{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MEXINUH36JNLPGEUVLPOTW3P63","short_pith_number":"pith:MEXINUH3","canonical_record":{"source":{"id":"2407.02392","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T16:10:55Z","cross_cats_sorted":[],"title_canon_sha256":"d3a4a5e649b93f12521f2cdb50dc8295f2d9d222900684f3edf0d97b39b1ded4","abstract_canon_sha256":"c2e39f2d2a40a5dc0f5f8ae00e59f911fe7a7183950ad5cdd453278ce2c2e1b4"},"schema_version":"1.0"},"canonical_sha256":"612e86d0fbf25ab79894aadee9db6ff6cee98be012b7490df68c0e7d9bb448ed","source":{"kind":"arxiv","id":"2407.02392","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02392","created_at":"2026-07-05T09:00:05Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02392v4","created_at":"2026-07-05T09:00:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02392","created_at":"2026-07-05T09:00:05Z"},{"alias_kind":"pith_short_12","alias_value":"MEXINUH36JNL","created_at":"2026-07-05T09:00:05Z"},{"alias_kind":"pith_short_16","alias_value":"MEXINUH36JNLPGEU","created_at":"2026-07-05T09:00:05Z"},{"alias_kind":"pith_short_8","alias_value":"MEXINUH3","created_at":"2026-07-05T09:00:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MEXINUH36JNLPGEUVLPOTW3P63","target":"record","payload":{"canonical_record":{"source":{"id":"2407.02392","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T16:10:55Z","cross_cats_sorted":[],"title_canon_sha256":"d3a4a5e649b93f12521f2cdb50dc8295f2d9d222900684f3edf0d97b39b1ded4","abstract_canon_sha256":"c2e39f2d2a40a5dc0f5f8ae00e59f911fe7a7183950ad5cdd453278ce2c2e1b4"},"schema_version":"1.0"},"canonical_sha256":"612e86d0fbf25ab79894aadee9db6ff6cee98be012b7490df68c0e7d9bb448ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:05.847524Z","signature_b64":"Ii7xj7RSabL/VtbzLKpz7w+5GO8QzwpZy3oQkM8CgPcMg2YBReG7WJtcs2YkxJMau9ubzejozApIw+HYzvFWBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"612e86d0fbf25ab79894aadee9db6ff6cee98be012b7490df68c0e7d9bb448ed","last_reissued_at":"2026-07-05T09:00:05.847107Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:05.847107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.02392","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:00:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P25vo2e9Vwb0ys0EK6hlWRcBjwQP4zJmnO+RibK8rE0GZzC6sCkaD0goUNlWWIKXORk+nu+7eI8t3Z//THP7AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:52:18.780903Z"},"content_sha256":"51c7c403a5604ac8f87b14c64e446d6117ae2df91b902c41040ba3f78b7aafac","schema_version":"1.0","event_id":"sha256:51c7c403a5604ac8f87b14c64e446d6117ae2df91b902c41040ba3f78b7aafac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MEXINUH36JNLPGEUVLPOTW3P63","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TokenPacker: Efficient Visual Projector for Multimodal LLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongqi Tang, Jianke Zhu, Jian Liu, Jie Qin, Lei Zhang, Song Wang, Wentong Li, Yuqian Yuan","submitted_at":"2024-07-02T16:10:55Z","abstract_excerpt":"The visual projector serves as an essential bridge between the visual encoder and the Large Language Model (LLM) in a Multimodal LLM (MLLM). Typically, MLLMs adopt a simple MLP to preserve all visual contexts via one-to-one transformation. However, the visual tokens are redundant and can be considerably increased when dealing with high-resolution images, impairing the efficiency of MLLMs significantly. Some recent works have introduced resampler or abstractor to reduce the number of resulting visual tokens. Unfortunately, they fail to capture finer details and undermine the visual reasoning ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02392","kind":"arxiv","version":4},"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/2407.02392/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":"2026-07-05T09:00:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ml49Ggsy1HDI3M3fxCBYikzEPMKYbUQk4605WiGklvi0Y74ksYVwSnZHkuMb9LOneRJ1EeUzU14OpH7SCcz8Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:52:18.781419Z"},"content_sha256":"d04e0a2a3666fe9aec4d183fb290e40aeedd4937f8b97c05ba3b089cf990919d","schema_version":"1.0","event_id":"sha256:d04e0a2a3666fe9aec4d183fb290e40aeedd4937f8b97c05ba3b089cf990919d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MEXINUH36JNLPGEUVLPOTW3P63/bundle.json","state_url":"https://pith.science