{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KGHKRBPKJRLCLBMF3HPYOTVLHQ","short_pith_number":"pith:KGHKRBPK","schema_version":"1.0","canonical_sha256":"518ea885ea4c56258585d9df874eab3c258db9bbc4b2a9707547a63063f26a45","source":{"kind":"arxiv","id":"2211.12981","version":2},"attestation_state":"computed","paper":{"title":"Holistic Visual-Textual Sentiment Analysis with Prior Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Christopher Kanan, Hanjia Lyu, Jie An, Jiebo Luo, Junyu Chen","submitted_at":"2022-11-23T14:40:51Z","abstract_excerpt":"Visual-textual sentiment analysis aims to predict sentiment with the input of a pair of image and text, which poses a challenge in learning effective features for diverse input images. To address this, we propose a holistic method that achieves robust visual-textual sentiment analysis by exploiting a rich set of powerful pre-trained visual and textual prior models. The proposed method consists of four parts: (1) a visual-textual branch to learn features directly from data for sentiment analysis, (2) a visual expert branch with a set of pre-trained \"expert\" encoders to extract selected semantic"},"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":"2211.12981","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-23T14:40:51Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"dabc03512acee9e0516a7ea44dc153f8750e4b2ffb404830b319d93a0a77f0f8","abstract_canon_sha256":"92ac314587e189a7f84f81eb1bc65c5c474a0e9e9381e2e9b9b4787adb18cf50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:13.433182Z","signature_b64":"n09tvxFNHJS4+B//3HfSvH21w7Xbo3BC2lu1p1tM5J/jkFtzo+vCqjbi2bfOAXyRJStDNhGcsemW6YzAHEjVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"518ea885ea4c56258585d9df874eab3c258db9bbc4b2a9707547a63063f26a45","last_reissued_at":"2026-07-05T08:29:13.432703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:13.432703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Holistic Visual-Textual Sentiment Analysis with Prior Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Christopher Kanan, Hanjia Lyu, Jie An, Jiebo Luo, Junyu Chen","submitted_at":"2022-11-23T14:40:51Z","abstract_excerpt":"Visual-textual sentiment analysis aims to predict sentiment with the input of a pair of image and text, which poses a challenge in learning effective features for diverse input images. To address this, we propose a holistic method that achieves robust visual-textual sentiment analysis by exploiting a rich set of powerful pre-trained visual and textual prior models. The proposed method consists of four parts: (1) a visual-textual branch to learn features directly from data for sentiment analysis, (2) a visual expert branch with a set of pre-trained \"expert\" encoders to extract selected semantic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12981","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/2211.12981/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":"2211.12981","created_at":"2026-07-05T08:29:13.432763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.12981v2","created_at":"2026-07-05T08:29:13.432763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12981","created_at":"2026-07-05T08:29:13.432763+00:00"},{"alias_kind":"pith_short_12","alias_value":"KGHKRBPKJRLC","created_at":"2026-07-05T08:29:13.432763+00:00"},{"alias_kind":"pith_short_16","alias_value":"KGHKRBPKJRLCLBMF","created_at":"2026-07-05T08:29:13.432763+00:00"},{"alias_kind":"pith_short_8","alias_value":"KGHKRBPK","created_at":"2026-07-05T08:29:13.432763+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02938","citing_title":"LLaVAC: Fine-tuning LLaVA as a Multimodal Sentiment Classifier","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KGHKRBPKJRLCLBMF3HPYOTVLHQ","json":"https://pith.science/pith/KGHKRBPKJRLCLBMF3HPYOTVLHQ.json","graph_json":"https://pith.science/api/pith-number/KGHKRBPKJRLCLBMF3HPYOTVLHQ/graph.json","events_json":"https://pith.science/api/pith-number/KGHKRBPKJRLCLBMF3HPYOTVLHQ/events.json","paper":"https://pith.science/paper/KGHKRBPK"},"agent_actions":{"view_html":"https://pith.science/pith/KGHKRBPKJRLCLBMF3HPYOTVLHQ","download_json":"https://pith.science/pith/KGHKRBPKJRLCLBMF3HPYOTVLHQ.json","view_paper":"https://pith.science/paper/KGHKRBPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.12981&json=true","fetch_graph":"https://pith.science/api/pith-number/KGHKRBPKJRLCLBMF3HPYOTVLHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KGHKRBPKJRLCLBMF3HPYOTVLHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KGHKRBPKJRLCLBMF3HPYOTVLHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KGHKRBPKJRLCLBMF3HPYOTVLHQ/action/storage_attestation","attest_author":"https://pith.science/pith/KGHKRBPKJRLCLBMF3HPYOTVLHQ/action/author_attestation","sign_citation":"https://pith.science/pith/KGHKRBPKJRLCLBMF3HPYOTVLHQ/action/citation_signature","submit_replication":"https://pith.science/pith/KGHKRBPKJRLCLBMF3HPYOTVLHQ/action/replication_record"}},"created_at":"2026-07-05T08:29:13.432763+00:00","updated_at":"2026-07-05T08:29:13.432763+00:00"}