{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:J376G6NR43PCG6P6TQKE3SDJQG","short_pith_number":"pith:J376G6NR","canonical_record":{"source":{"id":"2409.09564","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-15T00:38:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"edf85e09aa1b7650fc7d59e6ac60a4e9dba618f04c831602f86515ffe64c0047","abstract_canon_sha256":"dd30e81717fb40b5badf2f3a7f31b2c90e46501fb5ed97d98de502c7feecc5a7"},"schema_version":"1.0"},"canonical_sha256":"4effe379b1e6de2379fe9c144dc86981b42fba92fc0ff15b79b5e93c4632496a","source":{"kind":"arxiv","id":"2409.09564","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09564","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09564v2","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09564","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"pith_short_12","alias_value":"J376G6NR43PC","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"pith_short_16","alias_value":"J376G6NR43PCG6P6","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"pith_short_8","alias_value":"J376G6NR","created_at":"2026-07-05T09:09:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:J376G6NR43PCG6P6TQKE3SDJQG","target":"record","payload":{"canonical_record":{"source":{"id":"2409.09564","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-15T00:38:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"edf85e09aa1b7650fc7d59e6ac60a4e9dba618f04c831602f86515ffe64c0047","abstract_canon_sha256":"dd30e81717fb40b5badf2f3a7f31b2c90e46501fb5ed97d98de502c7feecc5a7"},"schema_version":"1.0"},"canonical_sha256":"4effe379b1e6de2379fe9c144dc86981b42fba92fc0ff15b79b5e93c4632496a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:25.961918Z","signature_b64":"VLXVIRaGYyyYPrUoGHtkbyiqEK8+XW8yh2Oq1fErAZooZbffVoBl6uvEYF7qt8+S8X1C1+3vaTg+oNFXXfdnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4effe379b1e6de2379fe9c144dc86981b42fba92fc0ff15b79b5e93c4632496a","last_reissued_at":"2026-07-05T09:09:25.961421Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:25.961421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.09564","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":"2026-07-05T09:09:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HTQfJAEqeoLhvsFDyPOAq6xbVYsaLBXnGalwJyatb87NLyRT3I7VeQu06zIDJaCteBS6aYgwGSh5LUn8Hb+lCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T21:59:50.401055Z"},"content_sha256":"e8eb4ed3e6e0d06c924adabb8233d73b0b1a36fb87f903bcab999f2758883838","schema_version":"1.0","event_id":"sha256:e8eb4ed3e6e0d06c924adabb8233d73b0b1a36fb87f903bcab999f2758883838"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:J376G6NR43PCG6P6TQKE3SDJQG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TG-LLaVA: Text Guided LLaVA via Learnable Latent Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Dawei Yan, Hao Chen, Haokui Zhang, Pengcheng Li, Qingguo Chen, Qingsen Yan, Wei Dong, Weihua Luo, Yang Li","submitted_at":"2024-09-15T00:38:34Z","abstract_excerpt":"Currently, inspired by the success of vision-language models (VLMs), an increasing number of researchers are focusing on improving VLMs and have achieved promising results. However, most existing methods concentrate on optimizing the connector and enhancing the language model component, while neglecting improvements to the vision encoder itself. In contrast, we propose Text Guided LLaVA (TG-LLaVA) in this paper, which optimizes VLMs by guiding the vision encoder with text, offering a new and orthogonal optimization direction. Specifically, inspired by the purpose-driven logic inherent in human"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09564","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/2409.09564/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":"2026-07-05T09:09:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zqdDE45dLra+gdgh2y+Tcl6rdJQjPUzd8pSuhgE1g8DhLMXqi3DirHnlRdhS8zRinamizls+5II3mEek3SEVBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T21:59:50.401458Z"},"content_sha256":"f4cdc59e8fb0e3665bb1bb4abfb2a64a463b8739197e3d3ff999b7cb7cef4a62","schema_version":"1.0","event_id":"sha256:f4cdc59e8fb0e3665bb1bb4abfb2a64a463b8739197e3d3ff999b7cb7cef4a62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J376G6NR43PCG6P6TQKE3SDJQG/bundle.json","state_url":"https://