{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:73HJPMF6SJ6MTOPEGQXT2UDHVW","short_pith_number":"pith:73HJPMF6","schema_version":"1.0","canonical_sha256":"fece97b0be927cc9b9e4342f3d5067adbd44dd2a04c700e9848dd017b465fcec","source":{"kind":"arxiv","id":"2402.00319","version":1},"attestation_state":"computed","paper":{"title":"SCO-VIST: Social Interaction Commonsense Knowledge-based Visual Storytelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Eileen Wang, Josiah Poon, Soyeon Caren Han","submitted_at":"2024-02-01T04:09:17Z","abstract_excerpt":"Visual storytelling aims to automatically generate a coherent story based on a given image sequence. Unlike tasks like image captioning, visual stories should contain factual descriptions, worldviews, and human social commonsense to put disjointed elements together to form a coherent and engaging human-writeable story. However, most models mainly focus on applying factual information and using taxonomic/lexical external knowledge when attempting to create stories. This paper introduces SCO-VIST, a framework representing the image sequence as a graph with objects and relations that includes hum"},"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":"2402.00319","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-01T04:09:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2e7237d99cab2208d598c0eb50c018738ff1ef89dc35acfeca7746f626d09d3d","abstract_canon_sha256":"369c677bd0a00a15df562224c3185731e17a1c5a926d42c2fbcd7c08e80bddfd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:10.035730Z","signature_b64":"2HCF81bV7/7L78jG7NgbCRDv7s1DbXRXJpDxPkZei4z2yo2AJlOh9XnQrKPOHrHe1YWbpiSj8LvdyOMjqKo/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fece97b0be927cc9b9e4342f3d5067adbd44dd2a04c700e9848dd017b465fcec","last_reissued_at":"2026-07-05T07:40:10.035231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:10.035231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCO-VIST: Social Interaction Commonsense Knowledge-based Visual Storytelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Eileen Wang, Josiah Poon, Soyeon Caren Han","submitted_at":"2024-02-01T04:09:17Z","abstract_excerpt":"Visual storytelling aims to automatically generate a coherent story based on a given image sequence. Unlike tasks like image captioning, visual stories should contain factual descriptions, worldviews, and human social commonsense to put disjointed elements together to form a coherent and engaging human-writeable story. However, most models mainly focus on applying factual information and using taxonomic/lexical external knowledge when attempting to create stories. This paper introduces SCO-VIST, a framework representing the image sequence as a graph with objects and relations that includes hum"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00319","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/2402.00319/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":"2402.00319","created_at":"2026-07-05T07:40:10.035293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.00319v1","created_at":"2026-07-05T07:40:10.035293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00319","created_at":"2026-07-05T07:40:10.035293+00:00"},{"alias_kind":"pith_short_12","alias_value":"73HJPMF6SJ6M","created_at":"2026-07-05T07:40:10.035293+00:00"},{"alias_kind":"pith_short_16","alias_value":"73HJPMF6SJ6MTOPE","created_at":"2026-07-05T07:40:10.035293+00:00"},{"alias_kind":"pith_short_8","alias_value":"73HJPMF6","created_at":"2026-07-05T07:40:10.035293+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.14045","citing_title":"From Image Captioning to Visual Storytelling","ref_index":76,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/73HJPMF6SJ6MTOPEGQXT2UDHVW","json":"https://pith.science/pith/73HJPMF6SJ6MTOPEGQXT2UDHVW.json","graph_json":"https://pith.science/api/pith-number/73HJPMF6SJ6MTOPEGQXT2UDHVW/graph.json","events_json":"https://pith.science/api/pith-number/73HJPMF6SJ6MTOPEGQXT2UDHVW/events.json","paper":"https://pith.science/paper/73HJPMF6"},"agent_actions":{"view_html":"https://pith.science/pith/73HJPMF6SJ6MTOPEGQXT2UDHVW","download_json":"https://pith.science/pith/73HJPMF6SJ6MTOPEGQXT2UDHVW.json","view_paper":"https://pith.science/paper/73HJPMF6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.00319&json=true","fetch_graph":"https://pith.science/api/pith-number/73HJPMF6SJ6MTOPEGQXT2UDHVW/graph.json","fetch_events":"https://pith.science/api/pith-number/73HJPMF6SJ6MTOPEGQXT2UDHVW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73HJPMF6SJ6MTOPEGQXT2UDHVW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73HJPMF6SJ6MTOPEGQXT2UDHVW/action/storage_attestation","attest_author":"https://pith.science/pith/73HJPMF6SJ6MTOPEGQXT2UDHVW/action/author_attestation","sign_citation":"https://pith.science/pith/73HJPMF6SJ6MTOPEGQXT2UDHVW/action/citation_signature","submit_replication":"https://pith.science/pith/73HJPMF6SJ6MTOPEGQXT2UDHVW/action/replication_record"}},"created_at":"2026-07-05T07:40:10.035293+00:00","updated_at":"2026-07-05T07:40:10.035293+00:00"}