{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W6QRKWFLLRZVGD4OHGHKHKIK4L","short_pith_number":"pith:W6QRKWFL","schema_version":"1.0","canonical_sha256":"b7a11558ab5c73530f8e398ea3a90ae2db6e35d99ef95d461a9eca163876e516","source":{"kind":"arxiv","id":"2305.14839","version":2},"attestation_state":"computed","paper":{"title":"PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Binyuan Hui, Fei Huang, Min Yang, Yongbin Li, Yunshui Li, Zhichao Yin","submitted_at":"2023-05-24T07:43:29Z","abstract_excerpt":"Perceiving multi-modal information and fulfilling dialogues with humans is a long-term goal of artificial intelligence. Pre-training is commonly regarded as an effective approach for multi-modal dialogue. However, due to the limited availability of multi-modal dialogue data, there is still scarce research on multi-modal dialogue pre-training. Yet another intriguing challenge emerges from the encompassing nature of multi-modal dialogue, which involves various modalities and tasks. Moreover, new forms of tasks may arise at unpredictable points in the future. Hence, it is essential for designed m"},"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":"2305.14839","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T07:43:29Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"37791d5bbe59a261a356d8ab2dc394a051d8ee8fc69784ee02ce6e54b423a03e","abstract_canon_sha256":"8c3a5b5846c87a0083963569238edab1e9b9da983e9b06ebdf704781fb460ef6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:59.169370Z","signature_b64":"NPBm5FiENWLiRiSpMvF7npzZd+/B1eT30AoE6gu2Fo61SMvHhzCidyJoDmiY8X/mh60dSz3VifrlBmeMnUDfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7a11558ab5c73530f8e398ea3a90ae2db6e35d99ef95d461a9eca163876e516","last_reissued_at":"2026-07-05T06:19:59.168949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:59.168949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Binyuan Hui, Fei Huang, Min Yang, Yongbin Li, Yunshui Li, Zhichao Yin","submitted_at":"2023-05-24T07:43:29Z","abstract_excerpt":"Perceiving multi-modal information and fulfilling dialogues with humans is a long-term goal of artificial intelligence. Pre-training is commonly regarded as an effective approach for multi-modal dialogue. However, due to the limited availability of multi-modal dialogue data, there is still scarce research on multi-modal dialogue pre-training. Yet another intriguing challenge emerges from the encompassing nature of multi-modal dialogue, which involves various modalities and tasks. Moreover, new forms of tasks may arise at unpredictable points in the future. Hence, it is essential for designed m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14839","kind":"arxiv","version":2},"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/2305.14839/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":"2305.14839","created_at":"2026-07-05T06:19:59.169011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14839v2","created_at":"2026-07-05T06:19:59.169011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14839","created_at":"2026-07-05T06:19:59.169011+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6QRKWFLLRZV","created_at":"2026-07-05T06:19:59.169011+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6QRKWFLLRZVGD4O","created_at":"2026-07-05T06:19:59.169011+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6QRKWFL","created_at":"2026-07-05T06:19:59.169011+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10233","citing_title":"Adapting 2D Multi-Modal Large Language Model for 3D CT Image Analysis","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W6QRKWFLLRZVGD4OHGHKHKIK4L","json":"https://pith.science/pith/W6QRKWFLLRZVGD4OHGHKHKIK4L.json","graph_json":"https://pith.science/api/pith-number/W6QRKWFLLRZVGD4OHGHKHKIK4L/graph.json","events_json":"https://pith.science/api/pith-number/W6QRKWFLLRZVGD4OHGHKHKIK4L/events.json","paper":"https://pith.science/paper/W6QRKWFL"},"agent_actions":{"view_html":"https://pith.science/pith/W6QRKWFLLRZVGD4OHGHKHKIK4L","download_json":"https://pith.science/pith/W6QRKWFLLRZVGD4OHGHKHKIK4L.json","view_paper":"https://pith.science/paper/W6QRKWFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14839&json=true","fetch_graph":"https://pith.science/api/pith-number/W6QRKWFLLRZVGD4OHGHKHKIK4L/graph.json","fetch_events":"https://pith.science/api/pith-number/W6QRKWFLLRZVGD4OHGHKHKIK4L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6QRKWFLLRZVGD4OHGHKHKIK4L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6QRKWFLLRZVGD4OHGHKHKIK4L/action/storage_attestation","attest_author":"https://pith.science/pith/W6QRKWFLLRZVGD4OHGHKHKIK4L/action/author_attestation","sign_citation":"https://pith.science/pith/W6QRKWFLLRZVGD4OHGHKHKIK4L/action/citation_signature","submit_replication":"https://pith.science/pith/W6QRKWFLLRZVGD4OHGHKHKIK4L/action/replication_record"}},"created_at":"2026-07-05T06:19:59.169011+00:00","updated_at":"2026-07-05T06:19:59.169011+00:00"}