{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XOMFU3NMVK6EQHZFCJLUNK245N","short_pith_number":"pith:XOMFU3NM","canonical_record":{"source":{"id":"2405.15738","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T17:34:15Z","cross_cats_sorted":[],"title_canon_sha256":"69a86fbabcca4b5658cfd1f18f4108d34580e6a049d6acaf39cba9eee6152a44","abstract_canon_sha256":"18a7644b7e27711d97a5ef072538970b0e92d929a99680d563f91cf611a755d4"},"schema_version":"1.0"},"canonical_sha256":"bb985a6dacaabc481f25125746ab5ceb42070674ddbd303cafbf33f73d792549","source":{"kind":"arxiv","id":"2405.15738","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15738","created_at":"2026-07-05T08:22:53Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15738v1","created_at":"2026-07-05T08:22:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15738","created_at":"2026-07-05T08:22:53Z"},{"alias_kind":"pith_short_12","alias_value":"XOMFU3NMVK6E","created_at":"2026-07-05T08:22:53Z"},{"alias_kind":"pith_short_16","alias_value":"XOMFU3NMVK6EQHZF","created_at":"2026-07-05T08:22:53Z"},{"alias_kind":"pith_short_8","alias_value":"XOMFU3NM","created_at":"2026-07-05T08:22:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XOMFU3NMVK6EQHZFCJLUNK245N","target":"record","payload":{"canonical_record":{"source":{"id":"2405.15738","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T17:34:15Z","cross_cats_sorted":[],"title_canon_sha256":"69a86fbabcca4b5658cfd1f18f4108d34580e6a049d6acaf39cba9eee6152a44","abstract_canon_sha256":"18a7644b7e27711d97a5ef072538970b0e92d929a99680d563f91cf611a755d4"},"schema_version":"1.0"},"canonical_sha256":"bb985a6dacaabc481f25125746ab5ceb42070674ddbd303cafbf33f73d792549","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:53.358945Z","signature_b64":"npaareNuh5ZsYc7pmgWpQSiER9WCf6YfCOs/vCXxOhoSPQk/55RHXglPd3fmHNp5X1OiPEAFlARLkGgCN9y5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb985a6dacaabc481f25125746ab5ceb42070674ddbd303cafbf33f73d792549","last_reissued_at":"2026-07-05T08:22:53.358521Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:53.358521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.15738","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":"2026-07-05T08:22:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sT0LdfnTApO9UaBNurZo5iVHq0V3/glRi9MAFzQlRyVkhw2elkujQaA1ev5uSSYhnZgc5tyVBTGyuf8TcUtAAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:13:26.864292Z"},"content_sha256":"9942fca467217ba856f581942a0d5f40e0f2173ed1a571d2d2f636ef531625e4","schema_version":"1.0","event_id":"sha256:9942fca467217ba856f581942a0d5f40e0f2173ed1a571d2d2f636ef531625e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XOMFU3NMVK6EQHZFCJLUNK245N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zheng, Chunjiang Ge, Gao Huang, Jiale Yuan, Jun Song, Shiji Song, Sijie Cheng, Yuan Gao, Ziming Wang","submitted_at":"2024-05-24T17:34:15Z","abstract_excerpt":"High-resolution Large Multimodal Models (LMMs) encounter the challenges of excessive visual tokens and quadratic visual complexity. Current high-resolution LMMs address the quadratic complexity while still generating excessive visual tokens. However, the redundancy in visual tokens is the key problem as it leads to more substantial compute. To mitigate this issue, we propose ConvLLaVA, which employs ConvNeXt, a hierarchical backbone, as the visual encoder of LMM to replace Vision Transformer (ViT). ConvLLaVA compresses high-resolution images into information-rich visual features, effectively p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15738","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/2405.15738/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":"2026-07-05T08:22:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"726H/YC1qKrw1gr+/kmJgkKzxaLvIlhpmj/scngcVlUmfY6mNAOaJt9/EcGdhYqZ8QEk12KTgFisLmymzdfWAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:13:26.864955Z"},"content_sha256":"8c80f4303a1b5f47ba07e4ca61a867b0fd5936571f4c85842e14c3b920bbd221","schema_version":"1.0","event_id":"sha256:8c80f4303a1b5f47ba07e4ca61a867b0fd5936571f4c85842e14c3b920bbd221"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XOMFU3NMVK6EQHZFCJLUNK245N/bundle.json","state_url":"https://pith.science/pith/XOMFU3NMVK6EQHZFCJLUNK245N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XOMFU3NMVK6EQHZFCJLUNK245N/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":"2026-08-18T16:13:26Z","links":{"resolver":"https://pith.science/pith/XOMFU3NMVK6EQHZFCJLUNK245N","bundle":"https://pith.science/pith/XOMFU3NMVK6EQHZFCJLUNK245N/bundle.json","state":"https://pith.science/pith/XOMFU3NMVK6EQHZFCJLUNK245N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XOMFU3NMVK6EQHZFCJLUNK245N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XOMFU3NMVK6EQHZFCJLUNK245N","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":"18a7644b7e27711d97a5ef072538970b0e92d929a99680d563f91cf611a755d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T17:34:15Z","title_canon_sha256":"69a86fbabcca4b5658cfd1f18f4108d34580e6a049d6acaf39cba9eee6152a44"},"schema_version":"1.0","source":{"id":"2405.15738","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15738","created_at":"2026-07-05T08:22:53Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15738v1","created_at":"2026-07-05T08:22:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15738","created_at":"2026-07-05T08:22:53Z"},{"alias_kind":"pith_short_12","alias_value":"XOMFU3NMVK6E","created_at":"2026-07-05T08:22:53Z"},{"alias_kind":"pith_short_16","alias_value":"XOMFU3NMVK6EQHZF","created_at":"2026-07-05T08:22:53Z"},{"alias_kind":"pith_short_8","alias_value":"XOMFU3NM","created_at":"2026-07-05T08:22:53Z"}],"graph_snapshots":[{"event_id":"sha256:8c80f4303a1b5f47ba07e4ca61a867b0fd5936571f4c85842e14c3b920bbd221","target":"graph","created_at":"2026-07-05T08:22:53Z","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/2405.15738/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-resolution Large Multimodal Models (LMMs) encounter the challenges of excessive visual tokens and quadratic visual complexity. Current high-resolution LMMs address the quadratic complexity while still generating excessive visual tokens. However, the redundancy in visual tokens is the key problem as it leads to more substantial compute. To mitigate this issue, we propose ConvLLaVA, which employs ConvNeXt, a hierarchical backbone, as the visual encoder of LMM to replace Vision Transformer (ViT). ConvLLaVA compresses high-resolution images into information-rich visual features, effectively p","authors_text":"Bo Zheng, Chunjiang Ge, Gao Huang, Jiale Yuan, Jun Song, Shiji Song, Sijie Cheng, Yuan Gao, Ziming Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T17:34:15Z","title":"ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15738","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":"sha256:9942fca467217ba856f581942a0d5f40e0f2173ed1a571d2d2f636ef531625e4","target":"record","created_at":"2026-07-05T08:22:53Z","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":"18a7644b7e27711d97a5ef072538970b0e92d929a99680d563f91cf611a755d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T17:34:15Z","title_canon_sha256":"69a86fbabcca4b5658cfd1f18f4108d34580e6a049d6acaf39cba9eee6152a44"},"schema_version":"1.0","source":{"id":"2405.15738","kind":"arxiv","version":1}},"canonical_sha256":"bb985a6dacaabc481f25125746ab5ceb42070674ddbd303cafbf33f73d792549","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb985a6dacaabc481f25125746ab5ceb42070674ddbd303cafbf33f73d792549","first_computed_at":"2026-07-05T08:22:53.358521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:22:53.358521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"npaareNuh5ZsYc7pmgWpQSiER9WCf6YfCOs/vCXxOhoSPQk/55RHXglPd3fmHNp5X1OiPEAFlARLkGgCN9y5BA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:22:53.358945Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.15738","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9942fca467217ba856f581942a0d5f40e0f2173ed1a571d2d2f636ef531625e4","sha256:8c80f4303a1b5f47ba07e4ca61a867b0fd5936571f4c85842e14c3b920bbd221"],"state_sha256":"6970566ee586631a5936600e9b2661b13bf79d61fa7930ffbfd6aa8d90e23df8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/i7eEC988WSHRgSB2KVfXlLA3SOyJ3B9ouI0+c/885URE2AmMDmccta4ldE9IMMK6XRR1kOdcHocmKciu7uCCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T16:13:26.870065Z","bundle_sha256":"11d2957bd601e07b8e8787ebb1095858c11ca430087c96af143bb89fc70b8ff6"}}