{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KKZF4YNQ3KYICDAS6MEUSYNIDJ","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":"689532b646399c6ad156f4a78f38838de6230f0d1ba40593baedfc11f7fe2d32","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T07:20:54Z","title_canon_sha256":"69e000bf06851143928102be38dd45b179939d1e08fd5a8086e67d723ccae85c"},"schema_version":"1.0","source":{"id":"2504.12316","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12316","created_at":"2026-07-05T10:50:13Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12316v1","created_at":"2026-07-05T10:50:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12316","created_at":"2026-07-05T10:50:13Z"},{"alias_kind":"pith_short_12","alias_value":"KKZF4YNQ3KYI","created_at":"2026-07-05T10:50:13Z"},{"alias_kind":"pith_short_16","alias_value":"KKZF4YNQ3KYICDAS","created_at":"2026-07-05T10:50:13Z"},{"alias_kind":"pith_short_8","alias_value":"KKZF4YNQ","created_at":"2026-07-05T10:50:13Z"}],"graph_snapshots":[{"event_id":"sha256:2f1ae06d345011c5dfca7eaa5496d6ece528b64dea452261cec1d8a5b334b833","target":"graph","created_at":"2026-07-05T10:50:13Z","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/2504.12316/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data curation plays a crucial role in training powerful Visual Language Models (VLMs). In this work, we introduce the concept of Data Metabolism and present our data-centric framework to build VLMs throughout the development lifecycle. Starting from a standard model architecture, we discuss and provide insights into two crucial development steps: data curation and iteration, forming a closed-loop system that continuously improves model performance. We show a detailed codebook on how to process existing massive datasets and build user-specific data flywheel. As a demonstration, we release a VLM","authors_text":"Chenxi Sun, Fanheng Kong, Fuzheng Zhang, Hongzhi Zhang, Jiakang Wang, Jingyuan Zhang, Qi Wang, Xingguang Ji, Yahui Liu, Zhou Haonan","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T07:20:54Z","title":"Data Metabolism: An Efficient Data Design Schema For Vision Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12316","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":"sha256:9cbd8d3949fc9a02f055c664d0494450a7872f56d5631b3356a80dd0d146a563","target":"record","created_at":"2026-07-05T10:50:13Z","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":"689532b646399c6ad156f4a78f38838de6230f0d1ba40593baedfc11f7fe2d32","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T07:20:54Z","title_canon_sha256":"69e000bf06851143928102be38dd45b179939d1e08fd5a8086e67d723ccae85c"},"schema_version":"1.0","source":{"id":"2504.12316","kind":"arxiv","version":1}},"canonical_sha256":"52b25e61b0dab0810c12f3094961a81a6b0f1753f33066f3eca1165613656d8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52b25e61b0dab0810c12f3094961a81a6b0f1753f33066f3eca1165613656d8f","first_computed_at":"2026-07-05T10:50:13.968221Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:13.968221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G04sP5TK/SY7aL4oAZjpIV2ZSJNN4KWwNvxtlvatbWUGr7BEo6+9NkH0I2JoG129pmI8DxKK0B9WJv4IALJxBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:13.968766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.12316","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9cbd8d3949fc9a02f055c664d0494450a7872f56d5631b3356a80dd0d146a563","sha256:2f1ae06d345011c5dfca7eaa5496d6ece528b64dea452261cec1d8a5b334b833"],"state_sha256":"25e72c26b257cee27bc69097c19e290407f1bc5b894e998397e3d1563c9cde83"}