{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WDWBR5JINY5ABDDD4PQ2SUMBZK","short_pith_number":"pith:WDWBR5JI","canonical_record":{"source":{"id":"2301.13670","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-31T14:40:05Z","cross_cats_sorted":[],"title_canon_sha256":"9c615e0590bc7451895e4d69c5937f6430e08d618b567944e431a89cd5c1d258","abstract_canon_sha256":"1a2d58244e1be2e7db909c2d72d7cab58119247aaef90c2897c4da36aa33eb6f"},"schema_version":"1.0"},"canonical_sha256":"b0ec18f5286e3a008c63e3e1a95181ca81bab994f4daafb8079eb733c2b44fc6","source":{"kind":"arxiv","id":"2301.13670","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.13670","created_at":"2026-07-05T05:37:57Z"},{"alias_kind":"arxiv_version","alias_value":"2301.13670v2","created_at":"2026-07-05T05:37:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13670","created_at":"2026-07-05T05:37:57Z"},{"alias_kind":"pith_short_12","alias_value":"WDWBR5JINY5A","created_at":"2026-07-05T05:37:57Z"},{"alias_kind":"pith_short_16","alias_value":"WDWBR5JINY5ABDDD","created_at":"2026-07-05T05:37:57Z"},{"alias_kind":"pith_short_8","alias_value":"WDWBR5JI","created_at":"2026-07-05T05:37:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WDWBR5JINY5ABDDD4PQ2SUMBZK","target":"record","payload":{"canonical_record":{"source":{"id":"2301.13670","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-31T14:40:05Z","cross_cats_sorted":[],"title_canon_sha256":"9c615e0590bc7451895e4d69c5937f6430e08d618b567944e431a89cd5c1d258","abstract_canon_sha256":"1a2d58244e1be2e7db909c2d72d7cab58119247aaef90c2897c4da36aa33eb6f"},"schema_version":"1.0"},"canonical_sha256":"b0ec18f5286e3a008c63e3e1a95181ca81bab994f4daafb8079eb733c2b44fc6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:57.739564Z","signature_b64":"nCABvO1lU/Tmnt0HVhUaCytZfBADI6YsBanOkg1Vi7Sf/yonHXdQgTl/Xl1aLpiadwdH93owmlFj6xH5tmu5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0ec18f5286e3a008c63e3e1a95181ca81bab994f4daafb8079eb733c2b44fc6","last_reissued_at":"2026-07-05T05:37:57.739149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:57.739149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.13670","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":"2026-07-05T05:37:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IxEGuiQtYNvT3UZ3FaiAq23rWcw59Hlb1J8QrB39njSl0KpBipt8QX2Auyk4Qn11/JEopXcqoXZ6L+EGkdmXAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T07:10:21.306467Z"},"content_sha256":"b3d95757f089ee7cec7a5c6f5b26a097ec2b0158c2a16ac5ea72bc03a79e89e1","schema_version":"1.0","event_id":"sha256:b3d95757f089ee7cec7a5c6f5b26a097ec2b0158c2a16ac5ea72bc03a79e89e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WDWBR5JINY5ABDDD4PQ2SUMBZK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Makes Good Examples for Visual In-Context Learning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaiyang Zhou, Yuanhan Zhang, Ziwei Liu","submitted_at":"2023-01-31T14:40:05Z","abstract_excerpt":"Large-scale models trained on broad data have recently become the mainstream architecture in computer vision due to their strong generalization performance. In this paper, the main focus is on an emergent ability in large vision models, known as in-context learning, which allows inference on unseen tasks by conditioning on in-context examples (a.k.a.~prompt) without updating the model parameters. This concept has been well-known in natural language processing but has only been studied very recently for large vision models. We for the first time provide a comprehensive investigation on the impa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13670","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/2301.13670/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":"2026-07-05T05:37:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G2sTAARe8nIyRM42ol0khQsaZ2vBGkDNLDkWJz4R/YeuxKXNS9+7kqc4Hu7J6lS3SOtdfNKkl6F11makMdsIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T07:10:21.306962Z"},"content_sha256":"7e565cca274656c694587150d6ee2693bd0bdcd45af06173468344656b63c642","schema_version":"1.0","event_id":"sha256:7e565cca274656c694587150d6ee2693bd0bdcd45af06173468344656b63c642"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WDWBR5JINY5ABDDD4PQ2SUMBZK/bundle.json","state_url":"https://pith.science/pith/WDWBR5JINY5ABDDD4PQ2SUMBZK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WDWBR5JINY5ABDDD4PQ2SUMBZK/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":"2026-08-13T07:10:21Z","links":{"resolver":"https://pith.science/pith/WDWBR5JINY5ABDDD4PQ2SUMBZK","bundle":"https://pith.science/pith/WDWBR5JINY5ABDDD4PQ2SUMBZK/bundle.json","state":"https://pith.science/pith/WDWBR5JINY5ABDDD4PQ2SUMBZK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WDWBR5JINY5ABDDD4PQ2SUMBZK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WDWBR5JINY5ABDDD4PQ2SUMBZK","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":"1a2d58244e1be2e7db909c2d72d7cab58119247aaef90c2897c4da36aa33eb6f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-31T14:40:05Z","title_canon_sha256":"9c615e0590bc7451895e4d69c5937f6430e08d618b567944e431a89cd5c1d258"},"schema_version":"1.0","source":{"id":"2301.13670","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.13670","created_at":"2026-07-05T05:37:57Z"},{"alias_kind":"arxiv_version","alias_value":"2301.13670v2","created_at":"2026-07-05T05:37:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13670","created_at":"2026-07-05T05:37:57Z"},{"alias_kind":"pith_short_12","alias_value":"WDWBR5JINY5A","created_at":"2026-07-05T05:37:57Z"},{"alias_kind":"pith_short_16","alias_value":"WDWBR5JINY5ABDDD","created_at":"2026-07-05T05:37:57Z"},{"alias_kind":"pith_short_8","alias_value":"WDWBR5JI","created_at":"2026-07-05T05:37:57Z"}],"graph_snapshots":[{"event_id":"sha256:7e565cca274656c694587150d6ee2693bd0bdcd45af06173468344656b63c642","target":"graph","created_at":"2026-07-05T05:37:57Z","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/2301.13670/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale models trained on broad data have recently become the mainstream architecture in computer vision due to their strong generalization performance. In this paper, the main focus is on an emergent ability in large vision models, known as in-context learning, which allows inference on unseen tasks by conditioning on in-context examples (a.k.a.~prompt) without updating the model parameters. This concept has been well-known in natural language processing but has only been studied very recently for large vision models. We for the first time provide a comprehensive investigation on the impa","authors_text":"Kaiyang Zhou, Yuanhan Zhang, Ziwei Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-31T14:40:05Z","title":"What Makes Good Examples for Visual In-Context Learning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13670","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:b3d95757f089ee7cec7a5c6f5b26a097ec2b0158c2a16ac5ea72bc03a79e89e1","target":"record","created_at":"2026-07-05T05:37:57Z","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":"1a2d58244e1be2e7db909c2d72d7cab58119247aaef90c2897c4da36aa33eb6f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-31T14:40:05Z","title_canon_sha256":"9c615e0590bc7451895e4d69c5937f6430e08d618b567944e431a89cd5c1d258"},"schema_version":"1.0","source":{"id":"2301.13670","kind":"arxiv","version":2}},"canonical_sha256":"b0ec18f5286e3a008c63e3e1a95181ca81bab994f4daafb8079eb733c2b44fc6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0ec18f5286e3a008c63e3e1a95181ca81bab994f4daafb8079eb733c2b44fc6","first_computed_at":"2026-07-05T05:37:57.739149Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:37:57.739149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nCABvO1lU/Tmnt0HVhUaCytZfBADI6YsBanOkg1Vi7Sf/yonHXdQgTl/Xl1aLpiadwdH93owmlFj6xH5tmu5CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:37:57.739564Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.13670","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3d95757f089ee7cec7a5c6f5b26a097ec2b0158c2a16ac5ea72bc03a79e89e1","sha256:7e565cca274656c694587150d6ee2693bd0bdcd45af06173468344656b63c642"],"state_sha256":"54fdffaca864814fcba176970f7b3317a45450cd70d63b93af81ef27616ef456"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o/cL4wRdVDwTc/5+vP59Rfr04J73BR5/pD7GxWp4gkp+IPX7BvShByj6RZZF/i9ATt/MdP0zjoxwFFWXa+hoAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T07:10:21.312152Z","bundle_sha256":"385ea46e5d3ff4c6ef59a6e5cd8008ff958f20b3712d5b330a2426894d7d035c"}}