{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AG6DKBYVE7Z2QH6ZLLJTF3YH3C","short_pith_number":"pith:AG6DKBYV","canonical_record":{"source":{"id":"2403.12736","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T13:53:37Z","cross_cats_sorted":[],"title_canon_sha256":"23253ba5ff6768f646ebe39559ea3aae3d41c94acd7245e7d326ae3cbfe2b268","abstract_canon_sha256":"631dddd7e04d09b820214946ae88dc18ba8705b0f4198acb8418b3238c63f1fb"},"schema_version":"1.0"},"canonical_sha256":"01bc35071527f3a81fd95ad332ef07d89cf16f7284b076643adae2435eca0f2c","source":{"kind":"arxiv","id":"2403.12736","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12736","created_at":"2026-07-05T08:44:52Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12736v2","created_at":"2026-07-05T08:44:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12736","created_at":"2026-07-05T08:44:52Z"},{"alias_kind":"pith_short_12","alias_value":"AG6DKBYVE7Z2","created_at":"2026-07-05T08:44:52Z"},{"alias_kind":"pith_short_16","alias_value":"AG6DKBYVE7Z2QH6Z","created_at":"2026-07-05T08:44:52Z"},{"alias_kind":"pith_short_8","alias_value":"AG6DKBYV","created_at":"2026-07-05T08:44:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AG6DKBYVE7Z2QH6ZLLJTF3YH3C","target":"record","payload":{"canonical_record":{"source":{"id":"2403.12736","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T13:53:37Z","cross_cats_sorted":[],"title_canon_sha256":"23253ba5ff6768f646ebe39559ea3aae3d41c94acd7245e7d326ae3cbfe2b268","abstract_canon_sha256":"631dddd7e04d09b820214946ae88dc18ba8705b0f4198acb8418b3238c63f1fb"},"schema_version":"1.0"},"canonical_sha256":"01bc35071527f3a81fd95ad332ef07d89cf16f7284b076643adae2435eca0f2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:52.429765Z","signature_b64":"mPwORqBAvDgRXhcPbMTosjHdSyIlBRHFlJ+MR9ofTRnW2HtzNA1JUz2uDImfQKT7jeE0DgjHg7LX7q9WK4G7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01bc35071527f3a81fd95ad332ef07d89cf16f7284b076643adae2435eca0f2c","last_reissued_at":"2026-07-05T08:44:52.429326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:52.429326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.12736","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:44:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y3sWt5oVVD1jZXzky7wK19Ue5MfE4lBBGLltiQbLV+fppK+2Vc29lG+zg+cFV5KKJIbHmBM4X09QDLjU9N7KDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:49:44.889326Z"},"content_sha256":"c6fbc335a4cacc9f576ae3472c366543d09ea296c0266364f888a652e7effc1d","schema_version":"1.0","event_id":"sha256:c6fbc335a4cacc9f576ae3472c366543d09ea296c0266364f888a652e7effc1d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AG6DKBYVE7Z2QH6ZLLJTF3YH3C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Multimodal In-Context Learning for Vision & Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amit Alfassy, Assaf Arbelle, Leonid Karlinsky, M. Jehanzeb Mirza, Shaked Perek, Shimon Ullman, Sivan Doveh, Wei Lin","submitted_at":"2024-03-19T13:53:37Z","abstract_excerpt":"State-of-the-art Vision-Language Models (VLMs) ground the vision and the language modality primarily via projecting the vision tokens from the encoder to language-like tokens, which are directly fed to the Large Language Model (LLM) decoder. While these models have shown unprecedented performance in many downstream zero-shot tasks (eg image captioning, question answers, etc), still little emphasis has been put on transferring one of the core LLM capability of In-Context Learning (ICL). ICL is the ability of a model to reason about a downstream task with a few examples demonstrations embedded i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12736","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/2403.12736/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":"2026-07-05T08:44:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QlrOGbqt5SqbH5wj+EqKHyb+xzdlqhlQDGiSlIEcfbsKoLTnr0qzMrh6OH639Nv/QvvZqVVWEBgfpZrnXN4hCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:49:44.889941Z"},"content_sha256":"96432b2a8f2d4e97ea86547c1ce94e9e3fe2dddb59f009334f39ddbbd02f15f0","schema_version":"1.0","event_id":"sha256:96432b2a8f2d4e97ea86547c1ce94e9e3fe2dddb59f009334f39ddbbd02f15f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AG6DKBYVE7Z2QH6ZLLJTF3YH3C/bundle.json","state_url":"https://pith.science/pith/