{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5X7IWD7CJ7ZKQWM3XUNTSAO3S5","short_pith_number":"pith:5X7IWD7C","schema_version":"1.0","canonical_sha256":"edfe8b0fe24ff2a8599bbd1b3901db977127826a3e2d736a7c4e0591df341c2e","source":{"kind":"arxiv","id":"2311.17041","version":4},"attestation_state":"computed","paper":{"title":"Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional Properties","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Fengyuan Hu, Joyce Chai, Keunwoo Peter Yu, Shane Storks, Zheyuan Zhang","submitted_at":"2023-11-28T18:53:06Z","abstract_excerpt":"A major reason behind the recent success of large language models (LLMs) is their \\textit{in-context learning} capability, which makes it possible to rapidly adapt them to downstream text-based tasks by prompting them with a small number of relevant demonstrations. While large vision-language models (VLMs) have recently been developed for tasks requiring both text and images, they largely lack in-context learning over visual information, especially in understanding and generating text about videos. In this work, we implement \\textbf{E}mergent \\textbf{I}n-context \\textbf{Le}arning on \\textbf{V}"},"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":"2311.17041","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T18:53:06Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"43a253e4562212f8b381021ab5356e20dc60f7cdb06e1d3a79dcb8b403ae20ab","abstract_canon_sha256":"a737c410cc5679c714ef2e3d5d29391da9c3962ee161c8e9666f888876c42e34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:07.423951Z","signature_b64":"AkWs7JENkIIS72UtyQyfAOdT4rboBKXwvJr7bNIJczxfYEdTtgaj/bX0Dkx3VzJOcHz7SQ5pXW3ErK3SeN9ZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edfe8b0fe24ff2a8599bbd1b3901db977127826a3e2d736a7c4e0591df341c2e","last_reissued_at":"2026-07-05T09:15:07.423501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:07.423501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional Properties","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Fengyuan Hu, Joyce Chai, Keunwoo Peter Yu, Shane Storks, Zheyuan Zhang","submitted_at":"2023-11-28T18:53:06Z","abstract_excerpt":"A major reason behind the recent success of large language models (LLMs) is their \\textit{in-context learning} capability, which makes it possible to rapidly adapt them to downstream text-based tasks by prompting them with a small number of relevant demonstrations. While large vision-language models (VLMs) have recently been developed for tasks requiring both text and images, they largely lack in-context learning over visual information, especially in understanding and generating text about videos. In this work, we implement \\textbf{E}mergent \\textbf{I}n-context \\textbf{Le}arning on \\textbf{V}"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17041","kind":"arxiv","version":4},"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/2311.17041/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":"2311.17041","created_at":"2026-07-05T09:15:07.423558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.17041v4","created_at":"2026-07-05T09:15:07.423558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17041","created_at":"2026-07-05T09:15:07.423558+00:00"},{"alias_kind":"pith_short_12","alias_value":"5X7IWD7CJ7ZK","created_at":"2026-07-05T09:15:07.423558+00:00"},{"alias_kind":"pith_short_16","alias_value":"5X7IWD7CJ7ZKQWM3","created_at":"2026-07-05T09:15:07.423558+00:00"},{"alias_kind":"pith_short_8","alias_value":"5X7IWD7C","created_at":"2026-07-05T09:15:07.423558+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10936","citing_title":"Personal Visual Context Learning in Large Multimodal Models","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05115","citing_title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","ref_index":263,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5X7IWD7CJ7ZKQWM3XUNTSAO3S5","json":"https://pith.science/pith/5X7IWD7CJ7ZKQWM3XUNTSAO3S5.json","graph_json":"https://pith.science/api/pith-number/5X7IWD7CJ7ZKQWM3XUNTSAO3S5/graph.json","events_json":"https://pith.science/api/pith-number/5X7IWD7CJ7ZKQWM3XUNTSAO3S5/events.json","paper":"https://pith.science/paper/5X7IWD7C"},"agent_actions":{"view_html":"https://pith.science/pith/5X7IWD7CJ7ZKQWM3XUNTSAO3S5","download_json":"https://pith.science/pith/5X7IWD7CJ7ZKQWM3XUNTSAO3S5.json","view_paper":"https://pith.science/paper/5X7IWD7C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.17041&json=true","fetch_graph":"https://pith.science/api/pith-number/5X7IWD7CJ7ZKQWM3XUNTSAO3S5/graph.json","fetch_events":"https://pith.science/api/pith-number/5X7IWD7CJ7ZKQWM3XUNTSAO3S5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5X7IWD7CJ7ZKQWM3XUNTSAO3S5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5X7IWD7CJ7ZKQWM3XUNTSAO3S5/action/storage_attestation","attest_author":"https://pith.science/pith/5X7IWD7CJ7ZKQWM3XUNTSAO3S5/action/author_attestation","sign_citation":"https://pith.science/pith/5X7IWD7CJ7ZKQWM3XUNTSAO3S5/action/citation_signature","submit_replication":"https://pith.science/pith/5X7IWD7CJ7ZKQWM3XUNTSAO3S5/action/replication_record"}},"created_at":"2026-07-05T09:15:07.423558+00:00","updated_at":"2026-07-05T09:15:07.423558+00:00"}