, Artem Shelmanov, Artemy Belousov, Danila Sedashov, Eldar Damirov, Ivan Lazichny, Ivan Lysenko, Leonid Sanochkin, Maxim Panov, Mikhail Burtsev, Vladimir Karlov","submitted_at":"2023-01-09T10:33:14Z","abstract_excerpt":"Construction of human-curated annotated datasets for abstractive text summarization (ATS) is very time-consuming and expensive because creating each instance requires a human annotator to read a long document and compose a shorter summary that would preserve the key information relayed by the original document. Active Learning (AL) is a technique developed to reduce the amount of annotation required to achieve a certain level of machine learning model performance. In information extraction and text classification, AL can reduce the amount of labor up to multiple times. Despite its potential fo"},"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":"2301.03252","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-09T10:33:14Z","cross_cats_sorted":[],"title_canon_sha256":"a125a2579a3fbe52d050aae06210c6be84bd09966778e5e5f8e4da1c425223bd","abstract_canon_sha256":"4146116c91449834b45fd74ea0c6dd74f583a7334dab43c6bb18c7cbede65a93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:31:27.438190Z","signature_b64":"lLZiAagHrx1O6ZxHkJeueQbSjFLuqdOjRYMmxOj+n5vmIWbsm7VZZ4TKxI6zO4x7ylTLKgixPyHmbEQAdxJ/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"067c570cfef9f97d4f066cc90fea062050e1515c3d304b468afd2b2e35c96ced","last_reissued_at":"2026-07-05T05:31:27.437776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:31:27.437776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active Learning for Abstractive Text Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akim Tsvigun, Alexander Panchenko, Artem Shelmanov, Artemy Belousov, Danila Sedashov, Eldar Damirov, Ivan Lazichny, Ivan Lysenko, Leonid Sanochkin, Maxim Panov, Mikhail Burtsev, Vladimir Karlov","submitted_at":"2023-01-09T10:33:14Z","abstract_excerpt":"Construction of human-curated annotated datasets for abstractive text summarization (ATS) is very time-consuming and expensive because creating each instance requires a human annotator to read a long document and compose a shorter summary that would preserve the key information relayed by the original document. Active Learning (AL) is a technique developed to reduce the amount of annotation required to achieve a certain level of machine learning model performance. In information extraction and text classification, AL can reduce the amount of labor up to multiple times. Despite its potential fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.03252","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/2301.03252/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":"2301.03252","created_at":"2026-07-05T05:31:27.437834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.03252v1","created_at":"2026-07-05T05:31:27.437834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.03252","created_at":"2026-07-05T05:31:27.437834+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZ6FODH67H4X","created_at":"2026-07-05T05:31:27.437834+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZ6FODH67H4X2TYG","created_at":"2026-07-05T05:31:27.437834+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZ6FODH6","created_at":"2026-07-05T05:31:27.437834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03292","citing_title":"ALPET: Active Few-shot Learning for Citation Worthiness Detection in Low-Resource Wikipedia Languages","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AZ6FODH67H4X2TYGNTEQ72QGEB","json":"https://pith.science/pith/AZ6FODH67H4X2TYGNTEQ72QGEB.json","graph_json":"https://pith.science/api/pith-number/AZ6FODH67H4X2TYGNTEQ72QGEB/graph.json","events_json":"https://pith.science/api/pith-number/AZ6FODH67H4X2TYGNTEQ72QGEB/events.json","paper":"https://pith.science/paper/AZ6FODH6"},"agent_actions":{"view_html":"https://pith.science/pith/AZ6FODH67H4X2TYGNTEQ72QGEB","download_json":"https://pith.science/pith/AZ6FODH67H4X2TYGNTEQ72QGEB.json","view_paper":"https://pith.science/paper/AZ6FODH6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.03252&json=true","fetch_graph":"https://pith.science/api/pith-number/AZ6FODH67H4X2TYGNTEQ72QGEB/graph.json","fetch_events":"https://pith.science/api/pith-number/AZ6FODH67H4X2TYGNTEQ72QGEB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZ6FODH67H4X2TYGNTEQ72QGEB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZ6FODH67H4X2TYGNTEQ72QGEB/action/storage_attestation","attest_author":"https://pith.science/pith/AZ6FODH67H4X2TYGNTEQ72QGEB/action/author_attestation","sign_citation":"https://pith.science/pith/AZ6FODH67H4X2TYGNTEQ72QGEB/action/citation_signature","submit_replication":"https://pith.science/pith/AZ6FODH67H4X2TYGNTEQ72QGEB/action/replication_record"}},"created_at":"2026-07-05T05:31:27.437834+00:00","updated_at":"2026-07-05T05:31:27.437834+00:00"}