{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YEIS3ADLO3SXHLHGULNFKDA3MJ","short_pith_number":"pith:YEIS3ADL","schema_version":"1.0","canonical_sha256":"c1112d806b76e573ace6a2da550c1b626447d71682ff78a1cd44ceb1b0884e71","source":{"kind":"arxiv","id":"2305.12767","version":2},"attestation_state":"computed","paper":{"title":"D$^2$TV: Dual Knowledge Distillation and Target-oriented Vision Modeling for Many-to-Many Multimodal Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Fandong Meng, Jiaan Wang, Jie Zhou, Jinan Xu, Yufeng Chen, Yunlong Liang","submitted_at":"2023-05-22T06:47:35Z","abstract_excerpt":"Many-to-many multimodal summarization (M$^3$S) task aims to generate summaries in any language with document inputs in any language and the corresponding image sequence, which essentially comprises multimodal monolingual summarization (MMS) and multimodal cross-lingual summarization (MXLS) tasks. Although much work has been devoted to either MMS or MXLS and has obtained increasing attention in recent years, little research pays attention to the M$^3$S task. Besides, existing studies mainly focus on 1) utilizing MMS to enhance MXLS via knowledge distillation without considering the performance "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.12767","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-22T06:47:35Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"5e99f3f10bab8b5fd1676feb5023bb58f03a6b140b6379aa5f3b9cb6d7351b65","abstract_canon_sha256":"2a51a540340ead5ec39b26aa5cd25e421c7583cb61a93676a743725e74c14f42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:01.482614Z","signature_b64":"mjJzHrNLPAiehtcKaETkxkJcIpCUJwwLPwGiOVDl5rQ5mn9zKW++UWjS06XNDdLI7Zd6GqbcxWAGH5ULAbJeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1112d806b76e573ace6a2da550c1b626447d71682ff78a1cd44ceb1b0884e71","last_reissued_at":"2026-07-05T07:01:01.482108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:01.482108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"D$^2$TV: Dual Knowledge Distillation and Target-oriented Vision Modeling for Many-to-Many Multimodal Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Fandong Meng, Jiaan Wang, Jie Zhou, Jinan Xu, Yufeng Chen, Yunlong Liang","submitted_at":"2023-05-22T06:47:35Z","abstract_excerpt":"Many-to-many multimodal summarization (M$^3$S) task aims to generate summaries in any language with document inputs in any language and the corresponding image sequence, which essentially comprises multimodal monolingual summarization (MMS) and multimodal cross-lingual summarization (MXLS) tasks. Although much work has been devoted to either MMS or MXLS and has obtained increasing attention in recent years, little research pays attention to the M$^3$S task. Besides, existing studies mainly focus on 1) utilizing MMS to enhance MXLS via knowledge distillation without considering the performance "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12767","kind":"arxiv","version":2},"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/2305.12767/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.12767","created_at":"2026-07-05T07:01:01.482167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12767v2","created_at":"2026-07-05T07:01:01.482167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12767","created_at":"2026-07-05T07:01:01.482167+00:00"},{"alias_kind":"pith_short_12","alias_value":"YEIS3ADLO3SX","created_at":"2026-07-05T07:01:01.482167+00:00"},{"alias_kind":"pith_short_16","alias_value":"YEIS3ADLO3SXHLHG","created_at":"2026-07-05T07:01:01.482167+00:00"},{"alias_kind":"pith_short_8","alias_value":"YEIS3ADL","created_at":"2026-07-05T07:01:01.482167+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YEIS3ADLO3SXHLHGULNFKDA3MJ","json":"https://pith.science/pith/YEIS3ADLO3SXHLHGULNFKDA3MJ.json","graph_json":"https://pith.science/api/pith-number/YEIS3ADLO3SXHLHGULNFKDA3MJ/graph.json","events_json":"https://pith.science/api/pith-number/YEIS3ADLO3SXHLHGULNFKDA3MJ/events.json","paper":"https://pith.science/paper/YEIS3ADL"},"agent_actions":{"view_html":"https://pith.science/pith/YEIS3ADLO3SXHLHGULNFKDA3MJ","download_json":"https://pith.science/pith/YEIS3ADLO3SXHLHGULNFKDA3MJ.json","view_paper":"https://pith.science/paper/YEIS3ADL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12767&json=true","fetch_graph":"https://pith.science/api/pith-number/YEIS3ADLO3SXHLHGULNFKDA3MJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YEIS3ADLO3SXHLHGULNFKDA3MJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YEIS3ADLO3SXHLHGULNFKDA3MJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YEIS3ADLO3SXHLHGULNFKDA3MJ/action/storage_attestation","attest_author":"https://pith.science/pith/YEIS3ADLO3SXHLHGULNFKDA3MJ/action/author_attestation","sign_citation":"https://pith.science/pith/YEIS3ADLO3SXHLHGULNFKDA3MJ/action/citation_signature","submit_replication":"https://pith.science/pith/YEIS3ADLO3SXHLHGULNFKDA3MJ/action/replication_record"}},"created_at":"2026-07-05T07:01:01.482167+00:00","updated_at":"2026-07-05T07:01:01.482167+00:00"}