{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:76KDTVCSOHUM7Y63HHCHDE27PK","short_pith_number":"pith:76KDTVCS","canonical_record":{"source":{"id":"2501.16297","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-27T18:36:10Z","cross_cats_sorted":[],"title_canon_sha256":"04976555e0170af1f7fad4fb7b889f685d26c86a6b766b2246ef1399d2a21f43","abstract_canon_sha256":"6e255281523b0a8f2b752ee6584591349648e7e6951762431e130567dbdb7cb1"},"schema_version":"1.0"},"canonical_sha256":"ff9439d45271e8cfe3db39c471935f7a8720c1e6e979ac838e771e3e92571874","source":{"kind":"arxiv","id":"2501.16297","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16297","created_at":"2026-07-05T11:29:06Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16297v2","created_at":"2026-07-05T11:29:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16297","created_at":"2026-07-05T11:29:06Z"},{"alias_kind":"pith_short_12","alias_value":"76KDTVCSOHUM","created_at":"2026-07-05T11:29:06Z"},{"alias_kind":"pith_short_16","alias_value":"76KDTVCSOHUM7Y63","created_at":"2026-07-05T11:29:06Z"},{"alias_kind":"pith_short_8","alias_value":"76KDTVCS","created_at":"2026-07-05T11:29:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:76KDTVCSOHUM7Y63HHCHDE27PK","target":"record","payload":{"canonical_record":{"source":{"id":"2501.16297","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-27T18:36:10Z","cross_cats_sorted":[],"title_canon_sha256":"04976555e0170af1f7fad4fb7b889f685d26c86a6b766b2246ef1399d2a21f43","abstract_canon_sha256":"6e255281523b0a8f2b752ee6584591349648e7e6951762431e130567dbdb7cb1"},"schema_version":"1.0"},"canonical_sha256":"ff9439d45271e8cfe3db39c471935f7a8720c1e6e979ac838e771e3e92571874","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:06.081548Z","signature_b64":"1LX+7Fd8oaIJTrWfzNHPKDQS4h3EMH3TRkNl+SZSLo45rc6/3oiYzvtMHyir3npPFhqT4kv+462WZGtlhOxMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff9439d45271e8cfe3db39c471935f7a8720c1e6e979ac838e771e3e92571874","last_reissued_at":"2026-07-05T11:29:06.080997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:06.080997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.16297","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":"2026-07-05T11:29:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2VUUVMcb2Y3N9BFBdK7Rns0+Xd4xMob95MrnA2qJpV+dOibeOwQtgOUfyGHHwIBDdbQeSCy9Winmw/nYjmhSDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:25:46.433176Z"},"content_sha256":"ba7e736c3062850b342806b3b7e3b12989d71d9f2ec8a0d15ef227d075eb30f3","schema_version":"1.0","event_id":"sha256:ba7e736c3062850b342806b3b7e3b12989d71d9f2ec8a0d15ef227d075eb30f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:76KDTVCSOHUM7Y63HHCHDE27PK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gongwei Chen, Kaiwen Zhou, Liqiang Nie, Miao Zhang, Renshan Zhang, Rui Shao, Weili Guan","submitted_at":"2025-01-27T18:36:10Z","abstract_excerpt":"The incorporation of high-resolution visual input equips multimodal large language models (MLLMs) with enhanced visual perception capabilities for real-world tasks. However, most existing high-resolution MLLMs rely on a cropping-based approach to process images, which leads to fragmented visual encoding and a sharp increase in redundant tokens. To tackle these issues, we propose the FALCON model. FALCON introduces a novel visual register technique to simultaneously: 1) Eliminate redundant tokens at the stage of visual encoding. To directly address the visual redundancy present in the output of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16297","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/2501.16297/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":"2026-07-05T11:29:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mfmQkVBg8g01UGEqwVYQH+ERaDG9eTUyz6zCZ4qx/y4UE1VOjNTrmFn/wWaqY6Tbl58ZHLZH++I8aMMpMs1lCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:25:46.433660Z"},"content_sha256":"b8140ee83b2f227a3ba5179a2ee95df601b47c9491fdc269505f021cc2be8471","schema_version":"1.0","event_id":"sha256:b8140ee83b2f227a3ba5179a2ee95df601b47c9491fdc269505f021cc2be8471"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/76KDTVCSOHUM7Y63HHCHDE27PK/bundle.json","state_url":"https://pith.science/pith/76KDTVCSOHUM