{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4BRY6WPS2QZYMLXFTZTNYEQBYZ","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":"b60e405797ef8c31ac4cb3956aed44fbf3671213f1fedcce694c135fe402311e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-10T04:20:08Z","title_canon_sha256":"2b93ee4f81adfcb9f7e63bd159ec7fa95cbaf9d3c788b4bc7573473fe4e63831"},"schema_version":"1.0","source":{"id":"2112.05328","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.05328","created_at":"2026-07-05T03:42:06Z"},{"alias_kind":"arxiv_version","alias_value":"2112.05328v3","created_at":"2026-07-05T03:42:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.05328","created_at":"2026-07-05T03:42:06Z"},{"alias_kind":"pith_short_12","alias_value":"4BRY6WPS2QZY","created_at":"2026-07-05T03:42:06Z"},{"alias_kind":"pith_short_16","alias_value":"4BRY6WPS2QZYMLXF","created_at":"2026-07-05T03:42:06Z"},{"alias_kind":"pith_short_8","alias_value":"4BRY6WPS","created_at":"2026-07-05T03:42:06Z"}],"graph_snapshots":[{"event_id":"sha256:d46e3fc47ba38804e9ba54478c8ac330f76012f180c23039241d1697ad0aec74","target":"graph","created_at":"2026-07-05T03:42:06Z","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/2112.05328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents our work on the Situated Interactive MultiModal Conversations 2.0 challenge held at Dialog State Tracking Challenge 10. SIMMC 2.0 includes 4 subtasks, and we introduce our multimodal approaches for the subtask \\#1, \\#2 and the generation of subtask \\#4. SIMMC 2.0 dataset is a multimodal dataset containing image and text information, which is more challenging than the problem of only text-based conversations because it must be solved by understanding the relationship between image and text. Therefore, since there is a limit to solving only text models such as BERT or GPT2, w","authors_text":"Joosung Lee, Kijong Han","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-10T04:20:08Z","title":"Multimodal Interactions Using Pretrained Unimodal Models for SIMMC 2.0"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.05328","kind":"arxiv","version":3},"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":"sha256:537033fd6b6b3e5117194d4a0c50348c0083690db675d517132534b39ed9b731","target":"record","created_at":"2026-07-05T03:42:06Z","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":"b60e405797ef8c31ac4cb3956aed44fbf3671213f1fedcce694c135fe402311e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-10T04:20:08Z","title_canon_sha256":"2b93ee4f81adfcb9f7e63bd159ec7fa95cbaf9d3c788b4bc7573473fe4e63831"},"schema_version":"1.0","source":{"id":"2112.05328","kind":"arxiv","version":3}},"canonical_sha256":"e0638f59f2d433862ee59e66dc1201c65368d43219bef27a1c5fbe15bfd6c977","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0638f59f2d433862ee59e66dc1201c65368d43219bef27a1c5fbe15bfd6c977","first_computed_at":"2026-07-05T03:42:06.371417Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:42:06.371417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nrC8+B0jwE2XPnZSUUxrVlB/QWQ452NO24N31KiyTaZvo43DJckYDKXH15sKUKzuJ0gc/5Ii4yy7Ue9izGiXBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:42:06.371954Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.05328","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:537033fd6b6b3e5117194d4a0c50348c0083690db675d517132534b39ed9b731","sha256:d46e3fc47ba38804e9ba54478c8ac330f76012f180c23039241d1697ad0aec74"],"state_sha256":"24a44d6e405aba0ac7a3badfd38f8579c4cc4e15d7150b5bc43d9e276f3d4786"}