{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4BRY6WPS2QZYMLXFTZTNYEQBYZ","short_pith_number":"pith:4BRY6WPS","schema_version":"1.0","canonical_sha256":"e0638f59f2d433862ee59e66dc1201c65368d43219bef27a1c5fbe15bfd6c977","source":{"kind":"arxiv","id":"2112.05328","version":3},"attestation_state":"computed","paper":{"title":"Multimodal Interactions Using Pretrained Unimodal Models for SIMMC 2.0","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Joosung Lee, Kijong Han","submitted_at":"2021-12-10T04:20:08Z","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"},"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":"2112.05328","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-10T04:20:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2b93ee4f81adfcb9f7e63bd159ec7fa95cbaf9d3c788b4bc7573473fe4e63831","abstract_canon_sha256":"b60e405797ef8c31ac4cb3956aed44fbf3671213f1fedcce694c135fe402311e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:42:06.371954Z","signature_b64":"nrC8+B0jwE2XPnZSUUxrVlB/QWQ452NO24N31KiyTaZvo43DJckYDKXH15sKUKzuJ0gc/5Ii4yy7Ue9izGiXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0638f59f2d433862ee59e66dc1201c65368d43219bef27a1c5fbe15bfd6c977","last_reissued_at":"2026-07-05T03:42:06.371417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:42:06.371417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Interactions Using Pretrained Unimodal Models for SIMMC 2.0","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Joosung Lee, Kijong Han","submitted_at":"2021-12-10T04:20:08Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.05328","kind":"arxiv","version":3},"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/2112.05328/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":"2112.05328","created_at":"2026-07-05T03:42:06.371475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.05328v3","created_at":"2026-07-05T03:42:06.371475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.05328","created_at":"2026-07-05T03:42:06.371475+00:00"},{"alias_kind":"pith_short_12","alias_value":"4BRY6WPS2QZY","created_at":"2026-07-05T03:42:06.371475+00:00"},{"alias_kind":"pith_short_16","alias_value":"4BRY6WPS2QZYMLXF","created_at":"2026-07-05T03:42:06.371475+00:00"},{"alias_kind":"pith_short_8","alias_value":"4BRY6WPS","created_at":"2026-07-05T03:42:06.371475+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4BRY6WPS2QZYMLXFTZTNYEQBYZ","json":"https://pith.science/pith/4BRY6WPS2QZYMLXFTZTNYEQBYZ.json","graph_json":"https://pith.science/api/pith-number/4BRY6WPS2QZYMLXFTZTNYEQBYZ/graph.json","events_json":"https://pith.science/api/pith-number/4BRY6WPS2QZYMLXFTZTNYEQBYZ/events.json","paper":"https://pith.science/paper/4BRY6WPS"},"agent_actions":{"view_html":"https://pith.science/pith/4BRY6WPS2QZYMLXFTZTNYEQBYZ","download_json":"https://pith.science/pith/4BRY6WPS2QZYMLXFTZTNYEQBYZ.json","view_paper":"https://pith.science/paper/4BRY6WPS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.05328&json=true","fetch_graph":"https://pith.science/api/pith-number/4BRY6WPS2QZYMLXFTZTNYEQBYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/4BRY6WPS2QZYMLXFTZTNYEQBYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4BRY6WPS2QZYMLXFTZTNYEQBYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4BRY6WPS2QZYMLXFTZTNYEQBYZ/action/storage_attestation","attest_author":"https://pith.science/pith/4BRY6WPS2QZYMLXFTZTNYEQBYZ/action/author_attestation","sign_citation":"https://pith.science/pith/4BRY6WPS2QZYMLXFTZTNYEQBYZ/action/citation_signature","submit_replication":"https://pith.science/pith/4BRY6WPS2QZYMLXFTZTNYEQBYZ/action/replication_record"}},"created_at":"2026-07-05T03:42:06.371475+00:00","updated_at":"2026-07-05T03:42:06.371475+00:00"}