{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VBZ37CDRQCY33AH57HY3QOCQHS","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":"b73ec25533503fb3756ee84791f254df2f0cfb28240a598c99140791b86c2112","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-27T16:32:12Z","title_canon_sha256":"cfb6c4e6a44fef97354c3965ebecaff161bd2ae498640e9fe056bbdde2fc7304"},"schema_version":"1.0","source":{"id":"2510.23497","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.23497","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"2510.23497v3","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.23497","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"VBZ37CDRQCY3","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"pith_short_16","alias_value":"VBZ37CDRQCY33AH5","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"pith_short_8","alias_value":"VBZ37CDR","created_at":"2026-06-05T00:13:44Z"}],"graph_snapshots":[{"event_id":"sha256:a27da63b14835ef2de9844dd9872758c1f230f10fdc79c6d354115e722a73796","target":"graph","created_at":"2026-06-05T00:13:44Z","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/2510.23497/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training vision-language models (VLMs) for complex reasoning remains a challenging task, i.a. due to the scarcity of high-quality image-text reasoning data. Conversely, text-based reasoning resources are abundant and scalable, but it is still an open question how to leveraging them for VLM reasoning. To address this problem, we propose VOLD, a framework to transfer reasoning capabilities from text-only teacher models to VLM student models. To this end, VOLD combines reinforcement learning via Group Relative Policy Optimization (GRPO) with on-policy distillation, which allows the student reason","authors_text":"Cordelia Schmid, Hilde Kuehne, Walid Bousselham","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-27T16:32:12Z","title":"VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.23497","kind":"arxiv","version":3},"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":"sha256:67e7d1c62aeee8f62c9ccd5c8626a028a4b1e8247ee58831b1f9170af799a921","target":"record","created_at":"2026-06-05T00:13:44Z","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":"b73ec25533503fb3756ee84791f254df2f0cfb28240a598c99140791b86c2112","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-27T16:32:12Z","title_canon_sha256":"cfb6c4e6a44fef97354c3965ebecaff161bd2ae498640e9fe056bbdde2fc7304"},"schema_version":"1.0","source":{"id":"2510.23497","kind":"arxiv","version":3}},"canonical_sha256":"a873bf887180b1bd80fdf9f1b838503c8b8437645d7fceb0d55f6a5168e7a552","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a873bf887180b1bd80fdf9f1b838503c8b8437645d7fceb0d55f6a5168e7a552","first_computed_at":"2026-06-05T00:13:44.139186Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T00:13:44.139186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2R0po+DVl4sKUXBBuqhyh6MsHGT1ZxjZkrMWNhUq0rfJhnI7RDkIkAZXRetKTR5gYbuLuklR9NtJx+xRvQKICw==","signature_status":"signed_v1","signed_at":"2026-06-05T00:13:44.140079Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.23497","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67e7d1c62aeee8f62c9ccd5c8626a028a4b1e8247ee58831b1f9170af799a921","sha256:a27da63b14835ef2de9844dd9872758c1f230f10fdc79c6d354115e722a73796"],"state_sha256":"e9b3bbc0709b726d8ef9620a720ebd0e8e001ecd15896068791b3d16f08a10c8"}