{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:V7JXP63WJZX7WVBRBP2XHLPET6","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":"c74db7b952acca8b6968043b5f9f9c507e98edf7a9937928edc29a1619de4418","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-24T05:18:23Z","title_canon_sha256":"bf235b128baea85242eb5958c1f773425287326855dd18dd31a88d5cf431330c"},"schema_version":"1.0","source":{"id":"2208.11303","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.11303","created_at":"2026-07-05T06:08:51Z"},{"alias_kind":"arxiv_version","alias_value":"2208.11303v3","created_at":"2026-07-05T06:08:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.11303","created_at":"2026-07-05T06:08:51Z"},{"alias_kind":"pith_short_12","alias_value":"V7JXP63WJZX7","created_at":"2026-07-05T06:08:51Z"},{"alias_kind":"pith_short_16","alias_value":"V7JXP63WJZX7WVBR","created_at":"2026-07-05T06:08:51Z"},{"alias_kind":"pith_short_8","alias_value":"V7JXP63W","created_at":"2026-07-05T06:08:51Z"}],"graph_snapshots":[{"event_id":"sha256:029e02252b63181aa2c37d8d6b47dc6f03404a5ebb72d63931884927be8e3b9c","target":"graph","created_at":"2026-07-05T06:08:51Z","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/2208.11303/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most current multi-modal summarization methods follow a cascaded manner, where an off-the-shelf object detector is first used to extract visual features, then these features are fused with language representations to generate the summary with an encoder-decoder model. The cascaded way cannot capture the semantic alignments between images and paragraphs, which are crucial to a precise summary. In this paper, we propose ViL-Sum to jointly model paragraph-level \\textbf{Vi}sion-\\textbf{L}anguage Semantic Alignment and Multi-Modal \\textbf{Sum}marization. The core of ViL-Sum is a joint multi-modal e","authors_text":"Chenhao Cui, Shuangzhi Wu, Xinnian Liang, Zhoujun Li","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-24T05:18:23Z","title":"Modeling Paragraph-Level Vision-Language Semantic Alignment for Multi-Modal Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.11303","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":"sha256:08307d2c5c54e5d0574dca00c6ee9cea0e0b5736f58d00e2d1c0b6c25d93d670","target":"record","created_at":"2026-07-05T06:08:51Z","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":"c74db7b952acca8b6968043b5f9f9c507e98edf7a9937928edc29a1619de4418","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-24T05:18:23Z","title_canon_sha256":"bf235b128baea85242eb5958c1f773425287326855dd18dd31a88d5cf431330c"},"schema_version":"1.0","source":{"id":"2208.11303","kind":"arxiv","version":3}},"canonical_sha256":"afd377fb764e6ffb54310bf573ade49fb207e54dfd3efde8f36723cbed9d8d7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afd377fb764e6ffb54310bf573ade49fb207e54dfd3efde8f36723cbed9d8d7d","first_computed_at":"2026-07-05T06:08:51.892410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:08:51.892410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tjtxJ3FEM/0G4ZN6AoUubpt/J5CMb+YoxRF6xMk8Vv9Q8V7bAh56i8mG/h0oj0vBS80ucibhXI3W+A1Hv4tqCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:08:51.892824Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.11303","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08307d2c5c54e5d0574dca00c6ee9cea0e0b5736f58d00e2d1c0b6c25d93d670","sha256:029e02252b63181aa2c37d8d6b47dc6f03404a5ebb72d63931884927be8e3b9c"],"state_sha256":"45e31252eb8c10cc61a06cdd8da08ed1454c982a15a2c8a9f6612af7a4499d71"}