{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4W5SPCSXNAB2H4EAAZCSBPBGBF","short_pith_number":"pith:4W5SPCSX","schema_version":"1.0","canonical_sha256":"e5bb278a576803a3f080064520bc26094f65e5e7d3353fb225992ae2ce14f012","source":{"kind":"arxiv","id":"2204.07955","version":2},"attestation_state":"computed","paper":{"title":"Vision-Language Pre-Training for Multimodal Aspect-Based Sentiment Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Jianfei Yu, Rui Xia, Yan Ling","submitted_at":"2022-04-17T08:44:00Z","abstract_excerpt":"As an important task in sentiment analysis, Multimodal Aspect-Based Sentiment Analysis (MABSA) has attracted increasing attention in recent years. However, previous approaches either (i) use separately pre-trained visual and textual models, which ignore the crossmodal alignment or (ii) use vision-language models pre-trained with general pre-training tasks, which are inadequate to identify finegrained aspects, opinions, and their alignments across modalities. To tackle these limitations, we propose a task-specific Vision-Language Pre-training framework for MABSA (VLPMABSA), which is a unified m"},"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":"2204.07955","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-17T08:44:00Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"889d77b8bd733c06102133a58809dd590eaf09285548a18ea8e60e9cafb88fec","abstract_canon_sha256":"6643f2a1e34e874dbfd33eb52ad835d5e0ba3fb70e6e7d1ed0d32001661d1abf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:41.330651Z","signature_b64":"cBvfhdC1okTroI323dw+frdSm2fGNifjhkG4a6/tm8WF+NRX6EWVkKdQBI3tQk1ZHXxhafkWKjxmi8HQqey5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5bb278a576803a3f080064520bc26094f65e5e7d3353fb225992ae2ce14f012","last_reissued_at":"2026-07-05T04:16:41.330250Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:41.330250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-Language Pre-Training for Multimodal Aspect-Based Sentiment Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Jianfei Yu, Rui Xia, Yan Ling","submitted_at":"2022-04-17T08:44:00Z","abstract_excerpt":"As an important task in sentiment analysis, Multimodal Aspect-Based Sentiment Analysis (MABSA) has attracted increasing attention in recent years. However, previous approaches either (i) use separately pre-trained visual and textual models, which ignore the crossmodal alignment or (ii) use vision-language models pre-trained with general pre-training tasks, which are inadequate to identify finegrained aspects, opinions, and their alignments across modalities. To tackle these limitations, we propose a task-specific Vision-Language Pre-training framework for MABSA (VLPMABSA), which is a unified m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.07955","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/2204.07955/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":"2204.07955","created_at":"2026-07-05T04:16:41.330306+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.07955v2","created_at":"2026-07-05T04:16:41.330306+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.07955","created_at":"2026-07-05T04:16:41.330306+00:00"},{"alias_kind":"pith_short_12","alias_value":"4W5SPCSXNAB2","created_at":"2026-07-05T04:16:41.330306+00:00"},{"alias_kind":"pith_short_16","alias_value":"4W5SPCSXNAB2H4EA","created_at":"2026-07-05T04:16:41.330306+00:00"},{"alias_kind":"pith_short_8","alias_value":"4W5SPCSX","created_at":"2026-07-05T04:16:41.330306+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16854","citing_title":"CLAMP: Contrastive Learning with Adaptive Multi-loss and Progressive Fusion for Multimodal Aspect-Based Sentiment Analysis","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4W5SPCSXNAB2H4EAAZCSBPBGBF","json":"https://pith.science/pith/4W5SPCSXNAB2H4EAAZCSBPBGBF.json","graph_json":"https://pith.science/api/pith-number/4W5SPCSXNAB2H4EAAZCSBPBGBF/graph.json","events_json":"https://pith.science/api/pith-number/4W5SPCSXNAB2H4EAAZCSBPBGBF/events.json","paper":"https://pith.science/paper/4W5SPCSX"},"agent_actions":{"view_html":"https://pith.science/pith/4W5SPCSXNAB2H4EAAZCSBPBGBF","download_json":"https://pith.science/pith/4W5SPCSXNAB2H4EAAZCSBPBGBF.json","view_paper":"https://pith.science/paper/4W5SPCSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.07955&json=true","fetch_graph":"https://pith.science/api/pith-number/4W5SPCSXNAB2H4EAAZCSBPBGBF/graph.json","fetch_events":"https://pith.science/api/pith-number/4W5SPCSXNAB2H4EAAZCSBPBGBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4W5SPCSXNAB2H4EAAZCSBPBGBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4W5SPCSXNAB2H4EAAZCSBPBGBF/action/storage_attestation","attest_author":"https://pith.science/pith/4W5SPCSXNAB2H4EAAZCSBPBGBF/action/author_attestation","sign_citation":"https://pith.science/pith/4W5SPCSXNAB2H4EAAZCSBPBGBF/action/citation_signature","submit_replication":"https://pith.science/pith/4W5SPCSXNAB2H4EAAZCSBPBGBF/action/replication_record"}},"created_at":"2026-07-05T04:16:41.330306+00:00","updated_at":"2026-07-05T04:16:41.330306+00:00"}