{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6BLUU7LARYOENY3RT6CMX6CSIF","short_pith_number":"pith:6BLUU7LA","schema_version":"1.0","canonical_sha256":"f0574a7d608e1c46e3719f84cbf852414b0088a7557dd2b1110d771e8f991876","source":{"kind":"arxiv","id":"2411.11909","version":2},"attestation_state":"computed","paper":{"title":"SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoya Jiang, Fei Huang, Haiyang Xu, Hongrui Jia, Ji Zhang, Mengfan Dong, Ming Yan, Shikun Zhang, Wei Ye","submitted_at":"2024-11-17T08:29:14Z","abstract_excerpt":"As language models continue to scale, Large Language Models (LLMs) have exhibited emerging capabilities in In-Context Learning (ICL), enabling them to solve language tasks by prefixing a few in-context demonstrations (ICDs) as context. Inspired by these advancements, researchers have extended these techniques to develop Large Multimodal Models (LMMs) with ICL capabilities. However, existing LMMs face a critical issue: they often fail to effectively leverage the visual context in multimodal demonstrations and instead simply follow textual patterns. This indicates that LMMs do not achieve effect"},"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":"2411.11909","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-17T08:29:14Z","cross_cats_sorted":[],"title_canon_sha256":"6ad1f2e57b98bf32176f821f24180614c042adbefb474f2a17ce00d42ae6a2d1","abstract_canon_sha256":"ba5403ad9c6059a33ec73646e092a0f220f3af7329eb93896fc06bc240e3c8be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:29.461675Z","signature_b64":"bqCFyY7fFy8g6HzuEyoNI7Nom1m3RlQhuugQEer33uGiAEMdbXhosyy9wj4t5BDJWReLQt4Y9J/0NyiYdB4PBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0574a7d608e1c46e3719f84cbf852414b0088a7557dd2b1110d771e8f991876","last_reissued_at":"2026-07-05T09:39:29.461203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:29.461203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoya Jiang, Fei Huang, Haiyang Xu, Hongrui Jia, Ji Zhang, Mengfan Dong, Ming Yan, Shikun Zhang, Wei Ye","submitted_at":"2024-11-17T08:29:14Z","abstract_excerpt":"As language models continue to scale, Large Language Models (LLMs) have exhibited emerging capabilities in In-Context Learning (ICL), enabling them to solve language tasks by prefixing a few in-context demonstrations (ICDs) as context. Inspired by these advancements, researchers have extended these techniques to develop Large Multimodal Models (LMMs) with ICL capabilities. However, existing LMMs face a critical issue: they often fail to effectively leverage the visual context in multimodal demonstrations and instead simply follow textual patterns. This indicates that LMMs do not achieve effect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11909","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/2411.11909/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":"2411.11909","created_at":"2026-07-05T09:39:29.461262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11909v2","created_at":"2026-07-05T09:39:29.461262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11909","created_at":"2026-07-05T09:39:29.461262+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BLUU7LARYOE","created_at":"2026-07-05T09:39:29.461262+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BLUU7LARYOENY3R","created_at":"2026-07-05T09:39:29.461262+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BLUU7LA","created_at":"2026-07-05T09:39:29.461262+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13403","citing_title":"Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6BLUU7LARYOENY3RT6CMX6CSIF","json":"https://pith.science/pith/6BLUU7LARYOENY3RT6CMX6CSIF.json","graph_json":"https://pith.science/api/pith-number/6BLUU7LARYOENY3RT6CMX6CSIF/graph.json","events_json":"https://pith.science/api/pith-number/6BLUU7LARYOENY3RT6CMX6CSIF/events.json","paper":"https://pith.science/paper/6BLUU7LA"},"agent_actions":{"view_html":"https://pith.science/pith/6BLUU7LARYOENY3RT6CMX6CSIF","download_json":"https://pith.science/pith/6BLUU7LARYOENY3RT6CMX6CSIF.json","view_paper":"https://pith.science/paper/6BLUU7LA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11909&json=true","fetch_graph":"https://pith.science/api/pith-number/6BLUU7LARYOENY3RT6CMX6CSIF/graph.json","fetch_events":"https://pith.science/api/pith-number/6BLUU7LARYOENY3RT6CMX6CSIF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BLUU7LARYOENY3RT6CMX6CSIF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BLUU7LARYOENY3RT6CMX6CSIF/action/storage_attestation","attest_author":"https://pith.science/pith/6BLUU7LARYOENY3RT6CMX6CSIF/action/author_attestation","sign_citation":"https://pith.science/pith/6BLUU7LARYOENY3RT6CMX6CSIF/action/citation_signature","submit_replication":"https://pith.science/pith/6BLUU7LARYOENY3RT6CMX6CSIF/action/replication_record"}},"created_at":"2026-07-05T09:39:29.461262+00:00","updated_at":"2026-07-05T09:39:29.461262+00:00"}