{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LPZCS4C7QQPD6GZMCL7A4NLHSZ","short_pith_number":"pith:LPZCS4C7","canonical_record":{"source":{"id":"2303.07284","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-13T17:01:42Z","cross_cats_sorted":[],"title_canon_sha256":"3f00997863e4b79f84738825df98ddd103af3d2677c615c2e05737e1a91cd3e5","abstract_canon_sha256":"71f612eccb0a6ced86ab4101a80222134f11d528ef7156c265dbc5acd8545c5c"},"schema_version":"1.0"},"canonical_sha256":"5bf229705f841e3f1b2c12fe0e3567965718ff44c4a487dd7a559a7bea044837","source":{"kind":"arxiv","id":"2303.07284","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.07284","created_at":"2026-07-05T06:19:56Z"},{"alias_kind":"arxiv_version","alias_value":"2303.07284v3","created_at":"2026-07-05T06:19:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07284","created_at":"2026-07-05T06:19:56Z"},{"alias_kind":"pith_short_12","alias_value":"LPZCS4C7QQPD","created_at":"2026-07-05T06:19:56Z"},{"alias_kind":"pith_short_16","alias_value":"LPZCS4C7QQPD6GZM","created_at":"2026-07-05T06:19:56Z"},{"alias_kind":"pith_short_8","alias_value":"LPZCS4C7","created_at":"2026-07-05T06:19:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LPZCS4C7QQPD6GZMCL7A4NLHSZ","target":"record","payload":{"canonical_record":{"source":{"id":"2303.07284","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-13T17:01:42Z","cross_cats_sorted":[],"title_canon_sha256":"3f00997863e4b79f84738825df98ddd103af3d2677c615c2e05737e1a91cd3e5","abstract_canon_sha256":"71f612eccb0a6ced86ab4101a80222134f11d528ef7156c265dbc5acd8545c5c"},"schema_version":"1.0"},"canonical_sha256":"5bf229705f841e3f1b2c12fe0e3567965718ff44c4a487dd7a559a7bea044837","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:56.940904Z","signature_b64":"zXXbszCNc4M4Qna4UKs5YZ+A2qjQsp4XOnJ4HEBYafxNqpCGyb/Ap5ZMJ1cdHEbJlYx5+DL6gWQKjI9A81LHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bf229705f841e3f1b2c12fe0e3567965718ff44c4a487dd7a559a7bea044837","last_reissued_at":"2026-07-05T06:19:56.940438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:56.940438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.07284","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":"2026-07-05T06:19:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Su3v7fYvvo9/KdwSo+2kAZOZzy15/7bf6RnWduGGp8Evv5xpYTdNWkHrDkCK/wl7iDTxb8EuyqUzDZaXe5kAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:26:33.645008Z"},"content_sha256":"4ff229f8894fcc82fb740f519033b6e98a3b53623bfa982d561a6e60b2ae72b9","schema_version":"1.0","event_id":"sha256:4ff229f8894fcc82fb740f519033b6e98a3b53623bfa982d561a6e60b2ae72b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LPZCS4C7QQPD6GZMCL7A4NLHSZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Bo He, Jielin Qiu, Jun Wang, Trung Bui, Zhaowen Wang","submitted_at":"2023-03-13T17:01:42Z","abstract_excerpt":"The goal of multimodal summarization is to extract the most important information from different modalities to form output summaries. Unlike the unimodal summarization, the multimodal summarization task explicitly leverages cross-modal information to help generate more reliable and high-quality summaries. However, existing methods fail to leverage the temporal correspondence between different modalities and ignore the intrinsic correlation between different samples. To address this issue, we introduce Align and Attend Multimodal Summarization (A2Summ), a unified multimodal transformer-based mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07284","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/2303.07284/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":"2026-07-05T06:19:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LGiX4Q087qNCHzgYazGpGHwVntFRm+4XSsVdlXAIvSofjjq8wFAKnzg14aPvEDU6azEswMSwxJ5T6DL/UwGMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:26:33.645543Z"},"content_sha256":"29ae7b76e5f629b05be6c226696e5bedae99c80e8d8491f2e630913a11c10bdd","schema_version":"1.0","event_id":"sha256:29ae7b76e5f629b05be6c226696e5bedae99c80e8d8491f2e630913a11c10bdd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LPZCS4C7QQPD6GZMCL7A4NLHSZ/bundle.json","state_url":"https://pith.science/pith/LPZCS4C7QQPD6GZMCL7A4NLHSZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LPZCS4C7QQPD6GZMCL7A4NLHSZ/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":"2026-08-07T15:26:33Z","links":{"resolver":"https://pith.science/pith/LPZCS4C7QQPD6GZMCL7A4NLHSZ","bundle":"https://pith.science/pith/LPZCS4C7QQPD6GZMCL7A4NLHSZ/bundle.json","state":"https://pith.science/pith/LPZCS4C7QQPD6GZMCL7A4NLHSZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LPZCS4C7QQPD6GZMCL7A4NLHSZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LPZCS4C7QQPD6GZMCL7A4NLHSZ","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":"71f612eccb0a6ced86ab4101a80222134f11d528ef7156c265dbc5acd8545c5c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-13T17:01:42Z","title_canon_sha256":"3f00997863e4b79f84738825df98ddd103af3d2677c615c2e05737e1a91cd3e5"},"schema_version":"1.0","source":{"id":"2303.07284","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.07284","created_at":"2026-07-05T06:19:56Z"},{"alias_kind":"arxiv_version","alias_value":"2303.07284v3","created_at":"2026-07-05T06:19:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07284","created_at":"2026-07-05T06:19:56Z"},{"alias_kind":"pith_short_12","alias_value":"LPZCS4C7QQPD","created_at":"2026-07-05T06:19:56Z"},{"alias_kind":"pith_short_16","alias_value":"LPZCS4C7QQPD6GZM","created_at":"2026-07-05T06:19:56Z"},{"alias_kind":"pith_short_8","alias_value":"LPZCS4C7","created_at":"2026-07-05T06:19:56Z"}],"graph_snapshots":[{"event_id":"sha256:29ae7b76e5f629b05be6c226696e5bedae99c80e8d8491f2e630913a11c10bdd","target":"graph","created_at":"2026-07-05T06:19:56Z","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/2303.07284/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of multimodal summarization is to extract the most important information from different modalities to form output summaries. Unlike the unimodal summarization, the multimodal summarization task explicitly leverages cross-modal information to help generate more reliable and high-quality summaries. However, existing methods fail to leverage the temporal correspondence between different modalities and ignore the intrinsic correlation between different samples. To address this issue, we introduce Align and Attend Multimodal Summarization (A2Summ), a unified multimodal transformer-based mo","authors_text":"Abhinav Shrivastava, Bo He, Jielin Qiu, Jun Wang, Trung Bui, Zhaowen Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-13T17:01:42Z","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07284","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":"sha256:4ff229f8894fcc82fb740f519033b6e98a3b53623bfa982d561a6e60b2ae72b9","target":"record","created_at":"2026-07-05T06:19:56Z","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":"71f612eccb0a6ced86ab4101a80222134f11d528ef7156c265dbc5acd8545c5c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-13T17:01:42Z","title_canon_sha256":"3f00997863e4b79f84738825df98ddd103af3d2677c615c2e05737e1a91cd3e5"},"schema_version":"1.0","source":{"id":"2303.07284","kind":"arxiv","version":3}},"canonical_sha256":"5bf229705f841e3f1b2c12fe0e3567965718ff44c4a487dd7a559a7bea044837","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bf229705f841e3f1b2c12fe0e3567965718ff44c4a487dd7a559a7bea044837","first_computed_at":"2026-07-05T06:19:56.940438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:56.940438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zXXbszCNc4M4Qna4UKs5YZ+A2qjQsp4XOnJ4HEBYafxNqpCGyb/Ap5ZMJ1cdHEbJlYx5+DL6gWQKjI9A81LHBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:56.940904Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.07284","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ff229f8894fcc82fb740f519033b6e98a3b53623bfa982d561a6e60b2ae72b9","sha256:29ae7b76e5f629b05be6c226696e5bedae99c80e8d8491f2e630913a11c10bdd"],"state_sha256":"c1f66e9526b57875951d3a16717a951690a60b7839dbf2003286f47563a38edf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YUiBLA9zFm2c/ToFoGx9WWXtBnEg0XBjBnom40t9OiE1dgPyJw+sXBR0jfSN0BQdlOVmGwG9IGEWy8SzIDK1DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:26:33.650067Z","bundle_sha256":"70b0061921f50e884be140ac324a22e03f9a4407704a468bc6483b6b246acc73"}}