{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5PAEBXSGZ5Z3TKXOYKZ23KAFQY","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":"f34d32dcf98ef62f45690e3400648e8b3dcee8b8f01ab09cb0e8485eacb98781","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T22:58:54Z","title_canon_sha256":"3032f3145cf685013ea58c0da0a494d4fc240d0e6bee04f6d4a5fd1ebb510874"},"schema_version":"1.0","source":{"id":"2607.03624","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03624","created_at":"2026-07-07T02:17:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03624v1","created_at":"2026-07-07T02:17:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03624","created_at":"2026-07-07T02:17:58Z"},{"alias_kind":"pith_short_12","alias_value":"5PAEBXSGZ5Z3","created_at":"2026-07-07T02:17:58Z"},{"alias_kind":"pith_short_16","alias_value":"5PAEBXSGZ5Z3TKXO","created_at":"2026-07-07T02:17:58Z"},{"alias_kind":"pith_short_8","alias_value":"5PAEBXSG","created_at":"2026-07-07T02:17:58Z"}],"graph_snapshots":[{"event_id":"sha256:c6bb4e9d6706cd4f11c9f29bc564249e6566afa713a53b901fe2332f11a28447","target":"graph","created_at":"2026-07-07T02:17:58Z","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/2607.03624/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper challenges the assumption that vision-language models (VLMs) require fixed patch-based 2D vision features. Analyzing fine-tuned vision encoders, we find that representations become increasingly abstract and less spatially coherent during VLM training. Notably, models trained with image-text alignment (such as SigLIP2) develop a small number of specialized tokens that effectively summarize global image content. Building on this, we introduce RADIO1D, which compresses images into a compact, variable-length 1D token sequence using multi-teacher knowledge distillation and an autoencoder","authors_text":"Andrew Tao, Bryan Catanzaro, Collin McCarthy, Eugene Khvedchenya, Greg Heinrich, Jan Kautz, Mike Ranzinger, Natan Bagrov, Pavlo Molchanov","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T22:58:54Z","title":"RADIO1D: Elastic Representations for Condensed Vision Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03624","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":"sha256:90def0b3e99de85bc4f6bb86c5e82e70fbc748eb06fd459d6950d9e9a40ba3ae","target":"record","created_at":"2026-07-07T02:17:58Z","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":"f34d32dcf98ef62f45690e3400648e8b3dcee8b8f01ab09cb0e8485eacb98781","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T22:58:54Z","title_canon_sha256":"3032f3145cf685013ea58c0da0a494d4fc240d0e6bee04f6d4a5fd1ebb510874"},"schema_version":"1.0","source":{"id":"2607.03624","kind":"arxiv","version":1}},"canonical_sha256":"ebc040de46cf73b9aaeec2b3ada80586229b5ce0f3a56999156863e89ded0b32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebc040de46cf73b9aaeec2b3ada80586229b5ce0f3a56999156863e89ded0b32","first_computed_at":"2026-07-07T02:17:58.005994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:17:58.005994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hYbFk7jz3HCOaUKDkZLnuhMidaFJdM+0zow50nSv9rNKT2A6ejwXnKyVZSYYQcnowF9Ak49SD1uDGTySV9lrCw==","signature_status":"signed_v1","signed_at":"2026-07-07T02:17:58.006946Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.03624","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90def0b3e99de85bc4f6bb86c5e82e70fbc748eb06fd459d6950d9e9a40ba3ae","sha256:c6bb4e9d6706cd4f11c9f29bc564249e6566afa713a53b901fe2332f11a28447"],"state_sha256":"4c7900485cdd1d6b4a3544df2e4c33350ed78d4944b2d7b307f6d1fbc8fe9cef"}