{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HJVCHPUAIA46RTVIKKA5HYKVC2","short_pith_number":"pith:HJVCHPUA","schema_version":"1.0","canonical_sha256":"3a6a23be804039e8cea85281d3e155168a481576bc3e5478d8200e2319d3b7e5","source":{"kind":"arxiv","id":"2606.03604","version":1},"attestation_state":"computed","paper":{"title":"Beyond the Literal: Decomposing Pragmatic Intent in Multimodal Meme Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binyang Li, Hanqi Yan, Huimin Wang, Kam-Fai Wong, Luyao Ye, Shubo Zhang, Yulan He, Zezhong Wang, Zhengyi Zhao","submitted_at":"2026-06-02T13:09:04Z","abstract_excerpt":"When asked what a meme or sarcastic post means, Large Vision Language Models (LVLMs) tend to describe what the image shows rather than what the author is trying to communicate. Standard instruction tuning entangles a post's literal content with its pragmatic meaning, letting surface-level details contaminate the final response. We reframe meme understanding as a problem of literal-pragmatic decomposition and propose \\textbf{Intent Projection}, a framework that separates the two signals at the representation, output, and objective levels within a single LVLM backbone. At the representation leve"},"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":"2606.03604","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T13:09:04Z","cross_cats_sorted":[],"title_canon_sha256":"f07c3a626c39292544ff6439e75c8f3786be00524a217d44e953e3f6077bb137","abstract_canon_sha256":"d4d673a897fb9cfc0a1dc87d21ad623dd205e8e3404d9146332e32696fafcde2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:06:02.149111Z","signature_b64":"xkp46YOlDPdz13JCCpbmUu1/u23xiBwn4wbFjrb99PILgMQAYmPC8F2yLrS9ILQP49YN3DeSLIijP6UffJQ5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a6a23be804039e8cea85281d3e155168a481576bc3e5478d8200e2319d3b7e5","last_reissued_at":"2026-06-03T01:06:02.148614Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:06:02.148614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond the Literal: Decomposing Pragmatic Intent in Multimodal Meme Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binyang Li, Hanqi Yan, Huimin Wang, Kam-Fai Wong, Luyao Ye, Shubo Zhang, Yulan He, Zezhong Wang, Zhengyi Zhao","submitted_at":"2026-06-02T13:09:04Z","abstract_excerpt":"When asked what a meme or sarcastic post means, Large Vision Language Models (LVLMs) tend to describe what the image shows rather than what the author is trying to communicate. Standard instruction tuning entangles a post's literal content with its pragmatic meaning, letting surface-level details contaminate the final response. We reframe meme understanding as a problem of literal-pragmatic decomposition and propose \\textbf{Intent Projection}, a framework that separates the two signals at the representation, output, and objective levels within a single LVLM backbone. At the representation leve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03604","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/2606.03604/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":"2606.03604","created_at":"2026-06-03T01:06:02.148677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03604v1","created_at":"2026-06-03T01:06:02.148677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03604","created_at":"2026-06-03T01:06:02.148677+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJVCHPUAIA46","created_at":"2026-06-03T01:06:02.148677+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJVCHPUAIA46RTVI","created_at":"2026-06-03T01:06:02.148677+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJVCHPUA","created_at":"2026-06-03T01:06:02.148677+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/HJVCHPUAIA46RTVIKKA5HYKVC2","json":"https://pith.science/pith/HJVCHPUAIA46RTVIKKA5HYKVC2.json","graph_json":"https://pith.science/api/pith-number/HJVCHPUAIA46RTVIKKA5HYKVC2/graph.json","events_json":"https://pith.science/api/pith-number/HJVCHPUAIA46RTVIKKA5HYKVC2/events.json","paper":"https://pith.science/paper/HJVCHPUA"},"agent_actions":{"view_html":"https://pith.science/pith/HJVCHPUAIA46RTVIKKA5HYKVC2","download_json":"https://pith.science/pith/HJVCHPUAIA46RTVIKKA5HYKVC2.json","view_paper":"https://pith.science/paper/HJVCHPUA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03604&json=true","fetch_graph":"https://pith.science/api/pith-number/HJVCHPUAIA46RTVIKKA5HYKVC2/graph.json","fetch_events":"https://pith.science/api/pith-number/HJVCHPUAIA46RTVIKKA5HYKVC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJVCHPUAIA46RTVIKKA5HYKVC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJVCHPUAIA46RTVIKKA5HYKVC2/action/storage_attestation","attest_author":"https://pith.science/pith/HJVCHPUAIA46RTVIKKA5HYKVC2/action/author_attestation","sign_citation":"https://pith.science/pith/HJVCHPUAIA46RTVIKKA5HYKVC2/action/citation_signature","submit_replication":"https://pith.science/pith/HJVCHPUAIA46RTVIKKA5HYKVC2/action/replication_record"}},"created_at":"2026-06-03T01:06:02.148677+00:00","updated_at":"2026-06-03T01:06:02.148677+00:00"}