{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VTH2F4UGCTSYUZC7462XALUDMY","short_pith_number":"pith:VTH2F4UG","canonical_record":{"source":{"id":"2403.07944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-10T16:09:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e3ce44a4ed39d570580868057b0489dad2c0c1045486127dcf31190d9cb92915","abstract_canon_sha256":"0270f289e276278bb87f6370a6bb282d6098be45ede71ef34ccf317ea98a53f3"},"schema_version":"1.0"},"canonical_sha256":"accfa2f28614e58a645fe7b5702e83660435d69ae63895dafe80290b5be1e00f","source":{"kind":"arxiv","id":"2403.07944","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.07944","created_at":"2026-07-05T07:55:32Z"},{"alias_kind":"arxiv_version","alias_value":"2403.07944v1","created_at":"2026-07-05T07:55:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07944","created_at":"2026-07-05T07:55:32Z"},{"alias_kind":"pith_short_12","alias_value":"VTH2F4UGCTSY","created_at":"2026-07-05T07:55:32Z"},{"alias_kind":"pith_short_16","alias_value":"VTH2F4UGCTSYUZC7","created_at":"2026-07-05T07:55:32Z"},{"alias_kind":"pith_short_8","alias_value":"VTH2F4UG","created_at":"2026-07-05T07:55:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VTH2F4UGCTSYUZC7462XALUDMY","target":"record","payload":{"canonical_record":{"source":{"id":"2403.07944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-10T16:09:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e3ce44a4ed39d570580868057b0489dad2c0c1045486127dcf31190d9cb92915","abstract_canon_sha256":"0270f289e276278bb87f6370a6bb282d6098be45ede71ef34ccf317ea98a53f3"},"schema_version":"1.0"},"canonical_sha256":"accfa2f28614e58a645fe7b5702e83660435d69ae63895dafe80290b5be1e00f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:32.498131Z","signature_b64":"EMH9WaCCjgsfY1+6uUG7rwRyW64CnQoP9vo/kuLa0pdpZmHjTQrwhljRRYcDglakWUe4K29HJddSKOHlZ1t6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"accfa2f28614e58a645fe7b5702e83660435d69ae63895dafe80290b5be1e00f","last_reissued_at":"2026-07-05T07:55:32.497760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:32.497760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.07944","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":"2026-07-05T07:55:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vP1Jru07XipOJFscsXZ0F9XlP1TbSfruKX61CA/3MKyPtAz5dmz0xmUEJYPFlEdfMhLy4YXVuCskVmpBW09gBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T10:46:32.177536Z"},"content_sha256":"0e8d8c17f3c64db70cb2ecc6dd41873a1cdcf4f67d774491a2b614bc0d228012","schema_version":"1.0","event_id":"sha256:0e8d8c17f3c64db70cb2ecc6dd41873a1cdcf4f67d774491a2b614bc0d228012"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VTH2F4UGCTSYUZC7462XALUDMY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WorldGPT: A Sora-Inspired Video AI Agent as Rich World Models from Text and Image Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bang Yang, Chris Kelly, Cindy Yang, Deshun Yang, Luhui Hu, Yuexian Zou, Yu Tian, Zihao Li","submitted_at":"2024-03-10T16:09:02Z","abstract_excerpt":"Several text-to-video diffusion models have demonstrated commendable capabilities in synthesizing high-quality video content. However, it remains a formidable challenge pertaining to maintaining temporal consistency and ensuring action smoothness throughout the generated sequences. In this paper, we present an innovative video generation AI agent that harnesses the power of Sora-inspired multimodal learning to build skilled world models framework based on textual prompts and accompanying images. The framework includes two parts: prompt enhancer and full video translation. The first part employ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07944","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/2403.07944/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":"2026-07-05T07:55:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kq3brig5t9ZpfshHy3CBVfHWfhAYi+epUIcMLpKi5GcS/SeQMiBySzkmLBJnklXMua2QfvHY56L9j4ShsXzHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T10:46:32.177906Z"},"content_sha256":"7442c3dd60c86a559a36581efe8b5b5c11f40b3f954b8d95ee66f1e4a1992602","schema_version":"1.0","event_id":"sha256:7442c3dd60c86a559a36581efe8b5b5c11f40b3f954b8d95ee66f1e4a1992602"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VTH2F4UGCTSYUZC7462XALUDMY/bundle.json","state_url":"https://pith.science