{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:V7JXP63WJZX7WVBRBP2XHLPET6","short_pith_number":"pith:V7JXP63W","canonical_record":{"source":{"id":"2208.11303","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-24T05:18:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"bf235b128baea85242eb5958c1f773425287326855dd18dd31a88d5cf431330c","abstract_canon_sha256":"c74db7b952acca8b6968043b5f9f9c507e98edf7a9937928edc29a1619de4418"},"schema_version":"1.0"},"canonical_sha256":"afd377fb764e6ffb54310bf573ade49fb207e54dfd3efde8f36723cbed9d8d7d","source":{"kind":"arxiv","id":"2208.11303","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:V7JXP63WJZX7WVBRBP2XHLPET6","target":"record","payload":{"canonical_record":{"source":{"id":"2208.11303","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-24T05:18:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"bf235b128baea85242eb5958c1f773425287326855dd18dd31a88d5cf431330c","abstract_canon_sha256":"c74db7b952acca8b6968043b5f9f9c507e98edf7a9937928edc29a1619de4418"},"schema_version":"1.0"},"canonical_sha256":"afd377fb764e6ffb54310bf573ade49fb207e54dfd3efde8f36723cbed9d8d7d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:51.892824Z","signature_b64":"tjtxJ3FEM/0G4ZN6AoUubpt/J5CMb+YoxRF6xMk8Vv9Q8V7bAh56i8mG/h0oj0vBS80ucibhXI3W+A1Hv4tqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afd377fb764e6ffb54310bf573ade49fb207e54dfd3efde8f36723cbed9d8d7d","last_reissued_at":"2026-07-05T06:08:51.892410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:51.892410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.11303","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:08:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mN9Q+sfXvACDtkkUuOdHplF2ymW9HMeNs5neA79ShhLYV41OClrw0e1sqj+8OgWf8vGEDzEFpbNX7Qo5NkF5Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:39:14.873037Z"},"content_sha256":"08307d2c5c54e5d0574dca00c6ee9cea0e0b5736f58d00e2d1c0b6c25d93d670","schema_version":"1.0","event_id":"sha256:08307d2c5c54e5d0574dca00c6ee9cea0e0b5736f58d00e2d1c0b6c25d93d670"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:V7JXP63WJZX7WVBRBP2XHLPET6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modeling Paragraph-Level Vision-Language Semantic Alignment for Multi-Modal Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Chenhao Cui, Shuangzhi Wu, Xinnian Liang, Zhoujun Li","submitted_at":"2022-08-24T05:18:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.11303","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/2208.11303/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:08:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uvRFoNcU+3nuhRPeAn29y1/WeY6oRWLseyz0/b3/i5oE64uF9Wpx0HZUByKok+kg7WRnI4d8w7hdRhk0cNNJBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:39:14.873939Z"},"content_sha256":"029e02252b63181aa2c37d8d6b47dc6f03404a5ebb72d63931884927be8e3b9c","schema_version":"1.0","event_id":"sha256:029e02252b63181aa2c37d8d6b47dc6f03404a5ebb72d63931884927be8e3b9c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V7JXP63WJZX7WVBRBP2XHLPET6/bundle.json","state_url":"https://pith.science/pith/V7JXP63WJZX7WVBRBP2XHLPET6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V7JXP63WJZX7WVBRBP2XHLPET6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T17:39:14Z","links":{"resolver":"https://pith.science/pith/V7JXP63WJZX7WVBRBP2XHLPET6","bundle":"https://pith.science/pith/V7JXP63WJZX7WVBRBP2XHLPET6/bundle.json","state":"https://pith.science/pith/V7JXP63WJZX7WVBRBP2XHLPET6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V7JXP63WJZX7WVBRBP2XHLPET6/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BRYd9Hw5E8oz8nWgtXuixO+XKoojM3B7UzfN+ZT60i5uawItx3QB4/Q8yE1YCIH5J0rm7oW2qTKL2vvKa3+HDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:39:14.879273Z","bundle_sha256":"7b748dfbd00cf41c1b39ad2de9d8c9747221afe6e96ff5324dc3ac67afcfbe8f"}}