pith.science/pith/J376G6NR43PCG6P6TQKE3SDJQG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J376G6NR43PCG6P6TQKE3SDJQG/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":"2026-07-07T21:59:50Z","links":{"resolver":"https://pith.science/pith/J376G6NR43PCG6P6TQKE3SDJQG","bundle":"https://pith.science/pith/J376G6NR43PCG6P6TQKE3SDJQG/bundle.json","state":"https://pith.science/pith/J376G6NR43PCG6P6TQKE3SDJQG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J376G6NR43PCG6P6TQKE3SDJQG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:J376G6NR43PCG6P6TQKE3SDJQG","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":"dd30e81717fb40b5badf2f3a7f31b2c90e46501fb5ed97d98de502c7feecc5a7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-15T00:38:34Z","title_canon_sha256":"edf85e09aa1b7650fc7d59e6ac60a4e9dba618f04c831602f86515ffe64c0047"},"schema_version":"1.0","source":{"id":"2409.09564","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09564","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09564v2","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09564","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"pith_short_12","alias_value":"J376G6NR43PC","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"pith_short_16","alias_value":"J376G6NR43PCG6P6","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"pith_short_8","alias_value":"J376G6NR","created_at":"2026-07-05T09:09:25Z"}],"graph_snapshots":[{"event_id":"sha256:f4cdc59e8fb0e3665bb1bb4abfb2a64a463b8739197e3d3ff999b7cb7cef4a62","target":"graph","created_at":"2026-07-05T09:09:25Z","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/2409.09564/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Currently, inspired by the success of vision-language models (VLMs), an increasing number of researchers are focusing on improving VLMs and have achieved promising results. However, most existing methods concentrate on optimizing the connector and enhancing the language model component, while neglecting improvements to the vision encoder itself. In contrast, we propose Text Guided LLaVA (TG-LLaVA) in this paper, which optimizes VLMs by guiding the vision encoder with text, offering a new and orthogonal optimization direction. Specifically, inspired by the purpose-driven logic inherent in human","authors_text":"Chunhua Shen, Dawei Yan, Hao Chen, Haokui Zhang, Pengcheng Li, Qingguo Chen, Qingsen Yan, Wei Dong, Weihua Luo, Yang Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-15T00:38:34Z","title":"TG-LLaVA: Text Guided LLaVA via Learnable Latent Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09564","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:e8eb4ed3e6e0d06c924adabb8233d73b0b1a36fb87f903bcab999f2758883838","target":"record","created_at":"2026-07-05T09:09:25Z","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":"dd30e81717fb40b5badf2f3a7f31b2c90e46501fb5ed97d98de502c7feecc5a7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-15T00:38:34Z","title_canon_sha256":"edf85e09aa1b7650fc7d59e6ac60a4e9dba618f04c831602f86515ffe64c0047"},"schema_version":"1.0","source":{"id":"2409.09564","kind":"arxiv","version":2}},"canonical_sha256":"4effe379b1e6de2379fe9c144dc86981b42fba92fc0ff15b79b5e93c4632496a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4effe379b1e6de2379fe9c144dc86981b42fba92fc0ff15b79b5e93c4632496a","first_computed_at":"2026-07-05T09:09:25.961421Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:25.961421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VLXVIRaGYyyYPrUoGHtkbyiqEK8+XW8yh2Oq1fErAZooZbffVoBl6uvEYF7qt8+S8X1C1+3vaTg+oNFXXfdnCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:25.961918Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.09564","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8eb4ed3e6e0d06c924adabb8233d73b0b1a36fb87f903bcab999f2758883838","sha256:f4cdc59e8fb0e3665bb1bb4abfb2a64a463b8739197e3d3ff999b7cb7cef4a62"],"state_sha256":"fea5852243347adee9151cd072072e85894bfaea6f34db6563be6f4619babcf7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Khb2FwjBPprv+z7vLwzR+Ft8TUTwkWkjcZGfgr3vawO5h/u1spGMa1yfKLk9C5ykKU/Z3h194nzAtjD9MptjDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T21:59:50.404520Z","bundle_sha256":"792b6a780c6a0fd4d25c04709e2b2dc389efbcd86d51936fa8e62ba5a741f838"}}