{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GGGBZ7PU3RG66R6P6FGGDYAMNS","short_pith_number":"pith:GGGBZ7PU","canonical_record":{"source":{"id":"2605.25952","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T15:28:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4cc62f063fb1484e423eaf1c5e73930c6c411243e3a3059132b0c72fa087e9d2","abstract_canon_sha256":"48b8a720c0d5245284e35f01b72d842be887cea8b575b059060983af67290b20"},"schema_version":"1.0"},"canonical_sha256":"318c1cfdf4dc4def47cff14c61e00c6cb4b77f42fa679100b715831481d9856a","source":{"kind":"arxiv","id":"2605.25952","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25952","created_at":"2026-05-26T02:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25952v1","created_at":"2026-05-26T02:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25952","created_at":"2026-05-26T02:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"GGGBZ7PU3RG6","created_at":"2026-05-26T02:05:19Z"},{"alias_kind":"pith_short_16","alias_value":"GGGBZ7PU3RG66R6P","created_at":"2026-05-26T02:05:19Z"},{"alias_kind":"pith_short_8","alias_value":"GGGBZ7PU","created_at":"2026-05-26T02:05:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GGGBZ7PU3RG66R6P6FGGDYAMNS","target":"record","payload":{"canonical_record":{"source":{"id":"2605.25952","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T15:28:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4cc62f063fb1484e423eaf1c5e73930c6c411243e3a3059132b0c72fa087e9d2","abstract_canon_sha256":"48b8a720c0d5245284e35f01b72d842be887cea8b575b059060983af67290b20"},"schema_version":"1.0"},"canonical_sha256":"318c1cfdf4dc4def47cff14c61e00c6cb4b77f42fa679100b715831481d9856a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:19.889244Z","signature_b64":"zfHUwi89Q0i5TfIMjHZnDYcL6AuL6urYA8WKI+pjw0A4y+CtlLBufSRgjYzLoUduaiO9lyjX/aOvQ4jIochODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"318c1cfdf4dc4def47cff14c61e00c6cb4b77f42fa679100b715831481d9856a","last_reissued_at":"2026-05-26T02:05:19.888595Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:19.888595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.25952","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":"2026-05-26T02:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BZdbf0H32Kpe9OGf/OWt7PULwVmjDKpdgXw9fuvDoA54zHKLOdvhbEgh5/brjEbbfIalpkCXdeggfb7+evdUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T12:12:30.209966Z"},"content_sha256":"62c230743c6a71823268c5a7d2ba0e72148277db4cf7ef3a2e7a288024b189a9","schema_version":"1.0","event_id":"sha256:62c230743c6a71823268c5a7d2ba0e72148277db4cf7ef3a2e7a288024b189a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GGGBZ7PU3RG66R6P6FGGDYAMNS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VEN-VL: A Visual Ensemble MoE Framework for Effective and Efficient Multi-Modal Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Xiao-Ping Zhang, Yinghao Wu, Yiyao Yu, Yujiu Yang, Zhaojian Yu, Zhuoyan Luo","submitted_at":"2026-05-25T15:28:48Z","abstract_excerpt":"Despite the remarkable progress achieved by recent efficient methods in accelerating multimodal understanding, they still suffer from noticeable performance degradation. Their emphasis on the high compression ratio of a single visual clue and reliance on the heuristic pruning strategy with coarse attention alignment incurs a bottleneck on the information capacity and density of visual tokens. Addressing this limitation, we propose VEN-VL, a visual ensemble MoE framework for effective and efficient perception following the enrich then compact principle. Specifically, we first enrich the informa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25952","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/2605.25952/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":"2026-05-26T02:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gd0TYGjjwQ9lGqB4CUA6pPei95TcPnml/JRUBdKfRuj4r+xyekeB0nFe73jeR74aJLe9jKKNIPWrC0Caj2U1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T12:12:30.210351Z"},"content_sha256":"fca002abf2b2c6e056cc283e788257fc68dfd208a58830a9aefa62ca80a5c83a","schema_version":"1.0","event_id":"sha256:fca002abf2b2c6e056cc283e788257fc68dfd208a58830a9aefa62ca80a5c83a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GGGBZ7PU3RG66R6P6FGGDYAMNS/bundle.json","state_url":"https://pith