{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:W3X6P4F3474KG6GPW5CPBWAV3K","short_pith_number":"pith:W3X6P4F3","canonical_record":{"source":{"id":"2204.03734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T21:00:40Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"f181f4a3e033f2c9814c89aa71a0905b9d446d58169e295a76bea061e7c509fa","abstract_canon_sha256":"6ae43caa8a48d65f27f43b768b7b66b7df287b9de494abefb60c7ca1072fd2ca"},"schema_version":"1.0"},"canonical_sha256":"b6efe7f0bbe7f8a378cfb744f0d815dab2dbbcea5309a9aa86f9039b7999cfa8","source":{"kind":"arxiv","id":"2204.03734","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.03734","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"arxiv_version","alias_value":"2204.03734v1","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03734","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"pith_short_12","alias_value":"W3X6P4F3474K","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"pith_short_16","alias_value":"W3X6P4F3474KG6GP","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"pith_short_8","alias_value":"W3X6P4F3","created_at":"2026-07-05T04:12:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:W3X6P4F3474KG6GPW5CPBWAV3K","target":"record","payload":{"canonical_record":{"source":{"id":"2204.03734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T21:00:40Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"f181f4a3e033f2c9814c89aa71a0905b9d446d58169e295a76bea061e7c509fa","abstract_canon_sha256":"6ae43caa8a48d65f27f43b768b7b66b7df287b9de494abefb60c7ca1072fd2ca"},"schema_version":"1.0"},"canonical_sha256":"b6efe7f0bbe7f8a378cfb744f0d815dab2dbbcea5309a9aa86f9039b7999cfa8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:41.328146Z","signature_b64":"eeg8TVbyxL6znCDVIcrkCedOzuLHyaQQSql44tjyTrqeFxRWrzDuO81+Ug8R1pymNKqdTdspFwAY9m6MuxKGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6efe7f0bbe7f8a378cfb744f0d815dab2dbbcea5309a9aa86f9039b7999cfa8","last_reissued_at":"2026-07-05T04:12:41.327672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:41.327672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.03734","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:12:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5OOmKLtl+d+ROw3C1B/+FbO0+g2jQAT+DoFhphj9gDitl167uxtJmJa0SBWs1Veij8rjkQu7M5af3doGVFF6Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:36:13.826179Z"},"content_sha256":"4132e19f4bc59e9cdcf7e576cb707ab8d0fad3c626d3e22390c3baebc5907c24","schema_version":"1.0","event_id":"sha256:4132e19f4bc59e9cdcf7e576cb707ab8d0fad3c626d3e22390c3baebc5907c24"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:W3X6P4F3474KG6GPW5CPBWAV3K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MHMS: Multimodal Hierarchical Multimedia Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Bo Li, Ding Zhao, Franck Dernoncourt, Hailin Jin, Jiacheng Zhu, Jielin Qiu, Mengdi Xu, Trung Bui, Zhaowen Wang","submitted_at":"2022-04-07T21:00:40Z","abstract_excerpt":"Multimedia summarization with multimodal output can play an essential role in real-world applications, i.e., automatically generating cover images and titles for news articles or providing introductions to online videos. In this work, we propose a multimodal hierarchical multimedia summarization (MHMS) framework by interacting visual and language domains to generate both video and textual summaries. Our MHMS method contains video and textual segmentation and summarization module, respectively. It formulates a cross-domain alignment objective with optimal transport distance which leverages cros"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03734","kind":"arxiv","version":1},"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/2204.03734/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":"2026-07-05T04:12:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hiR30Cn4f4/9GzjttPE61P5pE+AvEi//rnziVb9KO2gnlLUprRVgwfVlC1jzTXePJtWCOnFrdEa+pPqjBCCtCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:36:13.826711Z"},"content_sha256":"fd2d61f12e40ca5b2ed126aa2679a87788fccf821c4e2ab83ba2f8595e583862","schema_version":"1.0","event_id":"sha256:fd2d61f12e40ca5b2ed126aa2679a87788fccf821c4e2ab83ba2f8595e583862"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W3X6P4F3474KG6GPW5CPBWAV3K/bundle.json","state_url":"https://pith.science/pith/W3X6P4