{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GFCA7FECJ4K5LHAF4BPRD4TATC","short_pith_number":"pith:GFCA7FEC","canonical_record":{"source":{"id":"2412.01289","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T09:02:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b5a5ecef9b3642cf9f8668dbcf0e86db2effe0ec46e7a88e27a29af47ef405d6","abstract_canon_sha256":"3a1f06cbf13b6e8803781c0e46b8553a58c8f85f335ae5dd77e9785a1716c8ac"},"schema_version":"1.0"},"canonical_sha256":"31440f94824f15d59c05e05f11f260988466f103214c80e05512f485a04b94e5","source":{"kind":"arxiv","id":"2412.01289","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01289","created_at":"2026-07-05T09:44:17Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01289v2","created_at":"2026-07-05T09:44:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01289","created_at":"2026-07-05T09:44:17Z"},{"alias_kind":"pith_short_12","alias_value":"GFCA7FECJ4K5","created_at":"2026-07-05T09:44:17Z"},{"alias_kind":"pith_short_16","alias_value":"GFCA7FECJ4K5LHAF","created_at":"2026-07-05T09:44:17Z"},{"alias_kind":"pith_short_8","alias_value":"GFCA7FEC","created_at":"2026-07-05T09:44:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GFCA7FECJ4K5LHAF4BPRD4TATC","target":"record","payload":{"canonical_record":{"source":{"id":"2412.01289","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T09:02:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b5a5ecef9b3642cf9f8668dbcf0e86db2effe0ec46e7a88e27a29af47ef405d6","abstract_canon_sha256":"3a1f06cbf13b6e8803781c0e46b8553a58c8f85f335ae5dd77e9785a1716c8ac"},"schema_version":"1.0"},"canonical_sha256":"31440f94824f15d59c05e05f11f260988466f103214c80e05512f485a04b94e5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:17.711688Z","signature_b64":"KUDUxdPTPse74Ct4wqOwH1Shsx/J/YJVEl/n72kWxRjt24XQ/5hOxy4o00n8kDhyNIUvPCj2P8Nh/0PqsJPABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31440f94824f15d59c05e05f11f260988466f103214c80e05512f485a04b94e5","last_reissued_at":"2026-07-05T09:44:17.711209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:17.711209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.01289","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":"2026-07-05T09:44:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0qQDigbafKtqC28vv2vHpyLjmjNaI7scg8iU/TyqANLLtlDbAcjENov9aP5IKxiVsYSdfrp6HhpTxLVmSZT+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:27:19.038663Z"},"content_sha256":"3e49a4496530ad13eb56478eb2506973a3580e4f362554f871e5b59d9a7c7e71","schema_version":"1.0","event_id":"sha256:3e49a4496530ad13eb56478eb2506973a3580e4f362554f871e5b59d9a7c7e71"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GFCA7FECJ4K5LHAF4BPRD4TATC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Perception Capabilities of Multimodal LLMs with Training-Free Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bohan Zhuang, Jinwu Hu, Mingkui Tan, Yufeng Wang, Zeshuai Deng, Zhuokun Chen","submitted_at":"2024-12-02T09:02:28Z","abstract_excerpt":"Multimodal LLMs (MLLMs) equip language models with visual capabilities by aligning vision encoders with language models. Existing methods to enhance the visual perception of MLLMs often involve designing more powerful vision encoders, which requires exploring a vast design space and re-aligning each potential encoder with the language model, resulting in prohibitively high training costs. In this paper, we introduce VisionFuse, a novel integration framework that efficiently utilizes multiple vision encoders from off-the-shelf MLLMs to enhance visual perception without requiring additional trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01289","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/2412.01289/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":"2026-07-05T09:44:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"swzgc90up8D88wLBzFRrSrRSqwhsOCef6odK1asxJcANF48IFi/AP4eXmIshgJ0rgfDAThOh8P18IQNtSSDXBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:27:19.039557Z"},"content_sha256":"21766b5274bbe7e20704285c837db37cb8b29343447085c39dbf6b6af5619a8f","schema_version":"1.0","event_id":"sha256:21766b5274bbe7e20704285c837db37cb8b29343447085c39dbf6b6af5619a8f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GFCA7FECJ4K5LHAF4BPRD4TATC/bundle.json","state_url":"https://