{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y34AZWCYFQTDIIISPENHJGCC6L","short_pith_number":"pith:Y34AZWCY","canonical_record":{"source":{"id":"2401.02330","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T16:07:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"af58d89b74f7bb8cca5b6907909eba7e27b1b4525c472afd5eef29a181695a48","abstract_canon_sha256":"9af08bb35193edd4d1ada32e8574e4521c773038366dd574e2002ed857001302"},"schema_version":"1.0"},"canonical_sha256":"c6f80cd8582c26342112791a749842f2d77d4cbf9902b42d11397a9ecad48518","source":{"kind":"arxiv","id":"2401.02330","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.02330","created_at":"2026-07-05T07:48:02Z"},{"alias_kind":"arxiv_version","alias_value":"2401.02330v4","created_at":"2026-07-05T07:48:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02330","created_at":"2026-07-05T07:48:02Z"},{"alias_kind":"pith_short_12","alias_value":"Y34AZWCYFQTD","created_at":"2026-07-05T07:48:02Z"},{"alias_kind":"pith_short_16","alias_value":"Y34AZWCYFQTDIIIS","created_at":"2026-07-05T07:48:02Z"},{"alias_kind":"pith_short_8","alias_value":"Y34AZWCY","created_at":"2026-07-05T07:48:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y34AZWCYFQTDIIISPENHJGCC6L","target":"record","payload":{"canonical_record":{"source":{"id":"2401.02330","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T16:07:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"af58d89b74f7bb8cca5b6907909eba7e27b1b4525c472afd5eef29a181695a48","abstract_canon_sha256":"9af08bb35193edd4d1ada32e8574e4521c773038366dd574e2002ed857001302"},"schema_version":"1.0"},"canonical_sha256":"c6f80cd8582c26342112791a749842f2d77d4cbf9902b42d11397a9ecad48518","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:02.329129Z","signature_b64":"tStESKtEPFpoQvgHcrmsgVwVNX8hPyay5bqkvWFjXcwkyrBKtLTThbJy6C18bcP2Bz4CrSk5B6Ki6e6bVotyAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6f80cd8582c26342112791a749842f2d77d4cbf9902b42d11397a9ecad48518","last_reissued_at":"2026-07-05T07:48:02.328664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:02.328664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.02330","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":"2026-07-05T07:48:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xXgO31nY0GonuXkTj+0JaA71Plq79nP/OdekfG7MnEHuNDlqByVqqL1gh9llu/kJpGDAQciucMOZi1Pi0C2sBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:26:08.060165Z"},"content_sha256":"91bacff112f41b404ff11d43e9c7c90de55704866b2aeb90051960afd41effe5","schema_version":"1.0","event_id":"sha256:91bacff112f41b404ff11d43e9c7c90de55704866b2aeb90051960afd41effe5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y34AZWCYFQTDIIISPENHJGCC6L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jian Tang, Minjie Zhu, Ning Liu, Xiaofeng Mou, Yichen Zhu, Zhicai Ou","submitted_at":"2024-01-04T16:07:43Z","abstract_excerpt":"In this paper, we introduce LLaVA-$\\phi$ (LLaVA-Phi), an efficient multi-modal assistant that harnesses the power of the recently advanced small language model, Phi-2, to facilitate multi-modal dialogues. LLaVA-Phi marks a notable advancement in the realm of compact multi-modal models. It demonstrates that even smaller language models, with as few as 2.7B parameters, can effectively engage in intricate dialogues that integrate both textual and visual elements, provided they are trained with high-quality corpora. Our model delivers commendable performance on publicly available benchmarks that e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02330","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/2401.02330/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":"2026-07-05T07:48:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QEgnDDKPAU/GDF4GQ/J39qNN2hLy4BHdmyqEy8hxhLm8+aYND7sCfzizYzNhNbqTX2U2Zue+7+hl1AQ6plA/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:26:08.060989Z"},"content_sha256":"fb009dc8296b566c68724fe5f09fd4b86344b1b2e237fb5417febe0039c26a1f","schema_version":"1.0","event_id":"sha256:fb009dc8296b566c68724fe5f09fd4b86344b1b2e237fb5417febe0039c26a1f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y34AZWCYFQTDIIISPENHJGCC6L/bundle.json","state_url":"https://pith.science/pith/Y