{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:M3GNM3FD2ZD2KHBC5CGNW376RK","short_pith_number":"pith:M3GNM3FD","schema_version":"1.0","canonical_sha256":"66ccd66ca3d647a51c22e88cdb6ffe8abe08ca9b9605475e0340cbd0f74f150b","source":{"kind":"arxiv","id":"2105.03664","version":1},"attestation_state":"computed","paper":{"title":"D2S: Document-to-Slide Generation Via Query-Based Text Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dakuo Wang, Edward Sun, Nancy X.R. Wang, Yufang Hou, Yunfeng Zhang","submitted_at":"2021-05-08T10:29:41Z","abstract_excerpt":"Presentations are critical for communication in all areas of our lives, yet the creation of slide decks is often tedious and time-consuming. There has been limited research aiming to automate the document-to-slides generation process and all face a critical challenge: no publicly available dataset for training and benchmarking. In this work, we first contribute a new dataset, SciDuet, consisting of pairs of papers and their corresponding slides decks from recent years' NLP and ML conferences (e.g., ACL). Secondly, we present D2S, a novel system that tackles the document-to-slides task with a 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":"2105.03664","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-08T10:29:41Z","cross_cats_sorted":[],"title_canon_sha256":"9f6253f785bb4e194b1ab197ed286c36196e2fd5a44570cb14c90bde319638d8","abstract_canon_sha256":"112577fdec32a3eaa8e12fbeefe74e92f44c63e8fb45408ae18ffc990a57b935"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:38:37.796715Z","signature_b64":"f8YRQt7qdFGF2pDxASGBkl6aPjEIAtT2dszaaEv5mVx5ArMEqdQMkEF8E4go1MmSYtmwA//C7pUlWHsKQ14zBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66ccd66ca3d647a51c22e88cdb6ffe8abe08ca9b9605475e0340cbd0f74f150b","last_reissued_at":"2026-07-05T02:38:37.796286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:38:37.796286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"D2S: Document-to-Slide Generation Via Query-Based Text Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dakuo Wang, Edward Sun, Nancy X.R. Wang, Yufang Hou, Yunfeng Zhang","submitted_at":"2021-05-08T10:29:41Z","abstract_excerpt":"Presentations are critical for communication in all areas of our lives, yet the creation of slide decks is often tedious and time-consuming. There has been limited research aiming to automate the document-to-slides generation process and all face a critical challenge: no publicly available dataset for training and benchmarking. In this work, we first contribute a new dataset, SciDuet, consisting of pairs of papers and their corresponding slides decks from recent years' NLP and ML conferences (e.g., ACL). Secondly, we present D2S, a novel system that tackles the document-to-slides task with a t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.03664","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/2105.03664/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":"2105.03664","created_at":"2026-07-05T02:38:37.796353+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.03664v1","created_at":"2026-07-05T02:38:37.796353+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.03664","created_at":"2026-07-05T02:38:37.796353+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3GNM3FD2ZD2","created_at":"2026-07-05T02:38:37.796353+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3GNM3FD2ZD2KHBC","created_at":"2026-07-05T02:38:37.796353+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3GNM3FD","created_at":"2026-07-05T02:38:37.796353+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03951","citing_title":"Demo2Tutorial: From Human Experience to Multimodal Software Tutorials","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17162","citing_title":"MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M3GNM3FD2ZD2KHBC5CGNW376RK","json":"https://pith.science/pith/M3GNM3FD2ZD2KHBC5CGNW376RK.json","graph_json":"https://pith.science/api/pith-number/M3GNM3FD2ZD2KHBC5CGNW376RK/graph.json","events_json":"https://pith.science/api/pith-number/M3GNM3FD2ZD2KHBC5CGNW376RK/events.json","paper":"https://pith.science/paper/M3GNM3FD"},"agent_actions":{"view_html":"https://pith.science/pith/M3GNM3FD2ZD2KHBC5CGNW376RK","download_json":"https://pith.science/pith/M3GNM3FD2ZD2KHBC5CGNW376RK.json","view_paper":"https://pith.science/paper/M3GNM3FD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.03664&json=true","fetch_graph":"https://pith.science/api/pith-number/M3GNM3FD2ZD2KHBC5CGNW376RK/graph.json","fetch_events":"https://pith.science/api/pith-number/M3GNM3FD2ZD2KHBC5CGNW376RK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3GNM3FD2ZD2KHBC5CGNW376RK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3GNM3FD2ZD2KHBC5CGNW376RK/action/storage_attestation","attest_author":"https://pith.science/pith/M3GNM3FD2ZD2KHBC5CGNW376RK/action/author_attestation","sign_citation":"https://pith.science/pith/M3GNM3FD2ZD2KHBC5CGNW376RK/action/citation_signature","submit_replication":"https://pith.science/pith/M3GNM3FD2ZD2KHBC5CGNW376RK/action/replication_record"}},"created_at":"2026-07-05T02:38:37.796353+00:00","updated_at":"2026-07-05T02:38:37.796353+00:00"}