{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SVYPO4G2JLDNYJRT4CI5R5JT6O","short_pith_number":"pith:SVYPO4G2","schema_version":"1.0","canonical_sha256":"9570f770da4ac6dc2633e091d8f533f3a33c6cb3266b75bb912181a259c60e5e","source":{"kind":"arxiv","id":"2004.15011","version":3},"attestation_state":"computed","paper":{"title":"TLDR: Extreme Summarization of Scientific Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Daniel S. Weld, Isabel Cachola, Kyle Lo","submitted_at":"2020-04-30T17:56:18Z","abstract_excerpt":"We introduce TLDR generation, a new form of extreme summarization, for scientific papers. TLDR generation involves high source compression and requires expert background knowledge and understanding of complex domain-specific language. To facilitate study on this task, we introduce SciTLDR, a new multi-target dataset of 5.4K TLDRs over 3.2K papers. SciTLDR contains both author-written and expert-derived TLDRs, where the latter are collected using a novel annotation protocol that produces high-quality summaries while minimizing annotation burden. We propose CATTS, a simple yet effective learning"},"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":"2004.15011","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T17:56:18Z","cross_cats_sorted":[],"title_canon_sha256":"708d8a0055d041bf29802454e2f3c325f81ba824ba08098a32add0775dab49b8","abstract_canon_sha256":"8feae2602c1a466500105932c98456aeacf6a50362e0e174bb60cef8aa5ae95d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:31.027091Z","signature_b64":"X/a2xKrkjMO2byy/SEvTt02TLVvas7MEvOEF/cxdCF5CTjFjPR8azvXULgtJXYSBG+fNi7B6q9VYbCWkQKIoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9570f770da4ac6dc2633e091d8f533f3a33c6cb3266b75bb912181a259c60e5e","last_reissued_at":"2026-07-05T01:41:31.026646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:31.026646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TLDR: Extreme Summarization of Scientific Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Daniel S. Weld, Isabel Cachola, Kyle Lo","submitted_at":"2020-04-30T17:56:18Z","abstract_excerpt":"We introduce TLDR generation, a new form of extreme summarization, for scientific papers. TLDR generation involves high source compression and requires expert background knowledge and understanding of complex domain-specific language. To facilitate study on this task, we introduce SciTLDR, a new multi-target dataset of 5.4K TLDRs over 3.2K papers. SciTLDR contains both author-written and expert-derived TLDRs, where the latter are collected using a novel annotation protocol that produces high-quality summaries while minimizing annotation burden. We propose CATTS, a simple yet effective learning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.15011","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/2004.15011/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":"2004.15011","created_at":"2026-07-05T01:41:31.026698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.15011v3","created_at":"2026-07-05T01:41:31.026698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.15011","created_at":"2026-07-05T01:41:31.026698+00:00"},{"alias_kind":"pith_short_12","alias_value":"SVYPO4G2JLDN","created_at":"2026-07-05T01:41:31.026698+00:00"},{"alias_kind":"pith_short_16","alias_value":"SVYPO4G2JLDNYJRT","created_at":"2026-07-05T01:41:31.026698+00:00"},{"alias_kind":"pith_short_8","alias_value":"SVYPO4G2","created_at":"2026-07-05T01:41:31.026698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2211.09085","citing_title":"Galactica: A Large Language Model for Science","ref_index":152,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SVYPO4G2JLDNYJRT4CI5R5JT6O","json":"https://pith.science/pith/SVYPO4G2JLDNYJRT4CI5R5JT6O.json","graph_json":"https://pith.science/api/pith-number/SVYPO4G2JLDNYJRT4CI5R5JT6O/graph.json","events_json":"https://pith.science/api/pith-number/SVYPO4G2JLDNYJRT4CI5R5JT6O/events.json","paper":"https://pith.science/paper/SVYPO4G2"},"agent_actions":{"view_html":"https://pith.science/pith/SVYPO4G2JLDNYJRT4CI5R5JT6O","download_json":"https://pith.science/pith/SVYPO4G2JLDNYJRT4CI5R5JT6O.json","view_paper":"https://pith.science/paper/SVYPO4G2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.15011&json=true","fetch_graph":"https://pith.science/api/pith-number/SVYPO4G2JLDNYJRT4CI5R5JT6O/graph.json","fetch_events":"https://pith.science/api/pith-number/SVYPO4G2JLDNYJRT4CI5R5JT6O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SVYPO4G2JLDNYJRT4CI5R5JT6O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SVYPO4G2JLDNYJRT4CI5R5JT6O/action/storage_attestation","attest_author":"https://pith.science/pith/SVYPO4G2JLDNYJRT4CI5R5JT6O/action/author_attestation","sign_citation":"https://pith.science/pith/SVYPO4G2JLDNYJRT4CI5R5JT6O/action/citation_signature","submit_replication":"https://pith.science/pith/SVYPO4G2JLDNYJRT4CI5R5JT6O/action/replication_record"}},"created_at":"2026-07-05T01:41:31.026698+00:00","updated_at":"2026-07-05T01:41:31.026698+00:00"}