{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BVIKVITU7ZHFL5OBM4VVHKXTRZ","short_pith_number":"pith:BVIKVITU","schema_version":"1.0","canonical_sha256":"0d50aaa274fe4e55f5c1672b53aaf38e608e1f647e9f83b6d91bd8e93362588a","source":{"kind":"arxiv","id":"2311.09836","version":1},"attestation_state":"computed","paper":{"title":"PELMS: Pre-training for Effective Low-Shot Multi-Document Summarization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Joseph J. Peper, Lu Wang, Wenzhao Qiu","submitted_at":"2023-11-16T12:05:23Z","abstract_excerpt":"We investigate pre-training techniques for abstractive multi-document summarization (MDS), which is much less studied than summarizing single documents. Though recent work has demonstrated the effectiveness of highlighting information salience for pre-training strategy design, it struggles to generate abstractive and reflective summaries, which are critical properties for MDS. To this end, we present PELMS, a pre-trained model that uses objectives based on semantic coherence heuristics and faithfulness constraints with un-labeled multi-document inputs, to promote the generation of concise, flu"},"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":"2311.09836","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T12:05:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0cf3d3deedd70f3c7c9ef49ef4cf61383e6d81beb31dc1699bfc59c6b165fd95","abstract_canon_sha256":"3933797032dce44e343f5ce42eb5bb977bfe4ffd8826f18a766c0a3689f80a76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:33.518327Z","signature_b64":"QXaBYFcK/HOK7cOemWL2AIZnFhdmyvKo3YZEnrY7P/UOy1z8Fzn5p7f7cy/cJGmqxmB6tHVjaaSARKB7PRY+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d50aaa274fe4e55f5c1672b53aaf38e608e1f647e9f83b6d91bd8e93362588a","last_reissued_at":"2026-07-05T07:13:33.517880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:33.517880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PELMS: Pre-training for Effective Low-Shot Multi-Document Summarization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Joseph J. Peper, Lu Wang, Wenzhao Qiu","submitted_at":"2023-11-16T12:05:23Z","abstract_excerpt":"We investigate pre-training techniques for abstractive multi-document summarization (MDS), which is much less studied than summarizing single documents. Though recent work has demonstrated the effectiveness of highlighting information salience for pre-training strategy design, it struggles to generate abstractive and reflective summaries, which are critical properties for MDS. To this end, we present PELMS, a pre-trained model that uses objectives based on semantic coherence heuristics and faithfulness constraints with un-labeled multi-document inputs, to promote the generation of concise, flu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09836","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/2311.09836/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":"2311.09836","created_at":"2026-07-05T07:13:33.517927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09836v1","created_at":"2026-07-05T07:13:33.517927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09836","created_at":"2026-07-05T07:13:33.517927+00:00"},{"alias_kind":"pith_short_12","alias_value":"BVIKVITU7ZHF","created_at":"2026-07-05T07:13:33.517927+00:00"},{"alias_kind":"pith_short_16","alias_value":"BVIKVITU7ZHFL5OB","created_at":"2026-07-05T07:13:33.517927+00:00"},{"alias_kind":"pith_short_8","alias_value":"BVIKVITU","created_at":"2026-07-05T07:13:33.517927+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14927","citing_title":"MDBench: A Synthetic Multi-Document Reasoning Benchmark Generated with Knowledge Guidance","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BVIKVITU7ZHFL5OBM4VVHKXTRZ","json":"https://pith.science/pith/BVIKVITU7ZHFL5OBM4VVHKXTRZ.json","graph_json":"https://pith.science/api/pith-number/BVIKVITU7ZHFL5OBM4VVHKXTRZ/graph.json","events_json":"https://pith.science/api/pith-number/BVIKVITU7ZHFL5OBM4VVHKXTRZ/events.json","paper":"https://pith.science/paper/BVIKVITU"},"agent_actions":{"view_html":"https://pith.science/pith/BVIKVITU7ZHFL5OBM4VVHKXTRZ","download_json":"https://pith.science/pith/BVIKVITU7ZHFL5OBM4VVHKXTRZ.json","view_paper":"https://pith.science/paper/BVIKVITU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09836&json=true","fetch_graph":"https://pith.science/api/pith-number/BVIKVITU7ZHFL5OBM4VVHKXTRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/BVIKVITU7ZHFL5OBM4VVHKXTRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BVIKVITU7ZHFL5OBM4VVHKXTRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BVIKVITU7ZHFL5OBM4VVHKXTRZ/action/storage_attestation","attest_author":"https://pith.science/pith/BVIKVITU7ZHFL5OBM4VVHKXTRZ/action/author_attestation","sign_citation":"https://pith.science/pith/BVIKVITU7ZHFL5OBM4VVHKXTRZ/action/citation_signature","submit_replication":"https://pith.science/pith/BVIKVITU7ZHFL5OBM4VVHKXTRZ/action/replication_record"}},"created_at":"2026-07-05T07:13:33.517927+00:00","updated_at":"2026-07-05T07:13:33.517927+00:00"}