34AZWCYFQTDIIISPENHJGCC6L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y34AZWCYFQTDIIISPENHJGCC6L/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":"2026-08-03T18:26:08Z","links":{"resolver":"https://pith.science/pith/Y34AZWCYFQTDIIISPENHJGCC6L","bundle":"https://pith.science/pith/Y34AZWCYFQTDIIISPENHJGCC6L/bundle.json","state":"https://pith.science/pith/Y34AZWCYFQTDIIISPENHJGCC6L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y34AZWCYFQTDIIISPENHJGCC6L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y34AZWCYFQTDIIISPENHJGCC6L","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":"9af08bb35193edd4d1ada32e8574e4521c773038366dd574e2002ed857001302","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T16:07:43Z","title_canon_sha256":"af58d89b74f7bb8cca5b6907909eba7e27b1b4525c472afd5eef29a181695a48"},"schema_version":"1.0","source":{"id":"2401.02330","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.02330","created_at":"2026-07-05T07:48:02Z"},{"alias_kind":"arxiv_version","alias_value":"2401.02330v4","created_at":"2026-07-05T07:48:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02330","created_at":"2026-07-05T07:48:02Z"},{"alias_kind":"pith_short_12","alias_value":"Y34AZWCYFQTD","created_at":"2026-07-05T07:48:02Z"},{"alias_kind":"pith_short_16","alias_value":"Y34AZWCYFQTDIIIS","created_at":"2026-07-05T07:48:02Z"},{"alias_kind":"pith_short_8","alias_value":"Y34AZWCY","created_at":"2026-07-05T07:48:02Z"}],"graph_snapshots":[{"event_id":"sha256:fb009dc8296b566c68724fe5f09fd4b86344b1b2e237fb5417febe0039c26a1f","target":"graph","created_at":"2026-07-05T07:48:02Z","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/2401.02330/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce LLaVA-$\\phi$ (LLaVA-Phi), an efficient multi-modal assistant that harnesses the power of the recently advanced small language model, Phi-2, to facilitate multi-modal dialogues. LLaVA-Phi marks a notable advancement in the realm of compact multi-modal models. It demonstrates that even smaller language models, with as few as 2.7B parameters, can effectively engage in intricate dialogues that integrate both textual and visual elements, provided they are trained with high-quality corpora. Our model delivers commendable performance on publicly available benchmarks that e","authors_text":"Jian Tang, Minjie Zhu, Ning Liu, Xiaofeng Mou, Yichen Zhu, Zhicai Ou","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T16:07:43Z","title":"LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02330","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":"sha256:91bacff112f41b404ff11d43e9c7c90de55704866b2aeb90051960afd41effe5","target":"record","created_at":"2026-07-05T07:48:02Z","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":"9af08bb35193edd4d1ada32e8574e4521c773038366dd574e2002ed857001302","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T16:07:43Z","title_canon_sha256":"af58d89b74f7bb8cca5b6907909eba7e27b1b4525c472afd5eef29a181695a48"},"schema_version":"1.0","source":{"id":"2401.02330","kind":"arxiv","version":4}},"canonical_sha256":"c6f80cd8582c26342112791a749842f2d77d4cbf9902b42d11397a9ecad48518","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6f80cd8582c26342112791a749842f2d77d4cbf9902b42d11397a9ecad48518","first_computed_at":"2026-07-05T07:48:02.328664Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:02.328664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tStESKtEPFpoQvgHcrmsgVwVNX8hPyay5bqkvWFjXcwkyrBKtLTThbJy6C18bcP2Bz4CrSk5B6Ki6e6bVotyAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:02.329129Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.02330","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91bacff112f41b404ff11d43e9c7c90de55704866b2aeb90051960afd41effe5","sha256:fb009dc8296b566c68724fe5f09fd4b86344b1b2e237fb5417febe0039c26a1f"],"state_sha256":"a6be30b4b5e6911603864f896e31909923e195844add13414573166f618d297b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O7h7Ddep6f8YvnxQ8jptigGaxsz0UtWKpR59AfqLJ0hOxZm5tLkVu1tvlQnq8bmNWdl1IU0kGF8MMC1cK/g0Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:26:08.068579Z","bundle_sha256":"811753c83ce971b16f320ed11358318b32e83d1b282f557d07279e6114ebbdc7"}}