{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DAZQVSORILK7O2F27XLBX2TX4K","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":"bb625216fff5635f6634fe6c6726ddc616688cd617adce7be5c4a9c6e96f4adb","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T13:23:33Z","title_canon_sha256":"8fe0a927790d097073803c7140e8841881731ac13f5e02b8e9661e81ad7891f2"},"schema_version":"1.0","source":{"id":"2608.00013","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00013","created_at":"2026-08-04T00:31:38Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00013v1","created_at":"2026-08-04T00:31:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00013","created_at":"2026-08-04T00:31:38Z"},{"alias_kind":"pith_short_12","alias_value":"DAZQVSORILK7","created_at":"2026-08-04T00:31:38Z"},{"alias_kind":"pith_short_16","alias_value":"DAZQVSORILK7O2F2","created_at":"2026-08-04T00:31:38Z"},{"alias_kind":"pith_short_8","alias_value":"DAZQVSOR","created_at":"2026-08-04T00:31:38Z"}],"graph_snapshots":[{"event_id":"sha256:23f0e8a05fb5b82d48a74d6bade4b57253915ffe41b42c0f1712d1dbc0b21e5c","target":"graph","created_at":"2026-08-04T00:31:38Z","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/2608.00013/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Choosing the right large language model (LLM) backbone is the most consequential decision when building a vision-language model (VLM), yet it remains fundamentally unprincipled: compute-based scaling laws fail to generalize across model families, and no framework exists for directly predicting VLM performance before training begins. We propose the Capability-Driven Multimodal Scaling Law, the first cross-family framework that predicts VLM benchmark accuracy from directly observable textual capability. Given a low-dimensional capability score $S$ extracted from LLM textual benchmarks via PCA, w","authors_text":"Borun Chen, Jingang Wang, Qiang Wang, Shanglin Lei, Xunliang Cai, Zhengyu Chen, Ziran Li","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T13:23:33Z","title":"What Transfers from Text to Vision? Capability Scaling Laws and Transfer Dynamics for VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00013","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":"sha256:608ff9db10d155a5ba0b4261f667725cf4f8507756609c3876f98592593b0bd4","target":"record","created_at":"2026-08-04T00:31:38Z","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":"bb625216fff5635f6634fe6c6726ddc616688cd617adce7be5c4a9c6e96f4adb","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T13:23:33Z","title_canon_sha256":"8fe0a927790d097073803c7140e8841881731ac13f5e02b8e9661e81ad7891f2"},"schema_version":"1.0","source":{"id":"2608.00013","kind":"arxiv","version":1}},"canonical_sha256":"18330ac9d142d5f768bafdd61bea77e2a018e0b87a4d9531d9f26b3e0713f831","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18330ac9d142d5f768bafdd61bea77e2a018e0b87a4d9531d9f26b3e0713f831","first_computed_at":"2026-08-04T00:31:38.507023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T00:31:38.507023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XAhhXyUW/tBBnnwzOI6CNoLJkIk4NDsxkcnMGp9Yyf0UgMYjhMovidnAKZkIuupQPktz66NRpiK7zDtxoL4ICg==","signature_status":"signed_v1","signed_at":"2026-08-04T00:31:38.508462Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00013","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:608ff9db10d155a5ba0b4261f667725cf4f8507756609c3876f98592593b0bd4","sha256:23f0e8a05fb5b82d48a74d6bade4b57253915ffe41b42c0f1712d1dbc0b21e5c"],"state_sha256":"a5d22d7ea09fc18461bba807ff039ff05d5725546f8aa37aa2c77432743ee606"}