{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3EHBPDGVJM6Q44XEFC3MH4LEYQ","short_pith_number":"pith:3EHBPDGV","canonical_record":{"source":{"id":"2405.17815","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T04:23:00Z","cross_cats_sorted":[],"title_canon_sha256":"9841876e667f6bf7ba6d5a03dd634aedbfeff34f429a5980c886cf9f66dccfaa","abstract_canon_sha256":"83a1f697475e236f4108b7e8a36d3f5f9f0365f10007f2b6793a3a3852bc4c51"},"schema_version":"1.0"},"canonical_sha256":"d90e178cd54b3d0e72e428b6c3f164c421896d3c7a8e492bb219aab6183da362","source":{"kind":"arxiv","id":"2405.17815","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17815","created_at":"2026-07-05T09:30:15Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17815v2","created_at":"2026-07-05T09:30:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17815","created_at":"2026-07-05T09:30:15Z"},{"alias_kind":"pith_short_12","alias_value":"3EHBPDGVJM6Q","created_at":"2026-07-05T09:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"3EHBPDGVJM6Q44XE","created_at":"2026-07-05T09:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"3EHBPDGV","created_at":"2026-07-05T09:30:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3EHBPDGVJM6Q44XEFC3MH4LEYQ","target":"record","payload":{"canonical_record":{"source":{"id":"2405.17815","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T04:23:00Z","cross_cats_sorted":[],"title_canon_sha256":"9841876e667f6bf7ba6d5a03dd634aedbfeff34f429a5980c886cf9f66dccfaa","abstract_canon_sha256":"83a1f697475e236f4108b7e8a36d3f5f9f0365f10007f2b6793a3a3852bc4c51"},"schema_version":"1.0"},"canonical_sha256":"d90e178cd54b3d0e72e428b6c3f164c421896d3c7a8e492bb219aab6183da362","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:15.133021Z","signature_b64":"b7GeqIiLEtCEXpl+tISERfIO3AWbRkk7nLzM2oUfNqC5KT9EAo67wPUOeHEpHnFSlHO/YD8E1JdVY6/4JbT0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d90e178cd54b3d0e72e428b6c3f164c421896d3c7a8e492bb219aab6183da362","last_reissued_at":"2026-07-05T09:30:15.132540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:15.132540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.17815","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":"2026-07-05T09:30:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8d5JNbiCFTBe+maR7Q02t73iajlX4DbmHQ2FsvJrvlF6leJIYoWnrfYQ5Gjv4qwx1A2CmI1TNOy7SaMAfFofCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T19:26:18.004544Z"},"content_sha256":"f9153a53aa71e430dcada76eae9d7cab1d423d052fdb881bf9f91f1a25f63c85","schema_version":"1.0","event_id":"sha256:f9153a53aa71e430dcada76eae9d7cab1d423d052fdb881bf9f91f1a25f63c85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3EHBPDGVJM6Q44XEFC3MH4LEYQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haogeng Liu, Hongxia Yang, Huaibo Huang, Quanzeng You, Ran He, Xiaotian Han, Yongfei Liu","submitted_at":"2024-05-28T04:23:00Z","abstract_excerpt":"In the realm of Multimodal Large Language Models (MLLMs), vision-language connector plays a crucial role to link the pre-trained vision encoders with Large Language Models (LLMs). Despite its importance, the vision-language connector has been relatively less explored. In this study, we aim to propose a strong vision-language connector that enables MLLMs to achieve high accuracy while maintain low computation cost. We first reveal the existence of the visual anchors in Vision Transformer and propose a cost-effective search algorithm to extract them. Building on these findings, we introduce the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17815","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/2405.17815/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":"2026-07-05T09:30:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wnswgipuCZJ/51m7vVpLxrFyAuVroUk+FEkAstTG7qKxHe0CNPRs44NpPUuhDiSkL4c0A+5PWrC1SYxWtdo3CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T19:26:18.004921Z"},"content_sha256":"43138d4c13d3c3ea621efceb5b1c73719c262d55077fea09e4bdbe708fe8e03a","schema_version":"1.0","event_id":"sha256:43138d4c13d3c3ea621efceb5b1c73719c262d55077fea09e4bdbe708fe8e03a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3EHBPDGVJM6Q44XEFC3MH4LEYQ/bundle.json","state_url":"https://pith.science/pith/3EHBPDGVJM6Q44XEFC3MH4LEYQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3EHBPDGVJM6Q44XEFC3MH4LEYQ/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":"2026-07-14T19:26:18Z","links":{"resolver":"https://pith.science/pith/3EHBPDGVJM6Q44XEFC3MH4LEYQ","bundle":"https://pith.science/pith/3EHBPDGVJM6Q44XEFC3MH4LEYQ/bundle.json","state":"https://pith.science/pith/3EHBPDGVJM6Q44XEFC3MH4LEYQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3EHBPDGVJM6Q44XEFC3MH4LEYQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3EHBPDGVJM6Q44XEFC3MH4LEYQ","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":"83a1f697475e236f4108b7e8a36d3f5f9f0365f10007f2b6793a3a3852bc4c51","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T04:23:00Z","title_canon_sha256":"9841876e667f6bf7ba6d5a03dd634aedbfeff34f429a5980c886cf9f66dccfaa"},"schema_version":"1.0","source":{"id":"2405.17815","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17815","created_at":"2026-07-05T09:30:15Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17815v2","created_at":"2026-07-05T09:30:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17815","created_at":"2026-07-05T09:30:15Z"},{"alias_kind":"pith_short_12","alias_value":"3EHBPDGVJM6Q","created_at":"2026-07-05T09:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"3EHBPDGVJM6Q44XE","created_at":"2026-07-05T09:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"3EHBPDGV","created_at":"2026-07-05T09:30:15Z"}],"graph_snapshots":[{"event_id":"sha256:43138d4c13d3c3ea621efceb5b1c73719c262d55077fea09e4bdbe708fe8e03a","target":"graph","created_at":"2026-07-05T09:30:15Z","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/2405.17815/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the realm of Multimodal Large Language Models (MLLMs), vision-language connector plays a crucial role to link the pre-trained vision encoders with Large Language Models (LLMs). Despite its importance, the vision-language connector has been relatively less explored. In this study, we aim to propose a strong vision-language connector that enables MLLMs to achieve high accuracy while maintain low computation cost. We first reveal the existence of the visual anchors in Vision Transformer and propose a cost-effective search algorithm to extract them. Building on these findings, we introduce the ","authors_text":"Haogeng Liu, Hongxia Yang, Huaibo Huang, Quanzeng You, Ran He, Xiaotian Han, Yongfei Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T04:23:00Z","title":"Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17815","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:f9153a53aa71e430dcada76eae9d7cab1d423d052fdb881bf9f91f1a25f63c85","target":"record","created_at":"2026-07-05T09:30:15Z","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":"83a1f697475e236f4108b7e8a36d3f5f9f0365f10007f2b6793a3a3852bc4c51","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T04:23:00Z","title_canon_sha256":"9841876e667f6bf7ba6d5a03dd634aedbfeff34f429a5980c886cf9f66dccfaa"},"schema_version":"1.0","source":{"id":"2405.17815","kind":"arxiv","version":2}},"canonical_sha256":"d90e178cd54b3d0e72e428b6c3f164c421896d3c7a8e492bb219aab6183da362","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d90e178cd54b3d0e72e428b6c3f164c421896d3c7a8e492bb219aab6183da362","first_computed_at":"2026-07-05T09:30:15.132540Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:15.132540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b7GeqIiLEtCEXpl+tISERfIO3AWbRkk7nLzM2oUfNqC5KT9EAo67wPUOeHEpHnFSlHO/YD8E1JdVY6/4JbT0Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:15.133021Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17815","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9153a53aa71e430dcada76eae9d7cab1d423d052fdb881bf9f91f1a25f63c85","sha256:43138d4c13d3c3ea621efceb5b1c73719c262d55077fea09e4bdbe708fe8e03a"],"state_sha256":"b16ac3d75c035c77b04717d8c1ff7a12647dd0d79c1e6338e8d4a92242dca056"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nndWu/Du3ed7PJFH8fL5C7jx5J0BsPoccCZV1PoHTyrkLz+fTDzYjAQBv69pxmPJfhNmYH0u+oP9j9NwdMbtDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T19:26:18.007057Z","bundle_sha256":"c7ba94c3f53df3d698633251136827a310029d488717c51729b001a2bb46daa5"}}