{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5DZCKW23XUT5QNZIITW6DOV7CX","short_pith_number":"pith:5DZCKW23","schema_version":"1.0","canonical_sha256":"e8f2255b5bbd27d8372844ede1babf15dbdf32d95bb39cd151299a71ed691c13","source":{"kind":"arxiv","id":"2409.14713","version":1},"attestation_state":"computed","paper":{"title":"Phantom of Latent for Large Language and Vision Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beomchan Park, Byung-Kwan Lee, Chae Won Kim, Sangyun Chung, Yong Man Ro","submitted_at":"2024-09-23T05:19:06Z","abstract_excerpt":"The success of visual instruction tuning has accelerated the development of large language and vision models (LLVMs). Following the scaling laws of instruction-tuned large language models (LLMs), LLVMs either have further increased their sizes, reaching 26B, 34B, and even 80B parameters. While this increase in model size has yielded significant performance gains, it demands substantially more hardware resources for both training and inference. Consequently, there naturally exists a strong need for efficient LLVMs that achieve the performance of larger models while being smaller in size. To ach"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.14713","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-23T05:19:06Z","cross_cats_sorted":[],"title_canon_sha256":"5d8e56bad7d412a3d0c3ac5ad0cd2731b6bd64a13d111b334dacb9313e892fe6","abstract_canon_sha256":"abb4ffd03caac16dac053ed2b6930b5f7be45c36d7eb687eb247f1b667bcc16c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:20.528247Z","signature_b64":"ODwjiDF37oq6W8vWTQRhorT9EfqHmorPjiM1qTDulrqSkhQN0pec0DfNVg+mbR9l5IHkRvIhdrdLejl58uU0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8f2255b5bbd27d8372844ede1babf15dbdf32d95bb39cd151299a71ed691c13","last_reissued_at":"2026-07-05T09:10:20.527790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:20.527790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phantom of Latent for Large Language and Vision Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beomchan Park, Byung-Kwan Lee, Chae Won Kim, Sangyun Chung, Yong Man Ro","submitted_at":"2024-09-23T05:19:06Z","abstract_excerpt":"The success of visual instruction tuning has accelerated the development of large language and vision models (LLVMs). Following the scaling laws of instruction-tuned large language models (LLMs), LLVMs either have further increased their sizes, reaching 26B, 34B, and even 80B parameters. While this increase in model size has yielded significant performance gains, it demands substantially more hardware resources for both training and inference. Consequently, there naturally exists a strong need for efficient LLVMs that achieve the performance of larger models while being smaller in size. To ach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14713","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/2409.14713/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.14713","created_at":"2026-07-05T09:10:20.527846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.14713v1","created_at":"2026-07-05T09:10:20.527846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14713","created_at":"2026-07-05T09:10:20.527846+00:00"},{"alias_kind":"pith_short_12","alias_value":"5DZCKW23XUT5","created_at":"2026-07-05T09:10:20.527846+00:00"},{"alias_kind":"pith_short_16","alias_value":"5DZCKW23XUT5QNZI","created_at":"2026-07-05T09:10:20.527846+00:00"},{"alias_kind":"pith_short_8","alias_value":"5DZCKW23","created_at":"2026-07-05T09:10:20.527846+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18216","citing_title":"Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29082","citing_title":"Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28774","citing_title":"Agent Explorative Policy Optimization for Multimodal Agentic Reasoning","ref_index":89,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5DZCKW23XUT5QNZIITW6DOV7CX","json":"https://pith.science/pith/5DZCKW23XUT5QNZIITW6DOV7CX.json","graph_json":"https://pith.science/api/pith-number/5DZCKW23XUT5QNZIITW6DOV7CX/graph.json","events_json":"https://pith.science/api/pith-number/5DZCKW23XUT5QNZIITW6DOV7CX/events.json","paper":"https://pith.science/paper/5DZCKW23"},"agent_actions":{"view_html":"https://pith.science/pith/5DZCKW23XUT5QNZIITW6DOV7CX","download_json":"https://pith.science/pith/5DZCKW23XUT5QNZIITW6DOV7CX.json","view_paper":"https://pith.science/paper/5DZCKW23","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.14713&json=true","fetch_graph":"https://pith.science/api/pith-number/5DZCKW23XUT5QNZIITW6DOV7CX/graph.json","fetch_events":"https://pith.science/api/pith-number/5DZCKW23XUT5QNZIITW6DOV7CX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5DZCKW23XUT5QNZIITW6DOV7CX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5DZCKW23XUT5QNZIITW6DOV7CX/action/storage_attestation","attest_author":"https://pith.science/pith/5DZCKW23XUT5QNZIITW6DOV7CX/action/author_attestation","sign_citation":"https://pith.science/pith/5DZCKW23XUT5QNZIITW6DOV7CX/action/citation_signature","submit_replication":"https://pith.science/pith/5DZCKW23XUT5QNZIITW6DOV7CX/action/replication_record"}},"created_at":"2026-07-05T09:10:20.527846+00:00","updated_at":"2026-07-05T09:10:20.527846+00:00"}