{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WISWEJMM6CPKXUJCMYXFZ7PZPZ","short_pith_number":"pith:WISWEJMM","canonical_record":{"source":{"id":"2405.11850","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T07:53:41Z","cross_cats_sorted":[],"title_canon_sha256":"80fbb29128f5a665c323c0c51c7eae14cbf2191ddbd47ddef4659d375fb884dd","abstract_canon_sha256":"026aa67f8cd3dc00fa4e0ace2f9e12635d11abe23e9310b6ab67900c35caaeff"},"schema_version":"1.0"},"canonical_sha256":"b22562258cf09eabd122662e5cfdf97e42fdc230e3080152a92a8d24c7737cac","source":{"kind":"arxiv","id":"2405.11850","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11850","created_at":"2026-07-05T08:20:56Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11850v1","created_at":"2026-07-05T08:20:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11850","created_at":"2026-07-05T08:20:56Z"},{"alias_kind":"pith_short_12","alias_value":"WISWEJMM6CPK","created_at":"2026-07-05T08:20:56Z"},{"alias_kind":"pith_short_16","alias_value":"WISWEJMM6CPKXUJC","created_at":"2026-07-05T08:20:56Z"},{"alias_kind":"pith_short_8","alias_value":"WISWEJMM","created_at":"2026-07-05T08:20:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WISWEJMM6CPKXUJCMYXFZ7PZPZ","target":"record","payload":{"canonical_record":{"source":{"id":"2405.11850","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T07:53:41Z","cross_cats_sorted":[],"title_canon_sha256":"80fbb29128f5a665c323c0c51c7eae14cbf2191ddbd47ddef4659d375fb884dd","abstract_canon_sha256":"026aa67f8cd3dc00fa4e0ace2f9e12635d11abe23e9310b6ab67900c35caaeff"},"schema_version":"1.0"},"canonical_sha256":"b22562258cf09eabd122662e5cfdf97e42fdc230e3080152a92a8d24c7737cac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:56.860200Z","signature_b64":"20pvSY738g9zQTXmqDKTdPRpvX5on/4nDSp7rMQAWN3hz+Qf9biDbLCtNvPqbrOxY9QQq6gH9T+JBJGFs0FKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b22562258cf09eabd122662e5cfdf97e42fdc230e3080152a92a8d24c7737cac","last_reissued_at":"2026-07-05T08:20:56.859766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:56.859766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.11850","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":"2026-07-05T08:20:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DnPjGGTNEuqflN5U+RC3ssgh5gTo6Hb8UwnIbgCuc3kx0Y27fuAWNkCkdzGEHcNID39O8E3m+7iDvsFZygq+Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:35:01.753387Z"},"content_sha256":"2b960e7579afb3104e0e0864e15e80a9fd20683a0f96951e4cff7b2c9a95716b","schema_version":"1.0","event_id":"sha256:2b960e7579afb3104e0e0864e15e80a9fd20683a0f96951e4cff7b2c9a95716b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WISWEJMM6CPKXUJCMYXFZ7PZPZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking Overlooked Aspects in Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Le Tian, Xiao Zhou, Yuan Liu","submitted_at":"2024-05-20T07:53:41Z","abstract_excerpt":"Recent advancements in large vision-language models (LVLMs), such as GPT4-V and LLaVA, have been substantial. LLaVA's modular architecture, in particular, offers a blend of simplicity and efficiency. Recent works mainly focus on introducing more pre-training and instruction tuning data to improve model's performance. This paper delves into the often-neglected aspects of data efficiency during pre-training and the selection process for instruction tuning datasets. Our research indicates that merely increasing the size of pre-training data does not guarantee improved performance and may, in fact"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11850","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/2405.11850/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":"2026-07-05T08:20:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V+TN78D/Wef5mCgd9qUalDONq9Um5v4cHeLueM+IPX9Jt2owKxo/mVdDFROYs53fkpVY00dWQA1JvQXIVz9aAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:35:01.754219Z"},"content_sha256":"5a611001912e633b7af03ca39b40ccf251019d0271ff2142d0ba1c451bf037cf","schema_version":"1.0","event_id":"sha256:5a611001912e633b7af03ca39b40ccf251019d0271ff2142d0ba1c451bf037cf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WISWEJMM6CPKXUJCMYXFZ7PZPZ/bundle.json","state_url":"https://pith