{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JI2YAATOKQG3BHXHJ3UT73NYD5","short_pith_number":"pith:JI2YAATO","canonical_record":{"source":{"id":"2408.12321","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T11:57:16Z","cross_cats_sorted":["cs.CV","cs.MM"],"title_canon_sha256":"e48d673e5b900dfdf2f85a7a5f03b478989b17d3a3dcbe16f1b5334d9658dc1a","abstract_canon_sha256":"958a9b3ce5ece64f6d9f40c6dc11ebe46c510295f7b49a05adad61d8299b313e"},"schema_version":"1.0"},"canonical_sha256":"4a3580026e540db09ee74ee93fedb81f4fded67f3078d33460b71fea72546951","source":{"kind":"arxiv","id":"2408.12321","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12321","created_at":"2026-07-05T08:59:12Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12321v2","created_at":"2026-07-05T08:59:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12321","created_at":"2026-07-05T08:59:12Z"},{"alias_kind":"pith_short_12","alias_value":"JI2YAATOKQG3","created_at":"2026-07-05T08:59:12Z"},{"alias_kind":"pith_short_16","alias_value":"JI2YAATOKQG3BHXH","created_at":"2026-07-05T08:59:12Z"},{"alias_kind":"pith_short_8","alias_value":"JI2YAATO","created_at":"2026-07-05T08:59:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JI2YAATOKQG3BHXHJ3UT73NYD5","target":"record","payload":{"canonical_record":{"source":{"id":"2408.12321","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T11:57:16Z","cross_cats_sorted":["cs.CV","cs.MM"],"title_canon_sha256":"e48d673e5b900dfdf2f85a7a5f03b478989b17d3a3dcbe16f1b5334d9658dc1a","abstract_canon_sha256":"958a9b3ce5ece64f6d9f40c6dc11ebe46c510295f7b49a05adad61d8299b313e"},"schema_version":"1.0"},"canonical_sha256":"4a3580026e540db09ee74ee93fedb81f4fded67f3078d33460b71fea72546951","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:12.337860Z","signature_b64":"K2uXt1akqIFUUcBQQDjCNKq2iuyx1NFz7U9eIeDj5AuEhHSymS/fbrggf1p/RumAXJ7qjALxwj2pFpsM5EHbBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a3580026e540db09ee74ee93fedb81f4fded67f3078d33460b71fea72546951","last_reissued_at":"2026-07-05T08:59:12.337410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:12.337410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.12321","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":"2026-07-05T08:59:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h62RdDqhCCNjEm6V0+WVHYroJYpOeA/oKF0qwKqwdNwzk9OTHM/b5dQta177Zz9mmp1hKAf3pwjpldKcxc7XAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:09:24.630956Z"},"content_sha256":"7ca4d5ed5e010b163cc3d5ac1d3b35a337f7e82df33316e77459c75f382baf01","schema_version":"1.0","event_id":"sha256:7ca4d5ed5e010b163cc3d5ac1d3b35a337f7e82df33316e77459c75f382baf01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JI2YAATOKQG3BHXHJ3UT73NYD5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM"],"primary_cat":"cs.CL","authors_text":"Chaoya Jiang, Fei Huang, Haiyang Xu, Jia Hongrui, Ji Zhang, Mengfan Dong, Ming Yan, Shikun Zhang, Wei Ye","submitted_at":"2024-08-22T11:57:16Z","abstract_excerpt":"This paper presents MaVEn, an innovative Multi-granularity Visual Encoding framework designed to enhance the capabilities of Multimodal Large Language Models (MLLMs) in multi-image reasoning. Current MLLMs primarily focus on single-image visual understanding, limiting their ability to interpret and integrate information across multiple images. MaVEn addresses this limitation by combining discrete visual symbol sequences, which abstract coarse-grained semantic concepts, with traditional continuous representation sequences that model fine-grained features. This dual approach bridges the semantic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12321","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/2408.12321/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":"2026-07-05T08:59:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zzpSy7XpS7nUHUUe4q0R3HB3THsfRSqBRX1uhvBuuTB0Ud1jn4jD7PsdejDPAEpNChn1NCm8JFtojBIcdjCcCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:09:24.631447Z"},"content_sha256":"e617a9fe299899c9a841caad7a9a0f2c81cfc89c2d8aa9cf828e0d7b19a380ba","schema_version":"1.0","event_id":"sha256:e617a9fe299899c9a841caad7a9a0f2c81cfc89c2d8aa9cf828e0d7b19a380ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JI2YAATOKQG3BHXHJ3UT73NYD5/bundle.json","state_url":"https://pith.science/pith/JI2YAATOKQG3BHXHJ3UT73NYD5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JI2YAATOKQG3BHXHJ3UT73NYD5/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":"2026-08-08T22:09:24Z","links":{"resolver":"https://pith.science/pith/JI2YAATOKQG3BHXHJ3UT73NYD5","bundle":"https://pith.science/pith/JI2YAATOKQG3BHXHJ3UT73NYD5/bundle.json","state":"https://pith.science/pith/JI2YAATOKQG3BHXHJ3UT73NYD5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JI2YAATOKQG3BHXHJ3UT73NYD5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JI2YAATOKQG3BHXHJ3UT73NYD5","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":"958a9b3ce5ece64f6d9f40c6dc11ebe46c510295f7b49a05adad61d8299b313e","cross_cats_sorted":["cs.CV","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T11:57:16Z","title_canon_sha256":"e48d673e5b900dfdf2f85a7a5f03b478989b17d3a3dcbe16f1b5334d9658dc1a"},"schema_version":"1.0","source":{"id":"2408.12321","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12321","created_at":"2026-07-05T08:59:12Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12321v2","created_at":"2026-07-05T08:59:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12321","created_at":"2026-07-05T08:59:12Z"},{"alias_kind":"pith_short_12","alias_value":"JI2YAATOKQG3","created_at":"2026-07-05T08:59:12Z"},{"alias_kind":"pith_short_16","alias_value":"JI2YAATOKQG3BHXH","created_at":"2026-07-05T08:59:12Z"},{"alias_kind":"pith_short_8","alias_value":"JI2YAATO","created_at":"2026-07-05T08:59:12Z"}],"graph_snapshots":[{"event_id":"sha256:e617a9fe299899c9a841caad7a9a0f2c81cfc89c2d8aa9cf828e0d7b19a380ba","target":"graph","created_at":"2026-07-05T08:59:12Z","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/2408.12321/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents MaVEn, an innovative Multi-granularity Visual Encoding framework designed to enhance the capabilities of Multimodal Large Language Models (MLLMs) in multi-image reasoning. Current MLLMs primarily focus on single-image visual understanding, limiting their ability to interpret and integrate information across multiple images. MaVEn addresses this limitation by combining discrete visual symbol sequences, which abstract coarse-grained semantic concepts, with traditional continuous representation sequences that model fine-grained features. This dual approach bridges the semantic","authors_text":"Chaoya Jiang, Fei Huang, Haiyang Xu, Jia Hongrui, Ji Zhang, Mengfan Dong, Ming Yan, Shikun Zhang, Wei Ye","cross_cats":["cs.CV","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T11:57:16Z","title":"MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12321","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":"sha256:7ca4d5ed5e010b163cc3d5ac1d3b35a337f7e82df33316e77459c75f382baf01","target":"record","created_at":"2026-07-05T08:59:12Z","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":"958a9b3ce5ece64f6d9f40c6dc11ebe46c510295f7b49a05adad61d8299b313e","cross_cats_sorted":["cs.CV","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T11:57:16Z","title_canon_sha256":"e48d673e5b900dfdf2f85a7a5f03b478989b17d3a3dcbe16f1b5334d9658dc1a"},"schema_version":"1.0","source":{"id":"2408.12321","kind":"arxiv","version":2}},"canonical_sha256":"4a3580026e540db09ee74ee93fedb81f4fded67f3078d33460b71fea72546951","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a3580026e540db09ee74ee93fedb81f4fded67f3078d33460b71fea72546951","first_computed_at":"2026-07-05T08:59:12.337410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:59:12.337410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K2uXt1akqIFUUcBQQDjCNKq2iuyx1NFz7U9eIeDj5AuEhHSymS/fbrggf1p/RumAXJ7qjALxwj2pFpsM5EHbBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:59:12.337860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.12321","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ca4d5ed5e010b163cc3d5ac1d3b35a337f7e82df33316e77459c75f382baf01","sha256:e617a9fe299899c9a841caad7a9a0f2c81cfc89c2d8aa9cf828e0d7b19a380ba"],"state_sha256":"0b8aeb98e2821e957100f4bcb543612fde8cce7090fc0ccb0795126655f8ea5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bKrscGLA3keFYumyD1/FdlTRzrowgTDvtHqh1yHlE0f9SJXVphow6br7hzzSHGMmGEwR+g2FpQReWgQxBNQhDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:09:24.636184Z","bundle_sha256":"b244abe22472898e2d29685eb7439b037a8a214d16d8469afd98eb7ff386ad72"}}