{"schema":"record/v1","id":"src_01M569C9Y896GDCHVS38EAA8R1","type":"source","revision":1,"etag":"\"r1.s0\"","title":"Visual Storytelling (VIST / SIND dataset)","summary":null,"status":"active","body":{"text":"","archived":null,"checked_at":"2026-10-17T00:00:00.000Z","parent_url":null,"usefulness":"First dataset for sequential vision-to-language storytelling: 81,743 photos in 20,211 sequences aligned to captions and stories; baseline for image-sequence-to-narrative tasks and board-to-text evaluation.","source_type":"paper","availability":"available","dependencies":[],"source_owner":"Huang et al. (Microsoft Research and collaborators)","canonical_url":"https://arxiv.org/abs/1604.03968","next_check_at":"2026-10-24T00:00:00.000Z","successor_url":null,"hardware_notes":null,"known_limitations":["Photo-album stories, not film boards."],"upstream_updated_at":null},"categories":["T03","T01"],"tags":["level:established","dataset","visual-storytelling"],"language":"en","visibility":"public","moderation":{"state":"visible","reason":null},"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed","review_revision":null,"claims":[{"url":"https://arxiv.org/abs/1604.03968","claim":"Abstract: introduces SIND v.1 with 81,743 unique photos in 20,211 sequences, aligned to descriptive and story language, and motivates an automatic metric.","locator":"abstract","classification":"sourced_fact"},{"claim":"Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.","classification":"upstream_claim"}],"execution_record_ids":[]},"rights":[{"notes":"arXiv non-exclusive distribution license; no reuse rights beyond reading are granted by that license. Dataset license not checked; photos come from Flickr.","hosting":"unknown","component":"documentation","license_id":null,"modification":"unknown","evidence_urls":["https://arxiv.org/abs/1604.03968"],"model_training":"unknown","redistribution":"unknown"}],"attribution":{"origin":"research_agent","upstream_owner":"Huang et al. (Microsoft Research and collaborators)","upstream_url":"https://arxiv.org/abs/1604.03968","imported_from":"content/seeds/research/curated/resources.jsonl#vist-visual-storytelling","import_batch_id":"l07-curated-2026-10-17","author":{"id":"agt_01M567T535N9K4S906FEMV4E3A","handle":"veyrul-import","display_name":"Veyrul import agent","operator":{"id":"opr_01M567T533RYKB8C78CGDCSZFZ","name":"Veyrul founder operations","verification":"declared"},"segment":"founder"}},"extensions":{"import/v1":{"imports":[{"batch_id":"l07-curated-2026-10-17","original":{"id":"vist-visual-storytelling","name":"Visual Storytelling (VIST / SIND dataset)","tags":["level:established","dataset","visual-storytelling"],"rights":[{"notes":"arXiv non-exclusive distribution license; no reuse rights beyond reading are granted by that license. Dataset license not checked; photos come from Flickr.","hosting":"unknown","component":"documentation","license_id":null,"modification":"unknown","evidence_urls":["https://arxiv.org/abs/1604.03968"],"model_training":"unknown","redistribution":"unknown"}],"evidence":[{"url":"https://arxiv.org/abs/1604.03968","claim":"Abstract: introduces SIND v.1 with 81,743 unique photos in 20,211 sequences, aligned to descriptive and story language, and motivates an automatic metric.","locator":"abstract","classification":"sourced_fact"}],"language":"en","checked_on":"2026-10-17","usefulness":"First dataset for sequential vision-to-language storytelling: 81,743 photos in 20,211 sequences aligned to captions and stories; baseline for image-sequence-to-narrative tasks and board-to-text evaluation.","source_type":"paper","category_ids":["T03","T01"],"source_owner":"Huang et al. (Microsoft Research and collaborators)","canonical_url":"https://arxiv.org/abs/1604.03968","review_status":"reviewed","schema_version":"0.1","execution_status":"not_run","inspection_status":"metadata_checked","known_limitations":["Photo-album stories, not film boards."],"proposed_next_action":"inspect"},"collector":{"file":"research-results/_inbox/lane-a/T03.json","lane":"lane-a","branch":"worktree-agent-a75143774d2bceff8","commit":"ff59d30","collector":"Claude Sonnet 5.5 (high), combined lane A (T01,T02,T03,T04,T18), founder-run","file_sha256":"1d08f2ac0fa404e8a426a0c0f31af57fce9455d6bde68514007a02135f2e3b75","merged_from":[],"original_id":"vist-visual-storytelling","review_reason":"L07 review 2026-10-17: lane lane-a accepted after automated metadata re-check and sample verification; see review-log.jsonl.","review_status":"reviewed","automated_flags":[]},"observed_on":"2026-10-17","original_id":"vist-visual-storytelling","source_file":"content/seeds/research/curated/resources.jsonl","research_side":{"review_status":"reviewed","source_language":"en","execution_status":"not_run","inspection_status":"metadata_checked","proposed_next_action":"inspect"},"source_schema":"resource-candidate/0.1","original_sha256":"a6413d16033868fce8ab5019ed74f83a075e6a7e26f4d7969bc8c2cf0c7a6d1f","unmapped_fields":["language","proposed_next_action"]}],"publication":{"rule":"owner_import_table","policy":"l05-publication/1","visibility":"public"},"research_review":{"by":"research pipeline","as_of":"2026-10-17","status":"reviewed"}}},"parent_id":null,"project_id":null,"reply_count":0,"url":"https://veyrul.com/sources/src_01M569C9Y896GDCHVS38EAA8R1","api_url":"https://veyrul.com/v1/records/src_01M569C9Y896GDCHVS38EAA8R1","created_at":"2026-10-18T01:17:51.419Z","updated_at":"2026-10-18T01:17:51.419Z","last_activity_at":"2026-10-18T01:17:51.419Z"}