{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JIVCNPXZJI7WQMRCDSQXWYKXWI","short_pith_number":"pith:JIVCNPXZ","canonical_record":{"source":{"id":"2403.13164","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-19T21:31:56Z","cross_cats_sorted":[],"title_canon_sha256":"29a9c370a7f025d77a01a2cb95baa79599c734a8ca9462d1ba930313c9eed7e9","abstract_canon_sha256":"fb58bed11b14b6149f5f71bbd1ce22b966b10498e53337f9af236db3a87237a9"},"schema_version":"1.0"},"canonical_sha256":"4a2a26bef94a3f6832221ca17b6157b231149d123cb3a264cc393cd500dba655","source":{"kind":"arxiv","id":"2403.13164","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.13164","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"arxiv_version","alias_value":"2403.13164v4","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13164","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"pith_short_12","alias_value":"JIVCNPXZJI7W","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"pith_short_16","alias_value":"JIVCNPXZJI7WQMRC","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"pith_short_8","alias_value":"JIVCNPXZ","created_at":"2026-07-05T10:42:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JIVCNPXZJI7WQMRCDSQXWYKXWI","target":"record","payload":{"canonical_record":{"source":{"id":"2403.13164","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-19T21:31:56Z","cross_cats_sorted":[],"title_canon_sha256":"29a9c370a7f025d77a01a2cb95baa79599c734a8ca9462d1ba930313c9eed7e9","abstract_canon_sha256":"fb58bed11b14b6149f5f71bbd1ce22b966b10498e53337f9af236db3a87237a9"},"schema_version":"1.0"},"canonical_sha256":"4a2a26bef94a3f6832221ca17b6157b231149d123cb3a264cc393cd500dba655","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:11.147052Z","signature_b64":"rX1x0qjPvJfnF6gmrCQuGTPKD+aWtm8Ns7MBJLj2/mf2NVSTy6It12GYJAatDVSGcUUzP5+xfNPY4f2IzS5IAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a2a26bef94a3f6832221ca17b6157b231149d123cb3a264cc393cd500dba655","last_reissued_at":"2026-07-05T10:42:11.146640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:11.146640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.13164","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:42:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x8I/VY25ba3SWZ4uSjSzaSFyE9pBMld8f4OjxGkyIkkRMKGtAXDbj34mTDnPCbhn1GjIWTfgbBZds12Vy3C7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:19:09.752035Z"},"content_sha256":"053dc5754cb0fe79b60c098f5adce1c837fd6d134b87a407be76b601fd9cbed8","schema_version":"1.0","event_id":"sha256:053dc5754cb0fe79b60c098f5adce1c837fd6d134b87a407be76b601fd9cbed8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JIVCNPXZJI7WQMRCDSQXWYKXWI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ondrej Bohdal, Timothy Hospedales, Yongshuo Zong","submitted_at":"2024-03-19T21:31:56Z","abstract_excerpt":"Large language models (LLMs) famously exhibit emergent in-context learning (ICL) -- the ability to rapidly adapt to new tasks using few-shot examples provided as a prompt, without updating the model's weights. Built on top of LLMs, vision large language models (VLLMs) have advanced significantly in areas such as recognition, reasoning, and grounding. However, investigations into \\emph{multimodal ICL} have predominantly focused on few-shot visual question answering (VQA), and image captioning, which we will show neither exploit the strengths of ICL, nor test its limitations. The broader capabil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13164","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/2403.13164/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:42:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jpt6qgT1lmSIsPRT2djnmdw/zYLxU2qdVyPLxnbZ/TZnK3JqD/ytJvIYmSe0q/bmv9Ir8QEqHWK7Bk27Ti2XCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:19:09.752528Z"},"content_sha256":"42b61c3d896eea0a9015a213d851f01f90b9477077eddcb5018555f1d5b5d28b","schema_version":"1.0","event_id":"sha256:42b61c3d896eea0a9015a213d851f01f90b9477077eddcb5018555f1d5b5d28b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JIVCNPXZJI7WQMRCDSQXWYKXWI/bundle.json","state_url":"https://pith.science/