{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NFBQ4VPG5OGJNQWYJUOSITLF2I","short_pith_number":"pith:NFBQ4VPG","canonical_record":{"source":{"id":"2108.05123","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-08-11T09:59:34Z","cross_cats_sorted":[],"title_canon_sha256":"1d044cd3d1d6f8577ba7bd2bb714b4f1b78cb14db36e99f2133952ebc39d980a","abstract_canon_sha256":"1883209550dc1f1efd01149b241f6c4e13998a4ba8833001ea14c02baa9654e8"},"schema_version":"1.0"},"canonical_sha256":"69430e55e6eb8c96c2d84d1d244d65d21699d9ad1327d3fbbae26bd63632ba38","source":{"kind":"arxiv","id":"2108.05123","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.05123","created_at":"2026-07-05T04:46:32Z"},{"alias_kind":"arxiv_version","alias_value":"2108.05123v3","created_at":"2026-07-05T04:46:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05123","created_at":"2026-07-05T04:46:32Z"},{"alias_kind":"pith_short_12","alias_value":"NFBQ4VPG5OGJ","created_at":"2026-07-05T04:46:32Z"},{"alias_kind":"pith_short_16","alias_value":"NFBQ4VPG5OGJNQWY","created_at":"2026-07-05T04:46:32Z"},{"alias_kind":"pith_short_8","alias_value":"NFBQ4VPG","created_at":"2026-07-05T04:46:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NFBQ4VPG5OGJNQWYJUOSITLF2I","target":"record","payload":{"canonical_record":{"source":{"id":"2108.05123","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-08-11T09:59:34Z","cross_cats_sorted":[],"title_canon_sha256":"1d044cd3d1d6f8577ba7bd2bb714b4f1b78cb14db36e99f2133952ebc39d980a","abstract_canon_sha256":"1883209550dc1f1efd01149b241f6c4e13998a4ba8833001ea14c02baa9654e8"},"schema_version":"1.0"},"canonical_sha256":"69430e55e6eb8c96c2d84d1d244d65d21699d9ad1327d3fbbae26bd63632ba38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:32.427561Z","signature_b64":"T1HWgMe2Bv462cwOFVPKJgLeHAvIMj9LdQry0HtI+VE+cdmSO6lv1FJq3BuNTgEbSSKb+6NvsU+wBewrlZ17CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69430e55e6eb8c96c2d84d1d244d65d21699d9ad1327d3fbbae26bd63632ba38","last_reissued_at":"2026-07-05T04:46:32.427113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:32.427113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.05123","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":"2026-07-05T04:46:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cXrfoKhnvMTwU13JbQUyk0K3yEhNQ90z+C5FSo8giWtDx4Oe/wlkUU+DnGJcjagaTWb6nL88a7+j2iuQJ9VZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:32:05.657459Z"},"content_sha256":"d5912605b054b03702af5f377d549db080f1a843b3622719407bf495681284ad","schema_version":"1.0","event_id":"sha256:d5912605b054b03702af5f377d549db080f1a843b3622719407bf495681284ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NFBQ4VPG5OGJNQWYJUOSITLF2I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ICAF: Iterative Contrastive Alignment Framework for Multimodal Abstractive Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chang Shu, Jing Xiao, Lu Zheng, Qian Zhang, Youxin Chen, Zijian Zhang","submitted_at":"2021-08-11T09:59:34Z","abstract_excerpt":"Integrating multimodal knowledge for abstractive summarization task is a work-in-progress research area, with present techniques inheriting fusion-then-generation paradigm. Due to semantic gaps between computer vision and natural language processing, current methods often treat multiple data points as separate objects and rely on attention mechanisms to search for connection in order to fuse together. In addition, missing awareness of cross-modal matching from many frameworks leads to performance reduction. To solve these two drawbacks, we propose an Iterative Contrastive Alignment Framework ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05123","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/2108.05123/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":"2026-07-05T04:46:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1JrMzcR9PoUJeh9rQYwluP7kx42KgW3LoyX0vfHfFOlqX/mbneQqmD1HiVzK2xWNS0462ux8WBNCdfZf6oXZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:32:05.657835Z"},"content_sha256":"c6fb813143bffbbf88aa14d609685d99349caa39bfa242b5c3ad4307ac0c8e8b","schema_version":"1.0","event_id":"sha256:c6fb813143bffbbf88aa14d609685d99349caa39bfa242b5c3ad4307ac0c8e8b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NFBQ4VPG5OGJNQWYJUOSITLF2I/bundle.json","state_url":"https://pith.science/pith/NFBQ4VPG5OGJNQWYJUOSITLF2I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NFBQ4VPG5OGJNQWYJUOSITLF2I/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":"2026-07-06T19:32:05Z","links":{"resolver":"https://pith.science/pith/NFBQ4VPG5OGJNQWYJUOSITLF2I","bundle":"https://pith.science/pith/NFBQ4VPG5OGJNQWYJUOSITLF2I/bundle.json","state":"https://pith.science/pith/NFBQ4VPG5OGJNQWYJUOSITLF2I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NFBQ4VPG5OGJNQWYJUOSITLF2I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NFBQ4VPG5OGJNQWYJUOSITLF2I","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":"1883209550dc1f1efd01149b241f6c4e13998a4ba8833001ea14c02baa9654e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-08-11T09:59:34Z","title_canon_sha256":"1d044cd3d1d6f8577ba7bd2bb714b4f1b78cb14db36e99f2133952ebc39d980a"},"schema_version":"1.0","source":{"id":"2108.05123","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.05123","created_at":"2026-07-05T04:46:32Z"},{"alias_kind":"arxiv_version","alias_value":"2108.05123v3","created_at":"2026-07-05T04:46:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05123","created_at":"2026-07-05T04:46:32Z"},{"alias_kind":"pith_short_12","alias_value":"NFBQ4VPG5OGJ","created_at":"2026-07-05T04:46:32Z"},{"alias_kind":"pith_short_16","alias_value":"NFBQ4VPG5OGJNQWY","created_at":"2026-07-05T04:46:32Z"},{"alias_kind":"pith_short_8","alias_value":"NFBQ4VPG","created_at":"2026-07-05T04:46:32Z"}],"graph_snapshots":[{"event_id":"sha256:c6fb813143bffbbf88aa14d609685d99349caa39bfa242b5c3ad4307ac0c8e8b","target":"graph","created_at":"2026-07-05T04:46:32Z","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/2108.05123/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Integrating multimodal knowledge for abstractive summarization task is a work-in-progress research area, with present techniques inheriting fusion-then-generation paradigm. Due to semantic gaps between computer vision and natural language processing, current methods often treat multiple data points as separate objects and rely on attention mechanisms to search for connection in order to fuse together. In addition, missing awareness of cross-modal matching from many frameworks leads to performance reduction. To solve these two drawbacks, we propose an Iterative Contrastive Alignment Framework (","authors_text":"Chang Shu, Jing Xiao, Lu Zheng, Qian Zhang, Youxin Chen, Zijian Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-08-11T09:59:34Z","title":"ICAF: Iterative Contrastive Alignment Framework for Multimodal Abstractive Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05123","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:d5912605b054b03702af5f377d549db080f1a843b3622719407bf495681284ad","target":"record","created_at":"2026-07-05T04:46:32Z","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":"1883209550dc1f1efd01149b241f6c4e13998a4ba8833001ea14c02baa9654e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-08-11T09:59:34Z","title_canon_sha256":"1d044cd3d1d6f8577ba7bd2bb714b4f1b78cb14db36e99f2133952ebc39d980a"},"schema_version":"1.0","source":{"id":"2108.05123","kind":"arxiv","version":3}},"canonical_sha256":"69430e55e6eb8c96c2d84d1d244d65d21699d9ad1327d3fbbae26bd63632ba38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69430e55e6eb8c96c2d84d1d244d65d21699d9ad1327d3fbbae26bd63632ba38","first_computed_at":"2026-07-05T04:46:32.427113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:46:32.427113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T1HWgMe2Bv462cwOFVPKJgLeHAvIMj9LdQry0HtI+VE+cdmSO6lv1FJq3BuNTgEbSSKb+6NvsU+wBewrlZ17CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:46:32.427561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.05123","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5912605b054b03702af5f377d549db080f1a843b3622719407bf495681284ad","sha256:c6fb813143bffbbf88aa14d609685d99349caa39bfa242b5c3ad4307ac0c8e8b"],"state_sha256":"e8f1b091de1954519d06d6bd27ddb3d2323a1dd5fb29184a88b7970132fa788e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q05UehtnIN2hBuykMxfa6qXfK44mf26Ed3NsdMRWAYi94sSKTZ6iHaOn4u7okyYHsEoQJCcxCIN47wV3yPdwAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:32:05.659764Z","bundle_sha256":"a292379617900a43f391b57846083a8577418de9b9b0155644ab66f5aa31c90b"}}