{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HHX6PBLRXFQJGOBMT6ZNWANTBY","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":"72feda617734483f3aa3f785cfce10d8a863c980e2c021063986f2498b8e0555","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-16T18:12:04Z","title_canon_sha256":"ab761f1cac80d0d312147b888ef95ec9c6b131d791d0f80513431e2028229a72"},"schema_version":"1.0","source":{"id":"2212.08632","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08632","created_at":"2026-07-05T06:37:53Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08632v2","created_at":"2026-07-05T06:37:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08632","created_at":"2026-07-05T06:37:53Z"},{"alias_kind":"pith_short_12","alias_value":"HHX6PBLRXFQJ","created_at":"2026-07-05T06:37:53Z"},{"alias_kind":"pith_short_16","alias_value":"HHX6PBLRXFQJGOBM","created_at":"2026-07-05T06:37:53Z"},{"alias_kind":"pith_short_8","alias_value":"HHX6PBLR","created_at":"2026-07-05T06:37:53Z"}],"graph_snapshots":[{"event_id":"sha256:9f0faf49eec173672cabd8ec44678aa348ceb306c34ef1fb9ab847decda5406e","target":"graph","created_at":"2026-07-05T06:37:53Z","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/2212.08632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal multi-hop question answering involves answering a question by reasoning over multiple input sources from different modalities. Existing methods often retrieve evidences separately and then use a language model to generate an answer based on the retrieved evidences, and thus do not adequately connect candidates and are unable to model the interdependent relations during retrieval. Moreover, the pipelined approaches of retrieval and generation might result in poor generation performance when retrieval performance is low. To address these issues, we propose a Structured Knowledge and ","authors_text":"Baotian Hu, Min Zhang, Qian Chen, Qian Yang, Wen Wang","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-16T18:12:04Z","title":"Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08632","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":"sha256:567ea53a21c7b8c02778baf3d4552de7767203782bdbfa71ded5ad5caa37569e","target":"record","created_at":"2026-07-05T06:37:53Z","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":"72feda617734483f3aa3f785cfce10d8a863c980e2c021063986f2498b8e0555","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-16T18:12:04Z","title_canon_sha256":"ab761f1cac80d0d312147b888ef95ec9c6b131d791d0f80513431e2028229a72"},"schema_version":"1.0","source":{"id":"2212.08632","kind":"arxiv","version":2}},"canonical_sha256":"39efe78571b96093382c9fb2db01b30e2237a8c9378e174e396fe9235601b11d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39efe78571b96093382c9fb2db01b30e2237a8c9378e174e396fe9235601b11d","first_computed_at":"2026-07-05T06:37:53.656736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:37:53.656736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"00123UBeAlmgtOzD77g1NBHOsPt3wnhgog8t9z0HcfXUQ9lIEJisCd844NaRxcHvJ456dZxTnGoWFgUvb+DzCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:37:53.657241Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.08632","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:567ea53a21c7b8c02778baf3d4552de7767203782bdbfa71ded5ad5caa37569e","sha256:9f0faf49eec173672cabd8ec44678aa348ceb306c34ef1fb9ab847decda5406e"],"state_sha256":"a51d977a9d7a3834aff5a4329980b645fc6f1c7b83c17ac06906ae3f658367ba"}