{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PM5ZGGNJDNGYGRFYTFU3PWHVDO","short_pith_number":"pith:PM5ZGGNJ","schema_version":"1.0","canonical_sha256":"7b3b9319a91b4d8344b89969b7d8f51b9f5d44318e24305aad4448131106e91e","source":{"kind":"arxiv","id":"2504.18012","version":1},"attestation_state":"computed","paper":{"title":"Memory Reviving, Continuing Learning and Beyond: Evaluation of Pre-trained Encoders and Decoders for Multimodal Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hao Yang, Jing Zhao, Shiliang Sun, Tengfei Song, Zhuang Yu","submitted_at":"2025-04-25T01:44:04Z","abstract_excerpt":"Multimodal Machine Translation (MMT) aims to improve translation quality by leveraging auxiliary modalities such as images alongside textual input. While recent advances in large-scale pre-trained language and vision models have significantly benefited unimodal natural language processing tasks, their effectiveness and role in MMT remain underexplored. In this work, we conduct a systematic study on the impact of pre-trained encoders and decoders in multimodal translation models. Specifically, we analyze how different training strategies, from training from scratch to using pre-trained and part"},"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":"2504.18012","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-25T01:44:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"43eb91a3fac4001ce7887bcd82213af26f44d55f42dbd76174ab47422865228b","abstract_canon_sha256":"a1e28104b308080bcfc58a445ea185ccd31b2fadc99f25a0c652366df2712bb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:00.292143Z","signature_b64":"v+PgxC1YjnFDT9s4d7gzh535UTDNqT4be1jv/55JKGTchGpR4vujZilQ8IRny5aBsjHpqDTpJxvBk0qleJ87Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b3b9319a91b4d8344b89969b7d8f51b9f5d44318e24305aad4448131106e91e","last_reissued_at":"2026-07-05T10:54:00.291596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:00.291596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory Reviving, Continuing Learning and Beyond: Evaluation of Pre-trained Encoders and Decoders for Multimodal Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hao Yang, Jing Zhao, Shiliang Sun, Tengfei Song, Zhuang Yu","submitted_at":"2025-04-25T01:44:04Z","abstract_excerpt":"Multimodal Machine Translation (MMT) aims to improve translation quality by leveraging auxiliary modalities such as images alongside textual input. While recent advances in large-scale pre-trained language and vision models have significantly benefited unimodal natural language processing tasks, their effectiveness and role in MMT remain underexplored. In this work, we conduct a systematic study on the impact of pre-trained encoders and decoders in multimodal translation models. Specifically, we analyze how different training strategies, from training from scratch to using pre-trained and part"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18012","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/2504.18012/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":"2504.18012","created_at":"2026-07-05T10:54:00.291679+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.18012v1","created_at":"2026-07-05T10:54:00.291679+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18012","created_at":"2026-07-05T10:54:00.291679+00:00"},{"alias_kind":"pith_short_12","alias_value":"PM5ZGGNJDNGY","created_at":"2026-07-05T10:54:00.291679+00:00"},{"alias_kind":"pith_short_16","alias_value":"PM5ZGGNJDNGYGRFY","created_at":"2026-07-05T10:54:00.291679+00:00"},{"alias_kind":"pith_short_8","alias_value":"PM5ZGGNJ","created_at":"2026-07-05T10:54:00.291679+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/PM5ZGGNJDNGYGRFYTFU3PWHVDO","json":"https://pith.science/pith/PM5ZGGNJDNGYGRFYTFU3PWHVDO.json","graph_json":"https://pith.science/api/pith-number/PM5ZGGNJDNGYGRFYTFU3PWHVDO/graph.json","events_json":"https://pith.science/api/pith-number/PM5ZGGNJDNGYGRFYTFU3PWHVDO/events.json","paper":"https://pith.science/paper/PM5ZGGNJ"},"agent_actions":{"view_html":"https://pith.science/pith/PM5ZGGNJDNGYGRFYTFU3PWHVDO","download_json":"https://pith.science/pith/PM5ZGGNJDNGYGRFYTFU3PWHVDO.json","view_paper":"https://pith.science/paper/PM5ZGGNJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.18012&json=true","fetch_graph":"https://pith.science/api/pith-number/PM5ZGGNJDNGYGRFYTFU3PWHVDO/graph.json","fetch_events":"https://pith.science/api/pith-number/PM5ZGGNJDNGYGRFYTFU3PWHVDO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PM5ZGGNJDNGYGRFYTFU3PWHVDO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PM5ZGGNJDNGYGRFYTFU3PWHVDO/action/storage_attestation","attest_author":"https://pith.science/pith/PM5ZGGNJDNGYGRFYTFU3PWHVDO/action/author_attestation","sign_citation":"https://pith.science/pith/PM5ZGGNJDNGYGRFYTFU3PWHVDO/action/citation_signature","submit_replication":"https://pith.science/pith/PM5ZGGNJDNGYGRFYTFU3PWHVDO/action/replication_record"}},"created_at":"2026-07-05T10:54:00.291679+00:00","updated_at":"2026-07-05T10:54:00.291679+00:00"}