F3474KG6GPW5CPBWAV3K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W3X6P4F3474KG6GPW5CPBWAV3K/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":"2026-08-05T22:36:13Z","links":{"resolver":"https://pith.science/pith/W3X6P4F3474KG6GPW5CPBWAV3K","bundle":"https://pith.science/pith/W3X6P4F3474KG6GPW5CPBWAV3K/bundle.json","state":"https://pith.science/pith/W3X6P4F3474KG6GPW5CPBWAV3K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W3X6P4F3474KG6GPW5CPBWAV3K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:W3X6P4F3474KG6GPW5CPBWAV3K","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":"6ae43caa8a48d65f27f43b768b7b66b7df287b9de494abefb60c7ca1072fd2ca","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T21:00:40Z","title_canon_sha256":"f181f4a3e033f2c9814c89aa71a0905b9d446d58169e295a76bea061e7c509fa"},"schema_version":"1.0","source":{"id":"2204.03734","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.03734","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"arxiv_version","alias_value":"2204.03734v1","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03734","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"pith_short_12","alias_value":"W3X6P4F3474K","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"pith_short_16","alias_value":"W3X6P4F3474KG6GP","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"pith_short_8","alias_value":"W3X6P4F3","created_at":"2026-07-05T04:12:41Z"}],"graph_snapshots":[{"event_id":"sha256:fd2d61f12e40ca5b2ed126aa2679a87788fccf821c4e2ab83ba2f8595e583862","target":"graph","created_at":"2026-07-05T04:12:41Z","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/2204.03734/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimedia summarization with multimodal output can play an essential role in real-world applications, i.e., automatically generating cover images and titles for news articles or providing introductions to online videos. In this work, we propose a multimodal hierarchical multimedia summarization (MHMS) framework by interacting visual and language domains to generate both video and textual summaries. Our MHMS method contains video and textual segmentation and summarization module, respectively. It formulates a cross-domain alignment objective with optimal transport distance which leverages cros","authors_text":"Bo Li, Ding Zhao, Franck Dernoncourt, Hailin Jin, Jiacheng Zhu, Jielin Qiu, Mengdi Xu, Trung Bui, Zhaowen Wang","cross_cats":["cs.CL","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T21:00:40Z","title":"MHMS: Multimodal Hierarchical Multimedia Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03734","kind":"arxiv","version":1},"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":"sha256:4132e19f4bc59e9cdcf7e576cb707ab8d0fad3c626d3e22390c3baebc5907c24","target":"record","created_at":"2026-07-05T04:12:41Z","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":"6ae43caa8a48d65f27f43b768b7b66b7df287b9de494abefb60c7ca1072fd2ca","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T21:00:40Z","title_canon_sha256":"f181f4a3e033f2c9814c89aa71a0905b9d446d58169e295a76bea061e7c509fa"},"schema_version":"1.0","source":{"id":"2204.03734","kind":"arxiv","version":1}},"canonical_sha256":"b6efe7f0bbe7f8a378cfb744f0d815dab2dbbcea5309a9aa86f9039b7999cfa8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6efe7f0bbe7f8a378cfb744f0d815dab2dbbcea5309a9aa86f9039b7999cfa8","first_computed_at":"2026-07-05T04:12:41.327672Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:12:41.327672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eeg8TVbyxL6znCDVIcrkCedOzuLHyaQQSql44tjyTrqeFxRWrzDuO81+Ug8R1pymNKqdTdspFwAY9m6MuxKGCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:12:41.328146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.03734","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4132e19f4bc59e9cdcf7e576cb707ab8d0fad3c626d3e22390c3baebc5907c24","sha256:fd2d61f12e40ca5b2ed126aa2679a87788fccf821c4e2ab83ba2f8595e583862"],"state_sha256":"15cfecb0e1dd41c6678862856eece30e806d025bcdce11ec12b849a0c317ca07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kUa2OwpN3lAQsRQ9cBmgA5NMCrXhREuwlUgqwWr6iAfAGQ5oY1Pzf7fF32TcIPtuzBWOdHmhIcM+l4aiar8xCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:36:13.831909Z","bundle_sha256":"aa34e085b70e491066fef9065a482368f1c7fd95d5774e69185573d5c475f372"}}