{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:72ZBC5UXZIJEDHX27O3PW7NKJJ","short_pith_number":"pith:72ZBC5UX","canonical_record":{"source":{"id":"2605.28820","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T17:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"4d6f1ecfaefc5096ea9ce6f883be5a410517c75862a6cd12e82133d08b7b7850","abstract_canon_sha256":"3cf8ed4b92da37c7c57901e782ab48fa65cde10beeda7e3508a931de4c0903da"},"schema_version":"1.0"},"canonical_sha256":"feb2117697ca12419efafbb6fb7daa4a623a241cd05e8d4c7a6132cfc33e7e67","source":{"kind":"arxiv","id":"2605.28820","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28820","created_at":"2026-05-28T02:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28820v1","created_at":"2026-05-28T02:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28820","created_at":"2026-05-28T02:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"72ZBC5UXZIJE","created_at":"2026-05-28T02:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"72ZBC5UXZIJEDHX2","created_at":"2026-05-28T02:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"72ZBC5UX","created_at":"2026-05-28T02:05:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:72ZBC5UXZIJEDHX27O3PW7NKJJ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.28820","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T17:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"4d6f1ecfaefc5096ea9ce6f883be5a410517c75862a6cd12e82133d08b7b7850","abstract_canon_sha256":"3cf8ed4b92da37c7c57901e782ab48fa65cde10beeda7e3508a931de4c0903da"},"schema_version":"1.0"},"canonical_sha256":"feb2117697ca12419efafbb6fb7daa4a623a241cd05e8d4c7a6132cfc33e7e67","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:05:04.733975Z","signature_b64":"royBmqKMaI3eOYRVUG+Y+1EN2EJSf8/3aY1QtjmqE4aUpLng6wJI05H7VFJiBQfaWKNjv427mpXdfz46DZuCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"feb2117697ca12419efafbb6fb7daa4a623a241cd05e8d4c7a6132cfc33e7e67","last_reissued_at":"2026-05-28T02:05:04.733582Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:05:04.733582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.28820","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T02:05:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U84zCJO1fDc3A1oII9zXNJanAFxIwQY+P1M2E+lsRgDAegkj0f7tFxZ7n1E+Lw1GCncsICqtLzfHYZMBNF72AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T22:04:32.799898Z"},"content_sha256":"a7f25cfd7915f8770bd0112de31f728a23a919709e4ee941dca11a030fb11b32","schema_version":"1.0","event_id":"sha256:a7f25cfd7915f8770bd0112de31f728a23a919709e4ee941dca11a030fb11b32"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:72ZBC5UXZIJEDHX27O3PW7NKJJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Pixels to Words -- Towards Native One-Vision Models at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Li, Dahua Lin, Haiwen Diao, HanMing Deng, Huchuan Lu, Jiahao Wang, Lei Yang, Lewei Lu, Linjun Dai, Mingxuan Li, Penghao Wu, Quan Wang, Silei Wu, Weichen Fan, Xuanyu Zheng, Yuanhan Zhang, Yue Zhu, Yuhao Dong, Yuwei Niu, Zhongang Cai, Ziwei Liu","submitted_at":"2026-05-27T17:59:55Z","abstract_excerpt":"Current vision-language models (VLMs) typically stitch together separate image encoders and language decoders via multi-stage alignment, a modular framework that inevitably fragments pixel-level signals across frames and scatters early pixel-word interactions. In parallel, native VLMs, despite impressive performance on single images, remain largely unexplored in multi-image, video understanding, and spatial intelligence. Hence, we introduce NEO-ov, a native foundation model that learns cross-frame and pixel-word correspondence end-to-end, without any external encoders, auxiliary adapters, or p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28820","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.28820/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T02:05:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4RU4Ki8zt9tj2LXF2wuI3EXvtZTQwy0eBy4DkYF3DPghqcSbH7inJJjeA1uf9Pp5AnswFDypMdYXIxyAdNf+Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T22:04:32.800285Z"},"content_sha256":"03f681e3ee516ebb277115ca5a8fb1192439e349e57aede813dde86583e0959b","schema_version":"1.0","event_id":"sha256:03f681e3ee516ebb277115ca5a8fb1192439e349e57aede813dde86583e0959b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/72ZBC5UXZIJEDHX27O3PW7NKJJ/bundle.json","state_url":"https://pith.science/pith/72ZBC5