.science/pith/GGGBZ7PU3RG66R6P6FGGDYAMNS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GGGBZ7PU3RG66R6P6FGGDYAMNS/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":"2026-06-04T12:12:30Z","links":{"resolver":"https://pith.science/pith/GGGBZ7PU3RG66R6P6FGGDYAMNS","bundle":"https://pith.science/pith/GGGBZ7PU3RG66R6P6FGGDYAMNS/bundle.json","state":"https://pith.science/pith/GGGBZ7PU3RG66R6P6FGGDYAMNS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GGGBZ7PU3RG66R6P6FGGDYAMNS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GGGBZ7PU3RG66R6P6FGGDYAMNS","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":"48b8a720c0d5245284e35f01b72d842be887cea8b575b059060983af67290b20","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T15:28:48Z","title_canon_sha256":"4cc62f063fb1484e423eaf1c5e73930c6c411243e3a3059132b0c72fa087e9d2"},"schema_version":"1.0","source":{"id":"2605.25952","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25952","created_at":"2026-05-26T02:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25952v1","created_at":"2026-05-26T02:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25952","created_at":"2026-05-26T02:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"GGGBZ7PU3RG6","created_at":"2026-05-26T02:05:19Z"},{"alias_kind":"pith_short_16","alias_value":"GGGBZ7PU3RG66R6P","created_at":"2026-05-26T02:05:19Z"},{"alias_kind":"pith_short_8","alias_value":"GGGBZ7PU","created_at":"2026-05-26T02:05:19Z"}],"graph_snapshots":[{"event_id":"sha256:fca002abf2b2c6e056cc283e788257fc68dfd208a58830a9aefa62ca80a5c83a","target":"graph","created_at":"2026-05-26T02:05:19Z","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/2605.25952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the remarkable progress achieved by recent efficient methods in accelerating multimodal understanding, they still suffer from noticeable performance degradation. Their emphasis on the high compression ratio of a single visual clue and reliance on the heuristic pruning strategy with coarse attention alignment incurs a bottleneck on the information capacity and density of visual tokens. Addressing this limitation, we propose VEN-VL, a visual ensemble MoE framework for effective and efficient perception following the enrich then compact principle. Specifically, we first enrich the informa","authors_text":"Xiao-Ping Zhang, Yinghao Wu, Yiyao Yu, Yujiu Yang, Zhaojian Yu, Zhuoyan Luo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T15:28:48Z","title":"VEN-VL: A Visual Ensemble MoE Framework for Effective and Efficient Multi-Modal Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25952","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":"sha256:62c230743c6a71823268c5a7d2ba0e72148277db4cf7ef3a2e7a288024b189a9","target":"record","created_at":"2026-05-26T02:05:19Z","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":"48b8a720c0d5245284e35f01b72d842be887cea8b575b059060983af67290b20","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T15:28:48Z","title_canon_sha256":"4cc62f063fb1484e423eaf1c5e73930c6c411243e3a3059132b0c72fa087e9d2"},"schema_version":"1.0","source":{"id":"2605.25952","kind":"arxiv","version":1}},"canonical_sha256":"318c1cfdf4dc4def47cff14c61e00c6cb4b77f42fa679100b715831481d9856a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"318c1cfdf4dc4def47cff14c61e00c6cb4b77f42fa679100b715831481d9856a","first_computed_at":"2026-05-26T02:05:19.888595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:19.888595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zfHUwi89Q0i5TfIMjHZnDYcL6AuL6urYA8WKI+pjw0A4y+CtlLBufSRgjYzLoUduaiO9lyjX/aOvQ4jIochODQ==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:19.889244Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25952","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62c230743c6a71823268c5a7d2ba0e72148277db4cf7ef3a2e7a288024b189a9","sha256:fca002abf2b2c6e056cc283e788257fc68dfd208a58830a9aefa62ca80a5c83a"],"state_sha256":"e562d5fe9b26bdb8be32112d375ab4f15e0f897db338999c93c4847e922766d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ltr6L4ONwf4eqirfhicUE3wJtR3JoqVIKKNKnXizxbZz4mX8u1M6s/Moq16C5Vy4/TB+9KaFedfLiEGs3wGQCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T12:12:30.212259Z","bundle_sha256":"5ef41134aa811a35ba4fc0aa0f3cef7b5782fa6d49b761ced7a56e05611ee7cc"}}