.science/pith/WISWEJMM6CPKXUJCMYXFZ7PZPZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WISWEJMM6CPKXUJCMYXFZ7PZPZ/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":"2026-08-14T22:35:01Z","links":{"resolver":"https://pith.science/pith/WISWEJMM6CPKXUJCMYXFZ7PZPZ","bundle":"https://pith.science/pith/WISWEJMM6CPKXUJCMYXFZ7PZPZ/bundle.json","state":"https://pith.science/pith/WISWEJMM6CPKXUJCMYXFZ7PZPZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WISWEJMM6CPKXUJCMYXFZ7PZPZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WISWEJMM6CPKXUJCMYXFZ7PZPZ","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":"026aa67f8cd3dc00fa4e0ace2f9e12635d11abe23e9310b6ab67900c35caaeff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T07:53:41Z","title_canon_sha256":"80fbb29128f5a665c323c0c51c7eae14cbf2191ddbd47ddef4659d375fb884dd"},"schema_version":"1.0","source":{"id":"2405.11850","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11850","created_at":"2026-07-05T08:20:56Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11850v1","created_at":"2026-07-05T08:20:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11850","created_at":"2026-07-05T08:20:56Z"},{"alias_kind":"pith_short_12","alias_value":"WISWEJMM6CPK","created_at":"2026-07-05T08:20:56Z"},{"alias_kind":"pith_short_16","alias_value":"WISWEJMM6CPKXUJC","created_at":"2026-07-05T08:20:56Z"},{"alias_kind":"pith_short_8","alias_value":"WISWEJMM","created_at":"2026-07-05T08:20:56Z"}],"graph_snapshots":[{"event_id":"sha256:5a611001912e633b7af03ca39b40ccf251019d0271ff2142d0ba1c451bf037cf","target":"graph","created_at":"2026-07-05T08:20:56Z","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/2405.11850/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large vision-language models (LVLMs), such as GPT4-V and LLaVA, have been substantial. LLaVA's modular architecture, in particular, offers a blend of simplicity and efficiency. Recent works mainly focus on introducing more pre-training and instruction tuning data to improve model's performance. This paper delves into the often-neglected aspects of data efficiency during pre-training and the selection process for instruction tuning datasets. Our research indicates that merely increasing the size of pre-training data does not guarantee improved performance and may, in fact","authors_text":"Jie Zhou, Le Tian, Xiao Zhou, Yuan Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T07:53:41Z","title":"Rethinking Overlooked Aspects in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11850","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":"sha256:2b960e7579afb3104e0e0864e15e80a9fd20683a0f96951e4cff7b2c9a95716b","target":"record","created_at":"2026-07-05T08:20:56Z","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":"026aa67f8cd3dc00fa4e0ace2f9e12635d11abe23e9310b6ab67900c35caaeff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T07:53:41Z","title_canon_sha256":"80fbb29128f5a665c323c0c51c7eae14cbf2191ddbd47ddef4659d375fb884dd"},"schema_version":"1.0","source":{"id":"2405.11850","kind":"arxiv","version":1}},"canonical_sha256":"b22562258cf09eabd122662e5cfdf97e42fdc230e3080152a92a8d24c7737cac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b22562258cf09eabd122662e5cfdf97e42fdc230e3080152a92a8d24c7737cac","first_computed_at":"2026-07-05T08:20:56.859766Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:20:56.859766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"20pvSY738g9zQTXmqDKTdPRpvX5on/4nDSp7rMQAWN3hz+Qf9biDbLCtNvPqbrOxY9QQq6gH9T+JBJGFs0FKAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:20:56.860200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.11850","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b960e7579afb3104e0e0864e15e80a9fd20683a0f96951e4cff7b2c9a95716b","sha256:5a611001912e633b7af03ca39b40ccf251019d0271ff2142d0ba1c451bf037cf"],"state_sha256":"c03aa70d055aa738fe3c171facfdc182f3b2b058909311f06753cb9b1de83aee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IGJNpMIabRMygAxenV/KLlPZ2DwKIGRdOofhwtoMsefTXIfhplznieXh1FWuueYguMeWbYON0lGu2qteBtreBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T22:35:01.765406Z","bundle_sha256":"a3a3d4346ea87412baa659928568523908826556939664288542a7f3d816d39a"}}