AG6DKBYVE7Z2QH6ZLLJTF3YH3C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AG6DKBYVE7Z2QH6ZLLJTF3YH3C/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":"2026-08-09T05:49:44Z","links":{"resolver":"https://pith.science/pith/AG6DKBYVE7Z2QH6ZLLJTF3YH3C","bundle":"https://pith.science/pith/AG6DKBYVE7Z2QH6ZLLJTF3YH3C/bundle.json","state":"https://pith.science/pith/AG6DKBYVE7Z2QH6ZLLJTF3YH3C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AG6DKBYVE7Z2QH6ZLLJTF3YH3C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AG6DKBYVE7Z2QH6ZLLJTF3YH3C","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":"631dddd7e04d09b820214946ae88dc18ba8705b0f4198acb8418b3238c63f1fb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T13:53:37Z","title_canon_sha256":"23253ba5ff6768f646ebe39559ea3aae3d41c94acd7245e7d326ae3cbfe2b268"},"schema_version":"1.0","source":{"id":"2403.12736","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12736","created_at":"2026-07-05T08:44:52Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12736v2","created_at":"2026-07-05T08:44:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12736","created_at":"2026-07-05T08:44:52Z"},{"alias_kind":"pith_short_12","alias_value":"AG6DKBYVE7Z2","created_at":"2026-07-05T08:44:52Z"},{"alias_kind":"pith_short_16","alias_value":"AG6DKBYVE7Z2QH6Z","created_at":"2026-07-05T08:44:52Z"},{"alias_kind":"pith_short_8","alias_value":"AG6DKBYV","created_at":"2026-07-05T08:44:52Z"}],"graph_snapshots":[{"event_id":"sha256:96432b2a8f2d4e97ea86547c1ce94e9e3fe2dddb59f009334f39ddbbd02f15f0","target":"graph","created_at":"2026-07-05T08:44:52Z","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/2403.12736/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art Vision-Language Models (VLMs) ground the vision and the language modality primarily via projecting the vision tokens from the encoder to language-like tokens, which are directly fed to the Large Language Model (LLM) decoder. While these models have shown unprecedented performance in many downstream zero-shot tasks (eg image captioning, question answers, etc), still little emphasis has been put on transferring one of the core LLM capability of In-Context Learning (ICL). ICL is the ability of a model to reason about a downstream task with a few examples demonstrations embedded i","authors_text":"Amit Alfassy, Assaf Arbelle, Leonid Karlinsky, M. Jehanzeb Mirza, Shaked Perek, Shimon Ullman, Sivan Doveh, Wei Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T13:53:37Z","title":"Towards Multimodal In-Context Learning for Vision & Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12736","kind":"arxiv","version":2},"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:c6fbc335a4cacc9f576ae3472c366543d09ea296c0266364f888a652e7effc1d","target":"record","created_at":"2026-07-05T08:44:52Z","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":"631dddd7e04d09b820214946ae88dc18ba8705b0f4198acb8418b3238c63f1fb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T13:53:37Z","title_canon_sha256":"23253ba5ff6768f646ebe39559ea3aae3d41c94acd7245e7d326ae3cbfe2b268"},"schema_version":"1.0","source":{"id":"2403.12736","kind":"arxiv","version":2}},"canonical_sha256":"01bc35071527f3a81fd95ad332ef07d89cf16f7284b076643adae2435eca0f2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01bc35071527f3a81fd95ad332ef07d89cf16f7284b076643adae2435eca0f2c","first_computed_at":"2026-07-05T08:44:52.429326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:52.429326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mPwORqBAvDgRXhcPbMTosjHdSyIlBRHFlJ+MR9ofTRnW2HtzNA1JUz2uDImfQKT7jeE0DgjHg7LX7q9WK4G7AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:52.429765Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.12736","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6fbc335a4cacc9f576ae3472c366543d09ea296c0266364f888a652e7effc1d","sha256:96432b2a8f2d4e97ea86547c1ce94e9e3fe2dddb59f009334f39ddbbd02f15f0"],"state_sha256":"86305b788c0908eed7006e9844a5c5faa642491f243024e0560b2b55fa31fe23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"us9TulSnOZeQ5z/N7islt0wnUdBogViU3NEG1RqgDyThdbtqCBPtdWYNxHlAgsmx+6MKILq8wVCB4Cn9dv9+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:49:44.893984Z","bundle_sha256":"7b8582b4213fcf9b04b45a59be52061b88e7be422bc7755a30a4db8775480417"}}