{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MKMAXYYPLPNSIRKYXRTAG4QM2S","short_pith_number":"pith:MKMAXYYP","schema_version":"1.0","canonical_sha256":"62980be30f5bdb244558bc6603720cd485bf776bc388661c2aa9abd2bb5a1a1f","source":{"kind":"arxiv","id":"2205.03774","version":1},"attestation_state":"computed","paper":{"title":"RoViST:Learning Robust Metrics for Visual Storytelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Caren Han, Eileen Wang, Josiah Poon","submitted_at":"2022-05-08T03:51:22Z","abstract_excerpt":"Visual storytelling (VST) is the task of generating a story paragraph that describes a given image sequence. Most existing storytelling approaches have evaluated their models using traditional natural language generation metrics like BLEU or CIDEr. However, such metrics based on n-gram matching tend to have poor correlation with human evaluation scores and do not explicitly consider other criteria necessary for storytelling such as sentence structure or topic coherence. Moreover, a single score is not enough to assess a story as it does not inform us about what specific errors were made by the"},"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":"2205.03774","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-08T03:51:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"658c677ee604491f1336ff3ad759c6b799fc5d23b8b6495f6ebc26d8c3c6b7a7","abstract_canon_sha256":"bffd97f2aaba968aa39ba8c47e1abbbe3799ac93c0326fc3236995a7797d7a99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:18.398937Z","signature_b64":"XslHUuUqL8u8MLLpjcDv3eKnvRQ6m7A7cjbDzRnBcKKLeBj+WxqKywIcliT4ZnZJ0AzwQpMtikgIHHWgbIapDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62980be30f5bdb244558bc6603720cd485bf776bc388661c2aa9abd2bb5a1a1f","last_reissued_at":"2026-07-05T04:21:18.398466Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:18.398466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoViST:Learning Robust Metrics for Visual Storytelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Caren Han, Eileen Wang, Josiah Poon","submitted_at":"2022-05-08T03:51:22Z","abstract_excerpt":"Visual storytelling (VST) is the task of generating a story paragraph that describes a given image sequence. Most existing storytelling approaches have evaluated their models using traditional natural language generation metrics like BLEU or CIDEr. However, such metrics based on n-gram matching tend to have poor correlation with human evaluation scores and do not explicitly consider other criteria necessary for storytelling such as sentence structure or topic coherence. Moreover, a single score is not enough to assess a story as it does not inform us about what specific errors were made by the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03774","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/2205.03774/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":"2205.03774","created_at":"2026-07-05T04:21:18.398523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.03774v1","created_at":"2026-07-05T04:21:18.398523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03774","created_at":"2026-07-05T04:21:18.398523+00:00"},{"alias_kind":"pith_short_12","alias_value":"MKMAXYYPLPNS","created_at":"2026-07-05T04:21:18.398523+00:00"},{"alias_kind":"pith_short_16","alias_value":"MKMAXYYPLPNSIRKY","created_at":"2026-07-05T04:21:18.398523+00:00"},{"alias_kind":"pith_short_8","alias_value":"MKMAXYYP","created_at":"2026-07-05T04:21:18.398523+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":75,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MKMAXYYPLPNSIRKYXRTAG4QM2S","json":"https://pith.science/pith/MKMAXYYPLPNSIRKYXRTAG4QM2S.json","graph_json":"https://pith.science/api/pith-number/MKMAXYYPLPNSIRKYXRTAG4QM2S/graph.json","events_json":"https://pith.science/api/pith-number/MKMAXYYPLPNSIRKYXRTAG4QM2S/events.json","paper":"https://pith.science/paper/MKMAXYYP"},"agent_actions":{"view_html":"https://pith.science/pith/MKMAXYYPLPNSIRKYXRTAG4QM2S","download_json":"https://pith.science/pith/MKMAXYYPLPNSIRKYXRTAG4QM2S.json","view_paper":"https://pith.science/paper/MKMAXYYP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.03774&json=true","fetch_graph":"https://pith.science/api/pith-number/MKMAXYYPLPNSIRKYXRTAG4QM2S/graph.json","fetch_events":"https://pith.science/api/pith-number/MKMAXYYPLPNSIRKYXRTAG4QM2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MKMAXYYPLPNSIRKYXRTAG4QM2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MKMAXYYPLPNSIRKYXRTAG4QM2S/action/storage_attestation","attest_author":"https://pith.science/pith/MKMAXYYPLPNSIRKYXRTAG4QM2S/action/author_attestation","sign_citation":"https://pith.science/pith/MKMAXYYPLPNSIRKYXRTAG4QM2S/action/citation_signature","submit_replication":"https://pith.science/pith/MKMAXYYPLPNSIRKYXRTAG4QM2S/action/replication_record"}},"created_at":"2026-07-05T04:21:18.398523+00:00","updated_at":"2026-07-05T04:21:18.398523+00:00"}