{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UM356QTWTXJES3OW5FUW6O2WLN","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":"055c79991c4d3364542446e0ed26d25e865cee926fd9d1c5d70c7fb6c34ce06a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T10:44:49Z","title_canon_sha256":"343f2a0cb07c00c3652a3228a66694d487f0faa8962508d2432e07f4b62a189b"},"schema_version":"1.0","source":{"id":"2101.00419","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.00419","created_at":"2026-07-05T02:58:23Z"},{"alias_kind":"arxiv_version","alias_value":"2101.00419v2","created_at":"2026-07-05T02:58:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00419","created_at":"2026-07-05T02:58:23Z"},{"alias_kind":"pith_short_12","alias_value":"UM356QTWTXJE","created_at":"2026-07-05T02:58:23Z"},{"alias_kind":"pith_short_16","alias_value":"UM356QTWTXJES3OW","created_at":"2026-07-05T02:58:23Z"},{"alias_kind":"pith_short_8","alias_value":"UM356QTW","created_at":"2026-07-05T02:58:23Z"}],"graph_snapshots":[{"event_id":"sha256:42632191da8d4743d9a014d77ac10798e264cd1849584e3ec6dc03e0ae38cee5","target":"graph","created_at":"2026-07-05T02:58:23Z","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/2101.00419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Knowledge Enhanced Multimodal BART (KM-BART), which is a Transformer-based sequence-to-sequence model capable of reasoning about commonsense knowledge from multimodal inputs of images and texts. We adapt the generative BART architecture to a multimodal model with visual and textual inputs. We further develop novel pretraining tasks to improve the model performance on the Visual Commonsense Generation (VCG) task. In particular, our pretraining task of Knowledge-based Commonsense Generation (KCG) boosts model performance on the VCG task by leveraging commonsense knowledge from a large","authors_text":"Gerhard Lakemeyer, Roger Wattenhofer, Yiran Xing, Yunpu Ma, Zai Shi, Zhao Meng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T10:44:49Z","title":"KM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00419","kind":"arxiv","version":2},"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":"sha256:88ca30b6bf5e68ac2bbc6bda461eedc99a4188c5338ebcefe4cd8a2e3be82c4d","target":"record","created_at":"2026-07-05T02:58:23Z","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":"055c79991c4d3364542446e0ed26d25e865cee926fd9d1c5d70c7fb6c34ce06a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T10:44:49Z","title_canon_sha256":"343f2a0cb07c00c3652a3228a66694d487f0faa8962508d2432e07f4b62a189b"},"schema_version":"1.0","source":{"id":"2101.00419","kind":"arxiv","version":2}},"canonical_sha256":"a337df42769dd2496dd6e9696f3b565b6eb72ec2bc314144ffa596f8b80d3c54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a337df42769dd2496dd6e9696f3b565b6eb72ec2bc314144ffa596f8b80d3c54","first_computed_at":"2026-07-05T02:58:23.944910Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:58:23.944910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4I79Qc+Dg/j5KEYEaoJwlRNZVW9cfUVq3x11iqY/tT8oP0ts1DI12zvODLqiu0lBaTgb6fagw9v6Rh953hTEAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:58:23.945247Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.00419","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88ca30b6bf5e68ac2bbc6bda461eedc99a4188c5338ebcefe4cd8a2e3be82c4d","sha256:42632191da8d4743d9a014d77ac10798e264cd1849584e3ec6dc03e0ae38cee5"],"state_sha256":"21a494c0e469970b4a56d8dada642806af5e43a7ec0a8160485642374b46cf76"}