{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7E2AA6YR6EB7YZCHSNSGZ3GTMA","short_pith_number":"pith:7E2AA6YR","schema_version":"1.0","canonical_sha256":"f934007b11f103fc644793646cecd3601c7d8bf14d1c11be25e0c285cfabb942","source":{"kind":"arxiv","id":"2412.05821","version":2},"attestation_state":"computed","paper":{"title":"An Entailment Tree Generation Approach for Multimodal Multi-Hop Question Answering with Mixture-of-Experts and Iterative Feedback Mechanism","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haocheng Lv, Hao Wang, Jianyong Duan, Jie Liu, Li He, Mingying Xv, Qing Zhang, Zhiyun Chen","submitted_at":"2024-12-08T05:47:55Z","abstract_excerpt":"With the rise of large-scale language models (LLMs), it is currently popular and effective to convert multimodal information into text descriptions for multimodal multi-hop question answering. However, we argue that the current methods of multi-modal multi-hop question answering still mainly face two challenges: 1) The retrieved evidence containing a large amount of redundant information, inevitably leads to a significant drop in performance due to irrelevant information misleading the prediction. 2) The reasoning process without interpretable reasoning steps makes the model difficult to disco"},"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":"2412.05821","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-08T05:47:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"02421ac91f928747db0dfa4bd5f37bcfe6173d818d07022effc055717d56e822","abstract_canon_sha256":"34abace454abbd0b9e1f0c3cd8aa5561f863298e7374e34ba1300a5f8f8fa24e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:56.356160Z","signature_b64":"li2M/2EEkhG9GfCZRpLPcUMu/kbUWLBA1pg1BW/qghHLBrqHCrkBEZdehirs18H64N59N+bCYtzD2xezQZ5vDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f934007b11f103fc644793646cecd3601c7d8bf14d1c11be25e0c285cfabb942","last_reissued_at":"2026-07-05T09:46:56.355630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:56.355630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Entailment Tree Generation Approach for Multimodal Multi-Hop Question Answering with Mixture-of-Experts and Iterative Feedback Mechanism","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haocheng Lv, Hao Wang, Jianyong Duan, Jie Liu, Li He, Mingying Xv, Qing Zhang, Zhiyun Chen","submitted_at":"2024-12-08T05:47:55Z","abstract_excerpt":"With the rise of large-scale language models (LLMs), it is currently popular and effective to convert multimodal information into text descriptions for multimodal multi-hop question answering. However, we argue that the current methods of multi-modal multi-hop question answering still mainly face two challenges: 1) The retrieved evidence containing a large amount of redundant information, inevitably leads to a significant drop in performance due to irrelevant information misleading the prediction. 2) The reasoning process without interpretable reasoning steps makes the model difficult to disco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05821","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/2412.05821/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":"2412.05821","created_at":"2026-07-05T09:46:56.355688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05821v2","created_at":"2026-07-05T09:46:56.355688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05821","created_at":"2026-07-05T09:46:56.355688+00:00"},{"alias_kind":"pith_short_12","alias_value":"7E2AA6YR6EB7","created_at":"2026-07-05T09:46:56.355688+00:00"},{"alias_kind":"pith_short_16","alias_value":"7E2AA6YR6EB7YZCH","created_at":"2026-07-05T09:46:56.355688+00:00"},{"alias_kind":"pith_short_8","alias_value":"7E2AA6YR","created_at":"2026-07-05T09:46:56.355688+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/7E2AA6YR6EB7YZCHSNSGZ3GTMA","json":"https://pith.science/pith/7E2AA6YR6EB7YZCHSNSGZ3GTMA.json","graph_json":"https://pith.science/api/pith-number/7E2AA6YR6EB7YZCHSNSGZ3GTMA/graph.json","events_json":"https://pith.science/api/pith-number/7E2AA6YR6EB7YZCHSNSGZ3GTMA/events.json","paper":"https://pith.science/paper/7E2AA6YR"},"agent_actions":{"view_html":"https://pith.science/pith/7E2AA6YR6EB7YZCHSNSGZ3GTMA","download_json":"https://pith.science/pith/7E2AA6YR6EB7YZCHSNSGZ3GTMA.json","view_paper":"https://pith.science/paper/7E2AA6YR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05821&json=true","fetch_graph":"https://pith.science/api/pith-number/7E2AA6YR6EB7YZCHSNSGZ3GTMA/graph.json","fetch_events":"https://pith.science/api/pith-number/7E2AA6YR6EB7YZCHSNSGZ3GTMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7E2AA6YR6EB7YZCHSNSGZ3GTMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7E2AA6YR6EB7YZCHSNSGZ3GTMA/action/storage_attestation","attest_author":"https://pith.science/pith/7E2AA6YR6EB7YZCHSNSGZ3GTMA/action/author_attestation","sign_citation":"https://pith.science/pith/7E2AA6YR6EB7YZCHSNSGZ3GTMA/action/citation_signature","submit_replication":"https://pith.science/pith/7E2AA6YR6EB7YZCHSNSGZ3GTMA/action/replication_record"}},"created_at":"2026-07-05T09:46:56.355688+00:00","updated_at":"2026-07-05T09:46:56.355688+00:00"}