UXZIJEDHX27O3PW7NKJJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/72ZBC5UXZIJEDHX27O3PW7NKJJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-02T22:04:32Z","links":{"resolver":"https://pith.science/pith/72ZBC5UXZIJEDHX27O3PW7NKJJ","bundle":"https://pith.science/pith/72ZBC5UXZIJEDHX27O3PW7NKJJ/bundle.json","state":"https://pith.science/pith/72ZBC5UXZIJEDHX27O3PW7NKJJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/72ZBC5UXZIJEDHX27O3PW7NKJJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:72ZBC5UXZIJEDHX27O3PW7NKJJ","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":"3cf8ed4b92da37c7c57901e782ab48fa65cde10beeda7e3508a931de4c0903da","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T17:59:55Z","title_canon_sha256":"4d6f1ecfaefc5096ea9ce6f883be5a410517c75862a6cd12e82133d08b7b7850"},"schema_version":"1.0","source":{"id":"2605.28820","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28820","created_at":"2026-05-28T02:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28820v1","created_at":"2026-05-28T02:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28820","created_at":"2026-05-28T02:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"72ZBC5UXZIJE","created_at":"2026-05-28T02:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"72ZBC5UXZIJEDHX2","created_at":"2026-05-28T02:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"72ZBC5UX","created_at":"2026-05-28T02:05:04Z"}],"graph_snapshots":[{"event_id":"sha256:03f681e3ee516ebb277115ca5a8fb1192439e349e57aede813dde86583e0959b","target":"graph","created_at":"2026-05-28T02:05:04Z","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/2605.28820/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current vision-language models (VLMs) typically stitch together separate image encoders and language decoders via multi-stage alignment, a modular framework that inevitably fragments pixel-level signals across frames and scatters early pixel-word interactions. In parallel, native VLMs, despite impressive performance on single images, remain largely unexplored in multi-image, video understanding, and spatial intelligence. Hence, we introduce NEO-ov, a native foundation model that learns cross-frame and pixel-word correspondence end-to-end, without any external encoders, auxiliary adapters, or p","authors_text":"Bo Li, Dahua Lin, Haiwen Diao, HanMing Deng, Huchuan Lu, Jiahao Wang, Lei Yang, Lewei Lu, Linjun Dai, Mingxuan Li, Penghao Wu, Quan Wang, Silei Wu, Weichen Fan, Xuanyu Zheng, Yuanhan Zhang, Yue Zhu, Yuhao Dong, Yuwei Niu, Zhongang Cai, Ziwei Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T17:59:55Z","title":"From Pixels to Words -- Towards Native One-Vision Models at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28820","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:a7f25cfd7915f8770bd0112de31f728a23a919709e4ee941dca11a030fb11b32","target":"record","created_at":"2026-05-28T02:05:04Z","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":"3cf8ed4b92da37c7c57901e782ab48fa65cde10beeda7e3508a931de4c0903da","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T17:59:55Z","title_canon_sha256":"4d6f1ecfaefc5096ea9ce6f883be5a410517c75862a6cd12e82133d08b7b7850"},"schema_version":"1.0","source":{"id":"2605.28820","kind":"arxiv","version":1}},"canonical_sha256":"feb2117697ca12419efafbb6fb7daa4a623a241cd05e8d4c7a6132cfc33e7e67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"feb2117697ca12419efafbb6fb7daa4a623a241cd05e8d4c7a6132cfc33e7e67","first_computed_at":"2026-05-28T02:05:04.733582Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:05:04.733582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"royBmqKMaI3eOYRVUG+Y+1EN2EJSf8/3aY1QtjmqE4aUpLng6wJI05H7VFJiBQfaWKNjv427mpXdfz46DZuCBg==","signature_status":"signed_v1","signed_at":"2026-05-28T02:05:04.733975Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28820","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7f25cfd7915f8770bd0112de31f728a23a919709e4ee941dca11a030fb11b32","sha256:03f681e3ee516ebb277115ca5a8fb1192439e349e57aede813dde86583e0959b"],"state_sha256":"d12db4f3b04ae669149ec3eb5da7be11450a7a7e423ca203fc84793778786e31"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7ij/LcJcJOd7hXaBckqhAYKEnX+9Lpxrv9fOTbxS8b9Pc4epVizXBMuqxyDYtHQH3c6TDa2TleoqGpftc5F2BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T22:04:32.802482Z","bundle_sha256":"aa33dd466337e885124ab2d40939ae635e8950f8375c484b0e1bd0e7ec122698"}}