{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FKXSARZPKBI3263Q4MVHO2L3J3","short_pith_number":"pith:FKXSARZP","schema_version":"1.0","canonical_sha256":"2aaf20472f5051bd7b70e32a77697b4eecc0e419d93bef2588c8be78d9c9714c","source":{"kind":"arxiv","id":"2405.13095","version":1},"attestation_state":"computed","paper":{"title":"Presentations are not always linear! GNN meets LLM for Document-to-Presentation Transformation with Attribution","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anandhavelu Natarajan, Aparna Garimella, Himanshu Maheshwari, Sambaran Bandyopadhyay","submitted_at":"2024-05-21T13:52:33Z","abstract_excerpt":"Automatically generating a presentation from the text of a long document is a challenging and useful problem. In contrast to a flat summary, a presentation needs to have a better and non-linear narrative, i.e., the content of a slide can come from different and non-contiguous parts of the given document. However, it is difficult to incorporate such non-linear mapping of content to slides and ensure that the content is faithful to the document. LLMs are prone to hallucination and their performance degrades with the length of the input document. Towards this, we propose a novel graph based solut"},"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":"2405.13095","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-21T13:52:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"96f66c1e1aa620c1b15ae94694379ead509419b8fbb7d8a6fac71a569d4345d4","abstract_canon_sha256":"9656d263e3c71edd44264dc19ba64d957337f8a7309d3c533513d31fa709e9b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:57.391190Z","signature_b64":"wl2ICLLxpSMP2a0LrVpLAe1m75TYIpk7CXpgzwInoXyy71k4joMTMLscj7KiVIWqh48GHz/vbvSOWF3twpzGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2aaf20472f5051bd7b70e32a77697b4eecc0e419d93bef2588c8be78d9c9714c","last_reissued_at":"2026-07-05T08:21:57.390710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:57.390710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Presentations are not always linear! GNN meets LLM for Document-to-Presentation Transformation with Attribution","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anandhavelu Natarajan, Aparna Garimella, Himanshu Maheshwari, Sambaran Bandyopadhyay","submitted_at":"2024-05-21T13:52:33Z","abstract_excerpt":"Automatically generating a presentation from the text of a long document is a challenging and useful problem. In contrast to a flat summary, a presentation needs to have a better and non-linear narrative, i.e., the content of a slide can come from different and non-contiguous parts of the given document. However, it is difficult to incorporate such non-linear mapping of content to slides and ensure that the content is faithful to the document. LLMs are prone to hallucination and their performance degrades with the length of the input document. Towards this, we propose a novel graph based solut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13095","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/2405.13095/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":"2405.13095","created_at":"2026-07-05T08:21:57.390774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.13095v1","created_at":"2026-07-05T08:21:57.390774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13095","created_at":"2026-07-05T08:21:57.390774+00:00"},{"alias_kind":"pith_short_12","alias_value":"FKXSARZPKBI3","created_at":"2026-07-05T08:21:57.390774+00:00"},{"alias_kind":"pith_short_16","alias_value":"FKXSARZPKBI3263Q","created_at":"2026-07-05T08:21:57.390774+00:00"},{"alias_kind":"pith_short_8","alias_value":"FKXSARZP","created_at":"2026-07-05T08:21:57.390774+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00407","citing_title":"Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15202","citing_title":"DeepSlide: From Artifacts to Presentation Delivery","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":284,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FKXSARZPKBI3263Q4MVHO2L3J3","json":"https://pith.science/pith/FKXSARZPKBI3263Q4MVHO2L3J3.json","graph_json":"https://pith.science/api/pith-number/FKXSARZPKBI3263Q4MVHO2L3J3/graph.json","events_json":"https://pith.science/api/pith-number/FKXSARZPKBI3263Q4MVHO2L3J3/events.json","paper":"https://pith.science/paper/FKXSARZP"},"agent_actions":{"view_html":"https://pith.science/pith/FKXSARZPKBI3263Q4MVHO2L3J3","download_json":"https://pith.science/pith/FKXSARZPKBI3263Q4MVHO2L3J3.json","view_paper":"https://pith.science/paper/FKXSARZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.13095&json=true","fetch_graph":"https://pith.science/api/pith-number/FKXSARZPKBI3263Q4MVHO2L3J3/graph.json","fetch_events":"https://pith.science/api/pith-number/FKXSARZPKBI3263Q4MVHO2L3J3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FKXSARZPKBI3263Q4MVHO2L3J3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FKXSARZPKBI3263Q4MVHO2L3J3/action/storage_attestation","attest_author":"https://pith.science/pith/FKXSARZPKBI3263Q4MVHO2L3J3/action/author_attestation","sign_citation":"https://pith.science/pith/FKXSARZPKBI3263Q4MVHO2L3J3/action/citation_signature","submit_replication":"https://pith.science/pith/FKXSARZPKBI3263Q4MVHO2L3J3/action/replication_record"}},"created_at":"2026-07-05T08:21:57.390774+00:00","updated_at":"2026-07-05T08:21:57.390774+00:00"}