{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WOJDC4VQ6G5BWZ2HPUKAP7Z4Z7","short_pith_number":"pith:WOJDC4VQ","canonical_record":{"source":{"id":"2507.04036","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-05T13:24:15Z","cross_cats_sorted":[],"title_canon_sha256":"363a40ac76b16700eefea19ee9f53a277a3242b4d54f04b9e0de8fddc9b9b5c2","abstract_canon_sha256":"f277644ac66e2e9238b158a61135c30f4930f67d0ee6b23ddd0dfdd4bc3a7d7b"},"schema_version":"1.0"},"canonical_sha256":"b3923172b0f1ba1b67477d1407ff3ccfe6a6d3d5cf02b7821e41300a096818b1","source":{"kind":"arxiv","id":"2507.04036","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04036","created_at":"2026-07-05T11:32:41Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04036v1","created_at":"2026-07-05T11:32:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04036","created_at":"2026-07-05T11:32:41Z"},{"alias_kind":"pith_short_12","alias_value":"WOJDC4VQ6G5B","created_at":"2026-07-05T11:32:41Z"},{"alias_kind":"pith_short_16","alias_value":"WOJDC4VQ6G5BWZ2H","created_at":"2026-07-05T11:32:41Z"},{"alias_kind":"pith_short_8","alias_value":"WOJDC4VQ","created_at":"2026-07-05T11:32:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WOJDC4VQ6G5BWZ2HPUKAP7Z4Z7","target":"record","payload":{"canonical_record":{"source":{"id":"2507.04036","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-05T13:24:15Z","cross_cats_sorted":[],"title_canon_sha256":"363a40ac76b16700eefea19ee9f53a277a3242b4d54f04b9e0de8fddc9b9b5c2","abstract_canon_sha256":"f277644ac66e2e9238b158a61135c30f4930f67d0ee6b23ddd0dfdd4bc3a7d7b"},"schema_version":"1.0"},"canonical_sha256":"b3923172b0f1ba1b67477d1407ff3ccfe6a6d3d5cf02b7821e41300a096818b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:41.195633Z","signature_b64":"P5wx7LZ995OQzIN1ywm2ICJDWY0ymuV2KR2J8B+CoNNcq+VXLp0qjmbl94dX/kU52/uTLzVdWy9FlxtyffhWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3923172b0f1ba1b67477d1407ff3ccfe6a6d3d5cf02b7821e41300a096818b1","last_reissued_at":"2026-07-05T11:32:41.195157Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:41.195157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.04036","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:32:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"76DaNGdyg+dUvdZVg1yhUGbgLf1p630VLKtOsir/qs1pyRIVmaRCg5f1DBidPZJPkcFbp5De4r306nmUG4MYBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:06:57.950933Z"},"content_sha256":"26a690f7db3d333cd9820bde53c32e9847b112d178b03a75ba44d9a908b5eed4","schema_version":"1.0","event_id":"sha256:26a690f7db3d333cd9820bde53c32e9847b112d178b03a75ba44d9a908b5eed4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WOJDC4VQ6G5BWZ2HPUKAP7Z4Z7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PresentAgent: Multimodal Agent for Presentation Video Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Wu, Jingwei Shi, Ling Chen, Meng Fang, Yang Zhao, Yanjie Liang, Zeyu Zhang","submitted_at":"2025-07-05T13:24:15Z","abstract_excerpt":"We present PresentAgent, a multimodal agent that transforms long-form documents into narrated presentation videos. While existing approaches are limited to generating static slides or text summaries, our method advances beyond these limitations by producing fully synchronized visual and spoken content that closely mimics human-style presentations. To achieve this integration, PresentAgent employs a modular pipeline that systematically segments the input document, plans and renders slide-style visual frames, generates contextual spoken narration with large language models and Text-to-Speech mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04036","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/2507.04036/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:32:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6goR7RNSy5E4wMuJjxQrqzxxGpLStFbNYMEOzQ0CgnvXy07DItwRPKUeo7odibXOg2IeKCz5eMbQiLtff1DmBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:06:57.951446Z"},"content_sha256":"423ba5216682a0fbb8ecbc8d579765adad8a687088405ade2f64596a764bc2d2","schema_version":"1.0","event_id":"sha256:423ba5216682a0fbb8ecbc8d579765adad8a687088405ade2f64596a764bc2d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WOJDC4VQ6G5BWZ2HPUKAP7Z4Z7/bundle.json","state_url":"https