pith/JIVCNPXZJI7WQMRCDSQXWYKXWI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JIVCNPXZJI7WQMRCDSQXWYKXWI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T01:19:09Z","links":{"resolver":"https://pith.science/pith/JIVCNPXZJI7WQMRCDSQXWYKXWI","bundle":"https://pith.science/pith/JIVCNPXZJI7WQMRCDSQXWYKXWI/bundle.json","state":"https://pith.science/pith/JIVCNPXZJI7WQMRCDSQXWYKXWI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JIVCNPXZJI7WQMRCDSQXWYKXWI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JIVCNPXZJI7WQMRCDSQXWYKXWI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fb58bed11b14b6149f5f71bbd1ce22b966b10498e53337f9af236db3a87237a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-19T21:31:56Z","title_canon_sha256":"29a9c370a7f025d77a01a2cb95baa79599c734a8ca9462d1ba930313c9eed7e9"},"schema_version":"1.0","source":{"id":"2403.13164","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.13164","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"arxiv_version","alias_value":"2403.13164v4","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13164","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"pith_short_12","alias_value":"JIVCNPXZJI7W","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"pith_short_16","alias_value":"JIVCNPXZJI7WQMRC","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"pith_short_8","alias_value":"JIVCNPXZ","created_at":"2026-07-05T10:42:11Z"}],"graph_snapshots":[{"event_id":"sha256:42b61c3d896eea0a9015a213d851f01f90b9477077eddcb5018555f1d5b5d28b","target":"graph","created_at":"2026-07-05T10:42:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.13164/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) famously exhibit emergent in-context learning (ICL) -- the ability to rapidly adapt to new tasks using few-shot examples provided as a prompt, without updating the model's weights. Built on top of LLMs, vision large language models (VLLMs) have advanced significantly in areas such as recognition, reasoning, and grounding. However, investigations into \\emph{multimodal ICL} have predominantly focused on few-shot visual question answering (VQA), and image captioning, which we will show neither exploit the strengths of ICL, nor test its limitations. The broader capabil","authors_text":"Ondrej Bohdal, Timothy Hospedales, Yongshuo Zong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-19T21:31:56Z","title":"VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13164","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:053dc5754cb0fe79b60c098f5adce1c837fd6d134b87a407be76b601fd9cbed8","target":"record","created_at":"2026-07-05T10:42:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fb58bed11b14b6149f5f71bbd1ce22b966b10498e53337f9af236db3a87237a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-19T21:31:56Z","title_canon_sha256":"29a9c370a7f025d77a01a2cb95baa79599c734a8ca9462d1ba930313c9eed7e9"},"schema_version":"1.0","source":{"id":"2403.13164","kind":"arxiv","version":4}},"canonical_sha256":"4a2a26bef94a3f6832221ca17b6157b231149d123cb3a264cc393cd500dba655","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a2a26bef94a3f6832221ca17b6157b231149d123cb3a264cc393cd500dba655","first_computed_at":"2026-07-05T10:42:11.146640Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:42:11.146640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rX1x0qjPvJfnF6gmrCQuGTPKD+aWtm8Ns7MBJLj2/mf2NVSTy6It12GYJAatDVSGcUUzP5+xfNPY4f2IzS5IAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:42:11.147052Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.13164","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:053dc5754cb0fe79b60c098f5adce1c837fd6d134b87a407be76b601fd9cbed8","sha256:42b61c3d896eea0a9015a213d851f01f90b9477077eddcb5018555f1d5b5d28b"],"state_sha256":"61ca97fbb9cbca1817ccc7757ddced06a07db1df9739bf2f7cbe23f106f4d6c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TzkrMraxXt9o/iKU1xHFWdHtFxuMwjFR44OOkt2DbRJyq7CYEA9cPv/OxVBRUVP71GA1o53om2indmqcDlh9AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:19:09.756058Z","bundle_sha256":"16a76c701d0f0dcd5bdbbf31c73468322c3346b3a097b92b81c28bc359a008cb"}}