{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FNCQMRNWBISSCDHM2XL4WQLZLA","short_pith_number":"pith:FNCQMRNW","schema_version":"1.0","canonical_sha256":"2b450645b60a25210cecd5d7cb4179580c7a05398b124882c57c00e8db4ff896","source":{"kind":"arxiv","id":"2408.03695","version":1},"attestation_state":"computed","paper":{"title":"Openstory++: A Large-scale Dataset and Benchmark for Instance-aware Open-domain Visual Storytelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guo-jun Qi, Jinjin Cao, Jinxiu Liu, Mingyuan Zhou, Mohamed Elhoseiny, Qi Liu, Ruotian Peng, Xiaoqian Shen, Yiyang Zhang, Zhiyang Chen, Zilyu Ye, Ziwei Xuan","submitted_at":"2024-08-07T11:20:37Z","abstract_excerpt":"Recent image generation models excel at creating high-quality images from brief captions. However, they fail to maintain consistency of multiple instances across images when encountering lengthy contexts. This inconsistency is largely due to in existing training datasets the absence of granular instance feature labeling in existing training datasets. To tackle these issues, we introduce Openstory++, a large-scale dataset combining additional instance-level annotations with both images and text. Furthermore, we develop a training methodology that emphasizes entity-centric image-text generation,"},"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":"2408.03695","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-07T11:20:37Z","cross_cats_sorted":[],"title_canon_sha256":"020ca84e438e97e6cc3fb5a6a02b02039c3210f3c4e450b0ea46071ae3190363","abstract_canon_sha256":"243989d5328c69e199eb1edf2415bf1153d224b82dba303f7a476b6b79862147"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:01.977811Z","signature_b64":"RmCjgbcMgi/b7t/hmtQptZPvx/gsaTmT3WXhSpRD9E3Zgf5fF+Uhyy26vTxCbBsfrZX+kYudR61dh+cP6fmhDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b450645b60a25210cecd5d7cb4179580c7a05398b124882c57c00e8db4ff896","last_reissued_at":"2026-07-05T08:53:01.977369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:01.977369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Openstory++: A Large-scale Dataset and Benchmark for Instance-aware Open-domain Visual Storytelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guo-jun Qi, Jinjin Cao, Jinxiu Liu, Mingyuan Zhou, Mohamed Elhoseiny, Qi Liu, Ruotian Peng, Xiaoqian Shen, Yiyang Zhang, Zhiyang Chen, Zilyu Ye, Ziwei Xuan","submitted_at":"2024-08-07T11:20:37Z","abstract_excerpt":"Recent image generation models excel at creating high-quality images from brief captions. However, they fail to maintain consistency of multiple instances across images when encountering lengthy contexts. This inconsistency is largely due to in existing training datasets the absence of granular instance feature labeling in existing training datasets. To tackle these issues, we introduce Openstory++, a large-scale dataset combining additional instance-level annotations with both images and text. Furthermore, we develop a training methodology that emphasizes entity-centric image-text generation,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03695","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/2408.03695/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":"2408.03695","created_at":"2026-07-05T08:53:01.977424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.03695v1","created_at":"2026-07-05T08:53:01.977424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03695","created_at":"2026-07-05T08:53:01.977424+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNCQMRNWBISS","created_at":"2026-07-05T08:53:01.977424+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNCQMRNWBISSCDHM","created_at":"2026-07-05T08:53:01.977424+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNCQMRNW","created_at":"2026-07-05T08:53:01.977424+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01312","citing_title":"KathaTrace: Diagnosing Semantic Trajectory Collapse in Generated Visual Narratives","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FNCQMRNWBISSCDHM2XL4WQLZLA","json":"https://pith.science/pith/FNCQMRNWBISSCDHM2XL4WQLZLA.json","graph_json":"https://pith.science/api/pith-number/FNCQMRNWBISSCDHM2XL4WQLZLA/graph.json","events_json":"https://pith.science/api/pith-number/FNCQMRNWBISSCDHM2XL4WQLZLA/events.json","paper":"https://pith.science/paper/FNCQMRNW"},"agent_actions":{"view_html":"https://pith.science/pith/FNCQMRNWBISSCDHM2XL4WQLZLA","download_json":"https://pith.science/pith/FNCQMRNWBISSCDHM2XL4WQLZLA.json","view_paper":"https://pith.science/paper/FNCQMRNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.03695&json=true","fetch_graph":"https://pith.science/api/pith-number/FNCQMRNWBISSCDHM2XL4WQLZLA/graph.json","fetch_events":"https://pith.science/api/pith-number/FNCQMRNWBISSCDHM2XL4WQLZLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNCQMRNWBISSCDHM2XL4WQLZLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNCQMRNWBISSCDHM2XL4WQLZLA/action/storage_attestation","attest_author":"https://pith.science/pith/FNCQMRNWBISSCDHM2XL4WQLZLA/action/author_attestation","sign_citation":"https://pith.science/pith/FNCQMRNWBISSCDHM2XL4WQLZLA/action/citation_signature","submit_replication":"https://pith.science/pith/FNCQMRNWBISSCDHM2XL4WQLZLA/action/replication_record"}},"created_at":"2026-07-05T08:53:01.977424+00:00","updated_at":"2026-07-05T08:53:01.977424+00:00"}