/pith/MEXINUH36JNLPGEUVLPOTW3P63/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MEXINUH36JNLPGEUVLPOTW3P63/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":"2026-08-07T19:52:18Z","links":{"resolver":"https://pith.science/pith/MEXINUH36JNLPGEUVLPOTW3P63","bundle":"https://pith.science/pith/MEXINUH36JNLPGEUVLPOTW3P63/bundle.json","state":"https://pith.science/pith/MEXINUH36JNLPGEUVLPOTW3P63/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MEXINUH36JNLPGEUVLPOTW3P63/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MEXINUH36JNLPGEUVLPOTW3P63","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":"c2e39f2d2a40a5dc0f5f8ae00e59f911fe7a7183950ad5cdd453278ce2c2e1b4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T16:10:55Z","title_canon_sha256":"d3a4a5e649b93f12521f2cdb50dc8295f2d9d222900684f3edf0d97b39b1ded4"},"schema_version":"1.0","source":{"id":"2407.02392","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02392","created_at":"2026-07-05T09:00:05Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02392v4","created_at":"2026-07-05T09:00:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02392","created_at":"2026-07-05T09:00:05Z"},{"alias_kind":"pith_short_12","alias_value":"MEXINUH36JNL","created_at":"2026-07-05T09:00:05Z"},{"alias_kind":"pith_short_16","alias_value":"MEXINUH36JNLPGEU","created_at":"2026-07-05T09:00:05Z"},{"alias_kind":"pith_short_8","alias_value":"MEXINUH3","created_at":"2026-07-05T09:00:05Z"}],"graph_snapshots":[{"event_id":"sha256:d04e0a2a3666fe9aec4d183fb290e40aeedd4937f8b97c05ba3b089cf990919d","target":"graph","created_at":"2026-07-05T09:00:05Z","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/2407.02392/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The visual projector serves as an essential bridge between the visual encoder and the Large Language Model (LLM) in a Multimodal LLM (MLLM). Typically, MLLMs adopt a simple MLP to preserve all visual contexts via one-to-one transformation. However, the visual tokens are redundant and can be considerably increased when dealing with high-resolution images, impairing the efficiency of MLLMs significantly. Some recent works have introduced resampler or abstractor to reduce the number of resulting visual tokens. Unfortunately, they fail to capture finer details and undermine the visual reasoning ca","authors_text":"Dongqi Tang, Jianke Zhu, Jian Liu, Jie Qin, Lei Zhang, Song Wang, Wentong Li, Yuqian Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T16:10:55Z","title":"TokenPacker: Efficient Visual Projector for Multimodal LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02392","kind":"arxiv","version":4},"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":"sha256:51c7c403a5604ac8f87b14c64e446d6117ae2df91b902c41040ba3f78b7aafac","target":"record","created_at":"2026-07-05T09:00:05Z","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":"c2e39f2d2a40a5dc0f5f8ae00e59f911fe7a7183950ad5cdd453278ce2c2e1b4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T16:10:55Z","title_canon_sha256":"d3a4a5e649b93f12521f2cdb50dc8295f2d9d222900684f3edf0d97b39b1ded4"},"schema_version":"1.0","source":{"id":"2407.02392","kind":"arxiv","version":4}},"canonical_sha256":"612e86d0fbf25ab79894aadee9db6ff6cee98be012b7490df68c0e7d9bb448ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"612e86d0fbf25ab79894aadee9db6ff6cee98be012b7490df68c0e7d9bb448ed","first_computed_at":"2026-07-05T09:00:05.847107Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:05.847107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ii7xj7RSabL/VtbzLKpz7w+5GO8QzwpZy3oQkM8CgPcMg2YBReG7WJtcs2YkxJMau9ubzejozApIw+HYzvFWBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:05.847524Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.02392","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51c7c403a5604ac8f87b14c64e446d6117ae2df91b902c41040ba3f78b7aafac","sha256:d04e0a2a3666fe9aec4d183fb290e40aeedd4937f8b97c05ba3b089cf990919d"],"state_sha256":"5769d4c1551ba41c32320367988559579fc5d1b93a185f7e951079095129ce48"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nGUZuL74C+839dAvQ03pkmKQbr57NyoN0lISnI1pSp3NTRIGYw+Spf4zRTZbccrx3k0LjXlcS/Es4x8t4WmEAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:52:18.787537Z","bundle_sha256":"95984f72b4e0730720ddab074376d930c29523a1e3364ea06a189f5a21c6145c"}}