/pith/VTH2F4UGCTSYUZC7462XALUDMY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VTH2F4UGCTSYUZC7462XALUDMY/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":"2026-07-20T10:46:32Z","links":{"resolver":"https://pith.science/pith/VTH2F4UGCTSYUZC7462XALUDMY","bundle":"https://pith.science/pith/VTH2F4UGCTSYUZC7462XALUDMY/bundle.json","state":"https://pith.science/pith/VTH2F4UGCTSYUZC7462XALUDMY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VTH2F4UGCTSYUZC7462XALUDMY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VTH2F4UGCTSYUZC7462XALUDMY","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":"0270f289e276278bb87f6370a6bb282d6098be45ede71ef34ccf317ea98a53f3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-10T16:09:02Z","title_canon_sha256":"e3ce44a4ed39d570580868057b0489dad2c0c1045486127dcf31190d9cb92915"},"schema_version":"1.0","source":{"id":"2403.07944","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.07944","created_at":"2026-07-05T07:55:32Z"},{"alias_kind":"arxiv_version","alias_value":"2403.07944v1","created_at":"2026-07-05T07:55:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07944","created_at":"2026-07-05T07:55:32Z"},{"alias_kind":"pith_short_12","alias_value":"VTH2F4UGCTSY","created_at":"2026-07-05T07:55:32Z"},{"alias_kind":"pith_short_16","alias_value":"VTH2F4UGCTSYUZC7","created_at":"2026-07-05T07:55:32Z"},{"alias_kind":"pith_short_8","alias_value":"VTH2F4UG","created_at":"2026-07-05T07:55:32Z"}],"graph_snapshots":[{"event_id":"sha256:7442c3dd60c86a559a36581efe8b5b5c11f40b3f954b8d95ee66f1e4a1992602","target":"graph","created_at":"2026-07-05T07:55:32Z","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/2403.07944/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Several text-to-video diffusion models have demonstrated commendable capabilities in synthesizing high-quality video content. However, it remains a formidable challenge pertaining to maintaining temporal consistency and ensuring action smoothness throughout the generated sequences. In this paper, we present an innovative video generation AI agent that harnesses the power of Sora-inspired multimodal learning to build skilled world models framework based on textual prompts and accompanying images. The framework includes two parts: prompt enhancer and full video translation. The first part employ","authors_text":"Bang Yang, Chris Kelly, Cindy Yang, Deshun Yang, Luhui Hu, Yuexian Zou, Yu Tian, Zihao Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-10T16:09:02Z","title":"WorldGPT: A Sora-Inspired Video AI Agent as Rich World Models from Text and Image Inputs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07944","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":"sha256:0e8d8c17f3c64db70cb2ecc6dd41873a1cdcf4f67d774491a2b614bc0d228012","target":"record","created_at":"2026-07-05T07:55:32Z","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":"0270f289e276278bb87f6370a6bb282d6098be45ede71ef34ccf317ea98a53f3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-10T16:09:02Z","title_canon_sha256":"e3ce44a4ed39d570580868057b0489dad2c0c1045486127dcf31190d9cb92915"},"schema_version":"1.0","source":{"id":"2403.07944","kind":"arxiv","version":1}},"canonical_sha256":"accfa2f28614e58a645fe7b5702e83660435d69ae63895dafe80290b5be1e00f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"accfa2f28614e58a645fe7b5702e83660435d69ae63895dafe80290b5be1e00f","first_computed_at":"2026-07-05T07:55:32.497760Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:32.497760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EMH9WaCCjgsfY1+6uUG7rwRyW64CnQoP9vo/kuLa0pdpZmHjTQrwhljRRYcDglakWUe4K29HJddSKOHlZ1t6BA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:32.498131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.07944","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e8d8c17f3c64db70cb2ecc6dd41873a1cdcf4f67d774491a2b614bc0d228012","sha256:7442c3dd60c86a559a36581efe8b5b5c11f40b3f954b8d95ee66f1e4a1992602"],"state_sha256":"91e7fd54fd941bb2316191f1c1d125cf7da786d5a9cc0ac09aa23954dab1899d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pAcf+uFWVXlDmkLvSkydjg+NSRPKa4Ra1VRFOq0V17iXoy85stmfEmrG1T5N6KulaCMwyIgGqH+1KtXgnm1hCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-20T10:46:32.180422Z","bundle_sha256":"b7e2845f3188d7848b40e3a7c0471243effa339aec54804478266e409f7c3a58"}}