://pith.science/pith/WOJDC4VQ6G5BWZ2HPUKAP7Z4Z7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WOJDC4VQ6G5BWZ2HPUKAP7Z4Z7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T12:06:57Z","links":{"resolver":"https://pith.science/pith/WOJDC4VQ6G5BWZ2HPUKAP7Z4Z7","bundle":"https://pith.science/pith/WOJDC4VQ6G5BWZ2HPUKAP7Z4Z7/bundle.json","state":"https://pith.science/pith/WOJDC4VQ6G5BWZ2HPUKAP7Z4Z7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WOJDC4VQ6G5BWZ2HPUKAP7Z4Z7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WOJDC4VQ6G5BWZ2HPUKAP7Z4Z7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f277644ac66e2e9238b158a61135c30f4930f67d0ee6b23ddd0dfdd4bc3a7d7b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-05T13:24:15Z","title_canon_sha256":"363a40ac76b16700eefea19ee9f53a277a3242b4d54f04b9e0de8fddc9b9b5c2"},"schema_version":"1.0","source":{"id":"2507.04036","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04036","created_at":"2026-07-05T11:32:41Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04036v1","created_at":"2026-07-05T11:32:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04036","created_at":"2026-07-05T11:32:41Z"},{"alias_kind":"pith_short_12","alias_value":"WOJDC4VQ6G5B","created_at":"2026-07-05T11:32:41Z"},{"alias_kind":"pith_short_16","alias_value":"WOJDC4VQ6G5BWZ2H","created_at":"2026-07-05T11:32:41Z"},{"alias_kind":"pith_short_8","alias_value":"WOJDC4VQ","created_at":"2026-07-05T11:32:41Z"}],"graph_snapshots":[{"event_id":"sha256:423ba5216682a0fbb8ecbc8d579765adad8a687088405ade2f64596a764bc2d2","target":"graph","created_at":"2026-07-05T11:32:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.04036/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present PresentAgent, a multimodal agent that transforms long-form documents into narrated presentation videos. While existing approaches are limited to generating static slides or text summaries, our method advances beyond these limitations by producing fully synchronized visual and spoken content that closely mimics human-style presentations. To achieve this integration, PresentAgent employs a modular pipeline that systematically segments the input document, plans and renders slide-style visual frames, generates contextual spoken narration with large language models and Text-to-Speech mod","authors_text":"Biao Wu, Jingwei Shi, Ling Chen, Meng Fang, Yang Zhao, Yanjie Liang, Zeyu Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-05T13:24:15Z","title":"PresentAgent: Multimodal Agent for Presentation Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04036","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:26a690f7db3d333cd9820bde53c32e9847b112d178b03a75ba44d9a908b5eed4","target":"record","created_at":"2026-07-05T11:32:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f277644ac66e2e9238b158a61135c30f4930f67d0ee6b23ddd0dfdd4bc3a7d7b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-05T13:24:15Z","title_canon_sha256":"363a40ac76b16700eefea19ee9f53a277a3242b4d54f04b9e0de8fddc9b9b5c2"},"schema_version":"1.0","source":{"id":"2507.04036","kind":"arxiv","version":1}},"canonical_sha256":"b3923172b0f1ba1b67477d1407ff3ccfe6a6d3d5cf02b7821e41300a096818b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3923172b0f1ba1b67477d1407ff3ccfe6a6d3d5cf02b7821e41300a096818b1","first_computed_at":"2026-07-05T11:32:41.195157Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:41.195157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P5wx7LZ995OQzIN1ywm2ICJDWY0ymuV2KR2J8B+CoNNcq+VXLp0qjmbl94dX/kU52/uTLzVdWy9FlxtyffhWCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:41.195633Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.04036","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26a690f7db3d333cd9820bde53c32e9847b112d178b03a75ba44d9a908b5eed4","sha256:423ba5216682a0fbb8ecbc8d579765adad8a687088405ade2f64596a764bc2d2"],"state_sha256":"c910be361282a007fca6c078f01ec9ef90adf99d61cf70c2c4aa99ccc1b24b04"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"luOIC/rPBzJOqCE3aCOreE2mF7X4T4HLKrmWhr16gndCAq2NoaO2cYNnIdW5SAX54HJ7p3HO03+m8jEy+uAwBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:06:57.959810Z","bundle_sha256":"e0cdf521f8943c55642d50b5493329ec3063c724b334c444a9c71e0f4b8ce1e8"}}