{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4JYA3CNBDK7PD5727PUVN3BPHM","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":"a8c6facaf40c4f10a5905a000fcf592af65dde8ecdba83be9ac8d2d4663a4e5d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T17:59:56Z","title_canon_sha256":"aadd50d7a6197f642cc33b4edcdbf6aeb7ae29c0accbc73bce4778ed453bd4f6"},"schema_version":"1.0","source":{"id":"2608.09931","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09931","created_at":"2026-08-11T02:25:29Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09931v1","created_at":"2026-08-11T02:25:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09931","created_at":"2026-08-11T02:25:29Z"},{"alias_kind":"pith_short_12","alias_value":"4JYA3CNBDK7P","created_at":"2026-08-11T02:25:29Z"},{"alias_kind":"pith_short_16","alias_value":"4JYA3CNBDK7PD572","created_at":"2026-08-11T02:25:29Z"},{"alias_kind":"pith_short_8","alias_value":"4JYA3CNB","created_at":"2026-08-11T02:25:29Z"}],"graph_snapshots":[{"event_id":"sha256:2b51c2dfc802a91f00ff895a28ce7d65e1d8c73b6bdf0c885c72014c08e9e6da","target":"graph","created_at":"2026-08-11T02:25:29Z","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/2608.09931/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-improvement for multimodal large language models (MLLMs) is typically driven by reward-based methods that provide only coarse scalar feedback. Distillation offers a richer alternative through dense token-level supervision, but in the visual domain it usually depends on privileged context constructed using external annotations and tools, or stronger models. We introduce \\textbf{CVPD} (Contrastive Counterfactual Visual Process Distillation), which, to the best of our knowledge, is the first fully self-contained framework for dense, on-policy, token-level visual self-distillation for MLLMs. ","authors_text":"Abdelrahman Shaker, Omkar Thawakar, Rao Muhammad Anwer, Ritesh Thawkar, Shravan Venkatraman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T17:59:56Z","title":"Perception Before Supervision: Self-Contained Visual Distillation from Counterfactual Blind Spots"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09931","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":"sha256:8410dc1c9158f6196a3296aa88ce641df04095d6b0b78d8e61203e88024fedfa","target":"record","created_at":"2026-08-11T02:25:29Z","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":"a8c6facaf40c4f10a5905a000fcf592af65dde8ecdba83be9ac8d2d4663a4e5d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T17:59:56Z","title_canon_sha256":"aadd50d7a6197f642cc33b4edcdbf6aeb7ae29c0accbc73bce4778ed453bd4f6"},"schema_version":"1.0","source":{"id":"2608.09931","kind":"arxiv","version":1}},"canonical_sha256":"e2700d89a11abef1f7fafbe956ec2f3b1c5b2f4dff7bfb847fef843e40ec14a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2700d89a11abef1f7fafbe956ec2f3b1c5b2f4dff7bfb847fef843e40ec14a2","first_computed_at":"2026-08-11T02:25:29.291909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:25:29.291909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KOglfVX1JPyytAEJVWRDvy8dUkJsBrl8eAfA2X/FtmeMl6NI6SIyDtbglt8EWNpe42wT6D7W64KiVllOjaq/Bg==","signature_status":"signed_v1","signed_at":"2026-08-11T02:25:29.293442Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09931","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8410dc1c9158f6196a3296aa88ce641df04095d6b0b78d8e61203e88024fedfa","sha256:2b51c2dfc802a91f00ff895a28ce7d65e1d8c73b6bdf0c885c72014c08e9e6da"],"state_sha256":"158bcc65c1cbafd35146fb3b8a0c85fd6399aadf99ca937d5df7b15ec919f87c"}