{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZHEFC2KKLLCJRGFE5VWC6DGJBI","short_pith_number":"pith:ZHEFC2KK","canonical_record":{"source":{"id":"2309.07915","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T17:59:17Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"0d54a22fc0362d121c62f3855c2b71883a62f96a2f7619dc48203ae8ac1f8621","abstract_canon_sha256":"6a3df6485f745010bd2ee241a1460167bddb9c4eafeccae28c72d31292127d49"},"schema_version":"1.0"},"canonical_sha256":"c9c851694a5ac49898a4ed6c2f0cc90a00c39484acf14c1c2b6336315bebe366","source":{"kind":"arxiv","id":"2309.07915","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.07915","created_at":"2026-07-05T07:58:23Z"},{"alias_kind":"arxiv_version","alias_value":"2309.07915v3","created_at":"2026-07-05T07:58:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07915","created_at":"2026-07-05T07:58:23Z"},{"alias_kind":"pith_short_12","alias_value":"ZHEFC2KKLLCJ","created_at":"2026-07-05T07:58:23Z"},{"alias_kind":"pith_short_16","alias_value":"ZHEFC2KKLLCJRGFE","created_at":"2026-07-05T07:58:23Z"},{"alias_kind":"pith_short_8","alias_value":"ZHEFC2KK","created_at":"2026-07-05T07:58:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZHEFC2KKLLCJRGFE5VWC6DGJBI","target":"record","payload":{"canonical_record":{"source":{"id":"2309.07915","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T17:59:17Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"0d54a22fc0362d121c62f3855c2b71883a62f96a2f7619dc48203ae8ac1f8621","abstract_canon_sha256":"6a3df6485f745010bd2ee241a1460167bddb9c4eafeccae28c72d31292127d49"},"schema_version":"1.0"},"canonical_sha256":"c9c851694a5ac49898a4ed6c2f0cc90a00c39484acf14c1c2b6336315bebe366","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:23.136649Z","signature_b64":"j1ls2hYvIjCtYendqhsrZJkLb9mGQ1W2m8uCtW5ghIu+VfVI1hyZ8Or7gOu3OKD5SkjXBKyRHyPbgR0jnm0NDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9c851694a5ac49898a4ed6c2f0cc90a00c39484acf14c1c2b6336315bebe366","last_reissued_at":"2026-07-05T07:58:23.136138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:23.136138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.07915","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:58:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uViOrFm3yxnr0DFoSakTsxy2dw5cruodC+SatnKnCcpB30qnOku7NYqmIkdgoRcmeaKHsEnFSlDaX3Xgb3ZOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:53:34.721073Z"},"content_sha256":"87d29e78790ca5f805a559816681be71eba36524c8e005da408a2207830d5f0e","schema_version":"1.0","event_id":"sha256:87d29e78790ca5f805a559816681be71eba36524c8e005da408a2207830d5f0e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZHEFC2KKLLCJRGFE5VWC6DGJBI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Baobao Chang, Haozhe Zhao, Kaikai An, Liang Chen, Sheng Wang, Shuzheng Si, Wenjuan Han, Xiaojian Ma, Zefan Cai, Zixuan Liu","submitted_at":"2023-09-14T17:59:17Z","abstract_excerpt":"Since the resurgence of deep learning, vision-language models (VLMs) enhanced by large language models (LLMs) have grown exponentially in popularity. However, while LLMs can utilize extensive background knowledge and task information with in-context learning, most VLMs still struggle with understanding complex multi-modal prompts with multiple images, making VLMs less effective in downstream vision-language tasks. In this paper, we address the limitation above by 1) introducing vision-language Model with Multi-Modal In-Context Learning(MMICL), a new approach to allow the VLM to deal with multi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07915","kind":"arxiv","version":3},"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/2309.07915/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":"2026-07-05T07:58:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b8P0QhDFl0qk+gRJUjbVC4e+0MUvAXdiTLMB+nk6vwFBjHLKMPtrO/VVZkyuIUPKHEZYEk7RxYosJt23UscuDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:53:34.722540Z"},"content_sha256":"49d20eaa7780cf1693e1e55423b6350e4af6f7f4ac90aaee98bcb89210d27b54","schema_version":"1.0","event_id":"sha256:49d20eaa7780cf1693e1e55423b6350e4af6f7f4ac90aaee98bcb89210d27b54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZHEFC2KKLLCJRGFE5VWC6DGJBI/bundle.json","state_url":"https://pith.science/pith/ZHEFC2KKLLCJRGFE5VWC6DGJBI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZHEFC2KKLLCJRGFE5VWC6DGJBI/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":"2026-08-04T16:53:34Z","links":{"resolver":"https://pith.science/pith/ZHEFC2KKLLCJRGFE5VWC6DGJBI","bundle":"https://pith.science/pith/ZHEFC2KKLLCJRGFE5VWC6DGJBI/bundle.json","state":"https://pith.science/pith/ZHEFC2KKLLCJRGFE5VWC6DGJBI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZHEFC2KKLLCJRGFE5VWC6DGJBI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZHEFC2KKLLCJRGFE5VWC6DGJBI","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":"6a3df6485f745010bd2ee241a1460167bddb9c4eafeccae28c72d31292127d49","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T17:59:17Z","title_canon_sha256":"0d54a22fc0362d121c62f3855c2b71883a62f96a2f7619dc48203ae8ac1f8621"},"schema_version":"1.0","source":{"id":"2309.07915","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.07915","created_at":"2026-07-05T07:58:23Z"},{"alias_kind":"arxiv_version","alias_value":"2309.07915v3","created_at":"2026-07-05T07:58:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07915","created_at":"2026-07-05T07:58:23Z"},{"alias_kind":"pith_short_12","alias_value":"ZHEFC2KKLLCJ","created_at":"2026-07-05T07:58:23Z"},{"alias_kind":"pith_short_16","alias_value":"ZHEFC2KKLLCJRGFE","created_at":"2026-07-05T07:58:23Z"},{"alias_kind":"pith_short_8","alias_value":"ZHEFC2KK","created_at":"2026-07-05T07:58:23Z"}],"graph_snapshots":[{"event_id":"sha256:49d20eaa7780cf1693e1e55423b6350e4af6f7f4ac90aaee98bcb89210d27b54","target":"graph","created_at":"2026-07-05T07:58:23Z","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/2309.07915/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Since the resurgence of deep learning, vision-language models (VLMs) enhanced by large language models (LLMs) have grown exponentially in popularity. However, while LLMs can utilize extensive background knowledge and task information with in-context learning, most VLMs still struggle with understanding complex multi-modal prompts with multiple images, making VLMs less effective in downstream vision-language tasks. In this paper, we address the limitation above by 1) introducing vision-language Model with Multi-Modal In-Context Learning(MMICL), a new approach to allow the VLM to deal with multi","authors_text":"Baobao Chang, Haozhe Zhao, Kaikai An, Liang Chen, Sheng Wang, Shuzheng Si, Wenjuan Han, Xiaojian Ma, Zefan Cai, Zixuan Liu","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T17:59:17Z","title":"MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07915","kind":"arxiv","version":3},"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":"sha256:87d29e78790ca5f805a559816681be71eba36524c8e005da408a2207830d5f0e","target":"record","created_at":"2026-07-05T07:58:23Z","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":"6a3df6485f745010bd2ee241a1460167bddb9c4eafeccae28c72d31292127d49","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T17:59:17Z","title_canon_sha256":"0d54a22fc0362d121c62f3855c2b71883a62f96a2f7619dc48203ae8ac1f8621"},"schema_version":"1.0","source":{"id":"2309.07915","kind":"arxiv","version":3}},"canonical_sha256":"c9c851694a5ac49898a4ed6c2f0cc90a00c39484acf14c1c2b6336315bebe366","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9c851694a5ac49898a4ed6c2f0cc90a00c39484acf14c1c2b6336315bebe366","first_computed_at":"2026-07-05T07:58:23.136138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:58:23.136138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j1ls2hYvIjCtYendqhsrZJkLb9mGQ1W2m8uCtW5ghIu+VfVI1hyZ8Or7gOu3OKD5SkjXBKyRHyPbgR0jnm0NDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:58:23.136649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.07915","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87d29e78790ca5f805a559816681be71eba36524c8e005da408a2207830d5f0e","sha256:49d20eaa7780cf1693e1e55423b6350e4af6f7f4ac90aaee98bcb89210d27b54"],"state_sha256":"b56eefca6283868301801235278c2d5ad2642bff4cc9eea4cec5a83594a0c142"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tq53EsheP8qyT65Hi+Vt9J7njC1xlUcbOiEaGvmQVxPoZeScgGu2gdii96nbwGrgGWb2CdC472IXfvg+MPBEBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:53:34.728108Z","bundle_sha256":"670ac4a53968a154709d98d8913fefee1cbfcd7df96c4f73c08afd28ebf6364e"}}