pith.science/pith/GFCA7FECJ4K5LHAF4BPRD4TATC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GFCA7FECJ4K5LHAF4BPRD4TATC/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":"2026-08-14T07:27:19Z","links":{"resolver":"https://pith.science/pith/GFCA7FECJ4K5LHAF4BPRD4TATC","bundle":"https://pith.science/pith/GFCA7FECJ4K5LHAF4BPRD4TATC/bundle.json","state":"https://pith.science/pith/GFCA7FECJ4K5LHAF4BPRD4TATC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GFCA7FECJ4K5LHAF4BPRD4TATC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GFCA7FECJ4K5LHAF4BPRD4TATC","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":"3a1f06cbf13b6e8803781c0e46b8553a58c8f85f335ae5dd77e9785a1716c8ac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T09:02:28Z","title_canon_sha256":"b5a5ecef9b3642cf9f8668dbcf0e86db2effe0ec46e7a88e27a29af47ef405d6"},"schema_version":"1.0","source":{"id":"2412.01289","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01289","created_at":"2026-07-05T09:44:17Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01289v2","created_at":"2026-07-05T09:44:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01289","created_at":"2026-07-05T09:44:17Z"},{"alias_kind":"pith_short_12","alias_value":"GFCA7FECJ4K5","created_at":"2026-07-05T09:44:17Z"},{"alias_kind":"pith_short_16","alias_value":"GFCA7FECJ4K5LHAF","created_at":"2026-07-05T09:44:17Z"},{"alias_kind":"pith_short_8","alias_value":"GFCA7FEC","created_at":"2026-07-05T09:44:17Z"}],"graph_snapshots":[{"event_id":"sha256:21766b5274bbe7e20704285c837db37cb8b29343447085c39dbf6b6af5619a8f","target":"graph","created_at":"2026-07-05T09:44:17Z","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/2412.01289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal LLMs (MLLMs) equip language models with visual capabilities by aligning vision encoders with language models. Existing methods to enhance the visual perception of MLLMs often involve designing more powerful vision encoders, which requires exploring a vast design space and re-aligning each potential encoder with the language model, resulting in prohibitively high training costs. In this paper, we introduce VisionFuse, a novel integration framework that efficiently utilizes multiple vision encoders from off-the-shelf MLLMs to enhance visual perception without requiring additional trai","authors_text":"Bohan Zhuang, Jinwu Hu, Mingkui Tan, Yufeng Wang, Zeshuai Deng, Zhuokun Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T09:02:28Z","title":"Enhancing Perception Capabilities of Multimodal LLMs with Training-Free Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01289","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":"sha256:3e49a4496530ad13eb56478eb2506973a3580e4f362554f871e5b59d9a7c7e71","target":"record","created_at":"2026-07-05T09:44:17Z","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":"3a1f06cbf13b6e8803781c0e46b8553a58c8f85f335ae5dd77e9785a1716c8ac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T09:02:28Z","title_canon_sha256":"b5a5ecef9b3642cf9f8668dbcf0e86db2effe0ec46e7a88e27a29af47ef405d6"},"schema_version":"1.0","source":{"id":"2412.01289","kind":"arxiv","version":2}},"canonical_sha256":"31440f94824f15d59c05e05f11f260988466f103214c80e05512f485a04b94e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31440f94824f15d59c05e05f11f260988466f103214c80e05512f485a04b94e5","first_computed_at":"2026-07-05T09:44:17.711209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:17.711209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KUDUxdPTPse74Ct4wqOwH1Shsx/J/YJVEl/n72kWxRjt24XQ/5hOxy4o00n8kDhyNIUvPCj2P8Nh/0PqsJPABg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:17.711688Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01289","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e49a4496530ad13eb56478eb2506973a3580e4f362554f871e5b59d9a7c7e71","sha256:21766b5274bbe7e20704285c837db37cb8b29343447085c39dbf6b6af5619a8f"],"state_sha256":"b836680c5b823dfbeb5c3f09f3fa6801a88cd3c7a97c70bb122210d202b429b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DHv+pYjhVj61ECd1WayJs/iPTg+akSK7CYQSQSBsAlD0kSrH2L52tYwyj/BKgbVLM8Ol+yG7Z72ThUtA68oCBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T07:27:19.044901Z","bundle_sha256":"9c175990b9b63f983b2e11f329078b25e179c776aea1d68fc74fb53bde4f4273"}}