7Y63HHCHDE27PK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/76KDTVCSOHUM7Y63HHCHDE27PK/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":"2026-08-11T15:25:46Z","links":{"resolver":"https://pith.science/pith/76KDTVCSOHUM7Y63HHCHDE27PK","bundle":"https://pith.science/pith/76KDTVCSOHUM7Y63HHCHDE27PK/bundle.json","state":"https://pith.science/pith/76KDTVCSOHUM7Y63HHCHDE27PK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/76KDTVCSOHUM7Y63HHCHDE27PK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:76KDTVCSOHUM7Y63HHCHDE27PK","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":"6e255281523b0a8f2b752ee6584591349648e7e6951762431e130567dbdb7cb1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-27T18:36:10Z","title_canon_sha256":"04976555e0170af1f7fad4fb7b889f685d26c86a6b766b2246ef1399d2a21f43"},"schema_version":"1.0","source":{"id":"2501.16297","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16297","created_at":"2026-07-05T11:29:06Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16297v2","created_at":"2026-07-05T11:29:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16297","created_at":"2026-07-05T11:29:06Z"},{"alias_kind":"pith_short_12","alias_value":"76KDTVCSOHUM","created_at":"2026-07-05T11:29:06Z"},{"alias_kind":"pith_short_16","alias_value":"76KDTVCSOHUM7Y63","created_at":"2026-07-05T11:29:06Z"},{"alias_kind":"pith_short_8","alias_value":"76KDTVCS","created_at":"2026-07-05T11:29:06Z"}],"graph_snapshots":[{"event_id":"sha256:b8140ee83b2f227a3ba5179a2ee95df601b47c9491fdc269505f021cc2be8471","target":"graph","created_at":"2026-07-05T11:29:06Z","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/2501.16297/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The incorporation of high-resolution visual input equips multimodal large language models (MLLMs) with enhanced visual perception capabilities for real-world tasks. However, most existing high-resolution MLLMs rely on a cropping-based approach to process images, which leads to fragmented visual encoding and a sharp increase in redundant tokens. To tackle these issues, we propose the FALCON model. FALCON introduces a novel visual register technique to simultaneously: 1) Eliminate redundant tokens at the stage of visual encoding. To directly address the visual redundancy present in the output of","authors_text":"Gongwei Chen, Kaiwen Zhou, Liqiang Nie, Miao Zhang, Renshan Zhang, Rui Shao, Weili Guan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-27T18:36:10Z","title":"FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16297","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:ba7e736c3062850b342806b3b7e3b12989d71d9f2ec8a0d15ef227d075eb30f3","target":"record","created_at":"2026-07-05T11:29:06Z","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":"6e255281523b0a8f2b752ee6584591349648e7e6951762431e130567dbdb7cb1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-27T18:36:10Z","title_canon_sha256":"04976555e0170af1f7fad4fb7b889f685d26c86a6b766b2246ef1399d2a21f43"},"schema_version":"1.0","source":{"id":"2501.16297","kind":"arxiv","version":2}},"canonical_sha256":"ff9439d45271e8cfe3db39c471935f7a8720c1e6e979ac838e771e3e92571874","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff9439d45271e8cfe3db39c471935f7a8720c1e6e979ac838e771e3e92571874","first_computed_at":"2026-07-05T11:29:06.080997Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:06.080997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1LX+7Fd8oaIJTrWfzNHPKDQS4h3EMH3TRkNl+SZSLo45rc6/3oiYzvtMHyir3npPFhqT4kv+462WZGtlhOxMCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:06.081548Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.16297","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba7e736c3062850b342806b3b7e3b12989d71d9f2ec8a0d15ef227d075eb30f3","sha256:b8140ee83b2f227a3ba5179a2ee95df601b47c9491fdc269505f021cc2be8471"],"state_sha256":"ab4ff6e8c52b73d912883f3f8fc2ee7f23e584adc65e957d9b037295a0fc4461"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zyMb1Rb2igyEgSh+GesCShIfLDmRMrHpo9N9pV6vwlfzBIkmgO9E3YnKu33yl/1YDa7BfBtpx9tjHVnKIvRaBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T15:25:46.438196Z","bundle_sha256":"5b84a1feaada82ca0c32c9066d2d802de71546d23e6be3fe62ad1a4414fa2f7a"}}