{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:X63W2O446TW6GBBPVYB4WJIXQR","short_pith_number":"pith:X63W2O44","canonical_record":{"source":{"id":"2407.16198","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T06:02:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f8dcd3a3c85048e1fcf7f04ab891f596e473c5a80a80ee4e4674eab913618f3b","abstract_canon_sha256":"2dd7a177b0f6bd5baa3ab484e0fa90bb44e98f0becaca1f22b58c9b76ac46913"},"schema_version":"1.0"},"canonical_sha256":"bfb76d3b9cf4ede3042fae03cb2517846df037d6f632aa6f4caedf521696b7aa","source":{"kind":"arxiv","id":"2407.16198","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.16198","created_at":"2026-07-05T08:47:29Z"},{"alias_kind":"arxiv_version","alias_value":"2407.16198v1","created_at":"2026-07-05T08:47:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16198","created_at":"2026-07-05T08:47:29Z"},{"alias_kind":"pith_short_12","alias_value":"X63W2O446TW6","created_at":"2026-07-05T08:47:29Z"},{"alias_kind":"pith_short_16","alias_value":"X63W2O446TW6GBBP","created_at":"2026-07-05T08:47:29Z"},{"alias_kind":"pith_short_8","alias_value":"X63W2O44","created_at":"2026-07-05T08:47:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:X63W2O446TW6GBBPVYB4WJIXQR","target":"record","payload":{"canonical_record":{"source":{"id":"2407.16198","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T06:02:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f8dcd3a3c85048e1fcf7f04ab891f596e473c5a80a80ee4e4674eab913618f3b","abstract_canon_sha256":"2dd7a177b0f6bd5baa3ab484e0fa90bb44e98f0becaca1f22b58c9b76ac46913"},"schema_version":"1.0"},"canonical_sha256":"bfb76d3b9cf4ede3042fae03cb2517846df037d6f632aa6f4caedf521696b7aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:29.026089Z","signature_b64":"6xHJA0a5EkUWnEpdpTbPskYqscHRbheRDiH9zWEhQXpSr1TC8pg/iAdOIjOk8TjQsHq9fONYRNBtICGPTJiZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfb76d3b9cf4ede3042fae03cb2517846df037d6f632aa6f4caedf521696b7aa","last_reissued_at":"2026-07-05T08:47:29.025652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:29.025652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.16198","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:47:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8VSDuC+BqLTT1ljf+n7MzFOg+xrRmZY7Y5MNQNjkv/pKnu14RBZJwTFrzWCQBD5wanx0pg9W9fiopDVLB7tRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T17:33:07.681077Z"},"content_sha256":"e1711b38d37af8a0ed18c6f7be039b30d75441486e4627177f19450128aafc00","schema_version":"1.0","event_id":"sha256:e1711b38d37af8a0ed18c6f7be039b30d75441486e4627177f19450128aafc00"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:X63W2O446TW6GBBPVYB4WJIXQR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiayi Ji, Qiang Zhou, Rongrong Ji, Weihuang Lin, Xiaoshuai Sun, Yiwei Ma, Zhibin Wang","submitted_at":"2024-07-23T06:02:30Z","abstract_excerpt":"With advancements in data availability and computing resources, Multimodal Large Language Models (MLLMs) have showcased capabilities across various fields. However, the quadratic complexity of the vision encoder in MLLMs constrains the resolution of input images. Most current approaches mitigate this issue by cropping high-resolution images into smaller sub-images, which are then processed independently by the vision encoder. Despite capturing sufficient local details, these sub-images lack global context and fail to interact with one another. To address this limitation, we propose a novel MLL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16198","kind":"arxiv","version":1},"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/2407.16198/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":"2026-07-05T08:47:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m0DdOM386SLgkLo9s1ObpiauOKe1Idhh5AZ0WjHex6fFPfWws41aWjON3mF+6Qh0Z1hRdjEbdRKP3jRDjABTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T17:33:07.681677Z"},"content_sha256":"02ac0641f04fc52cb7ce97b76dee7b841b6cdb7a73260b70558adcff0cac7e04","schema_version":"1.0","event_id":"sha256:02ac0641f04fc52cb7ce97b76dee7b841b6cdb7a73260b70558adcff0cac7e04"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X63W2O446TW6GBBPVYB4WJIXQR/bundle.json","state_url":"https://pith.science/pith/X63W2O446TW6GBBPVYB4WJIXQR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X63W2O446TW6GBBPVYB4WJIXQR/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":"2026-08-20T17:33:07Z","links":{"resolver":"https://pith.science/pith/X63W2O446TW6GBBPVYB4WJIXQR","bundle":"https://pith.science/pith/X63W2O446TW6GBBPVYB4WJIXQR/bundle.json","state":"https://pith.science/pith/X63W2O446TW6GBBPVYB4WJIXQR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X63W2O446TW6GBBPVYB4WJIXQR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X63W2O446TW6GBBPVYB4WJIXQR","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":"2dd7a177b0f6bd5baa3ab484e0fa90bb44e98f0becaca1f22b58c9b76ac46913","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T06:02:30Z","title_canon_sha256":"f8dcd3a3c85048e1fcf7f04ab891f596e473c5a80a80ee4e4674eab913618f3b"},"schema_version":"1.0","source":{"id":"2407.16198","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.16198","created_at":"2026-07-05T08:47:29Z"},{"alias_kind":"arxiv_version","alias_value":"2407.16198v1","created_at":"2026-07-05T08:47:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16198","created_at":"2026-07-05T08:47:29Z"},{"alias_kind":"pith_short_12","alias_value":"X63W2O446TW6","created_at":"2026-07-05T08:47:29Z"},{"alias_kind":"pith_short_16","alias_value":"X63W2O446TW6GBBP","created_at":"2026-07-05T08:47:29Z"},{"alias_kind":"pith_short_8","alias_value":"X63W2O44","created_at":"2026-07-05T08:47:29Z"}],"graph_snapshots":[{"event_id":"sha256:02ac0641f04fc52cb7ce97b76dee7b841b6cdb7a73260b70558adcff0cac7e04","target":"graph","created_at":"2026-07-05T08:47:29Z","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/2407.16198/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With advancements in data availability and computing resources, Multimodal Large Language Models (MLLMs) have showcased capabilities across various fields. However, the quadratic complexity of the vision encoder in MLLMs constrains the resolution of input images. Most current approaches mitigate this issue by cropping high-resolution images into smaller sub-images, which are then processed independently by the vision encoder. Despite capturing sufficient local details, these sub-images lack global context and fail to interact with one another. To address this limitation, we propose a novel MLL","authors_text":"Jiayi Ji, Qiang Zhou, Rongrong Ji, Weihuang Lin, Xiaoshuai Sun, Yiwei Ma, Zhibin Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T06:02:30Z","title":"INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16198","kind":"arxiv","version":1},"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:e1711b38d37af8a0ed18c6f7be039b30d75441486e4627177f19450128aafc00","target":"record","created_at":"2026-07-05T08:47:29Z","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":"2dd7a177b0f6bd5baa3ab484e0fa90bb44e98f0becaca1f22b58c9b76ac46913","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T06:02:30Z","title_canon_sha256":"f8dcd3a3c85048e1fcf7f04ab891f596e473c5a80a80ee4e4674eab913618f3b"},"schema_version":"1.0","source":{"id":"2407.16198","kind":"arxiv","version":1}},"canonical_sha256":"bfb76d3b9cf4ede3042fae03cb2517846df037d6f632aa6f4caedf521696b7aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfb76d3b9cf4ede3042fae03cb2517846df037d6f632aa6f4caedf521696b7aa","first_computed_at":"2026-07-05T08:47:29.025652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:47:29.025652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6xHJA0a5EkUWnEpdpTbPskYqscHRbheRDiH9zWEhQXpSr1TC8pg/iAdOIjOk8TjQsHq9fONYRNBtICGPTJiZCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:47:29.026089Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.16198","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1711b38d37af8a0ed18c6f7be039b30d75441486e4627177f19450128aafc00","sha256:02ac0641f04fc52cb7ce97b76dee7b841b6cdb7a73260b70558adcff0cac7e04"],"state_sha256":"9f86041fc7c109139186a59b15c1093de18c8344f5d598f786333d1b1f33b2ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6uGUxFE/YK+VUJgVuhVi5tCRSPwGVuVbNNTYqL7RkIkXt+xEefWnbCWUU0sD3wQEmYEKNofTxmz4jGt4+upoCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T17:33:07.686718Z","bundle_sha256":"eaa6b827e399f9e8ee730f6e40714111c37d92c854ce9f08debb36638425fd26"}}