{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2USCKC2LZKA3MOMDZ6NCCUTFCT","short_pith_number":"pith:2USCKC2L","canonical_record":{"source":{"id":"2501.01709","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T09:10:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ba6370fdeaf3b95f31be0d1a9b9432fce4bc6530acfd8f9c87b1a598578b22d0","abstract_canon_sha256":"90a0313016e547018248c0048bcf55fcc15e87cf53c35f0711210cc03788e09b"},"schema_version":"1.0"},"canonical_sha256":"d524250b4bca81b63983cf9a21526514eba3d4d50b7736b3a11519e54651e2e4","source":{"kind":"arxiv","id":"2501.01709","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01709","created_at":"2026-07-05T10:33:42Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01709v3","created_at":"2026-07-05T10:33:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01709","created_at":"2026-07-05T10:33:42Z"},{"alias_kind":"pith_short_12","alias_value":"2USCKC2LZKA3","created_at":"2026-07-05T10:33:42Z"},{"alias_kind":"pith_short_16","alias_value":"2USCKC2LZKA3MOMD","created_at":"2026-07-05T10:33:42Z"},{"alias_kind":"pith_short_8","alias_value":"2USCKC2L","created_at":"2026-07-05T10:33:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2USCKC2LZKA3MOMDZ6NCCUTFCT","target":"record","payload":{"canonical_record":{"source":{"id":"2501.01709","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T09:10:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ba6370fdeaf3b95f31be0d1a9b9432fce4bc6530acfd8f9c87b1a598578b22d0","abstract_canon_sha256":"90a0313016e547018248c0048bcf55fcc15e87cf53c35f0711210cc03788e09b"},"schema_version":"1.0"},"canonical_sha256":"d524250b4bca81b63983cf9a21526514eba3d4d50b7736b3a11519e54651e2e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:42.121155Z","signature_b64":"2og7wqkulcHxW9qefA75LQHALcwOEZ8qxpcZRGLbBaOTMlGTs8OSWywP2vwZCXxUYhAQZv7KOc4aKx6AQmuECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d524250b4bca81b63983cf9a21526514eba3d4d50b7736b3a11519e54651e2e4","last_reissued_at":"2026-07-05T10:33:42.120674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:42.120674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.01709","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:33:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4DWtCvWL7OgOt9UOpMnr4k76xg1i4Gdvoh8iXFSj1gn+cPRry2I65nKVEye5tRG8AKcj1PRqdbgjo8fgTSRFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T06:28:08.182494Z"},"content_sha256":"62b383da6547d7d83716d586cefdf8cb440176e1844c4d42f811a6e8c6f93b7b","schema_version":"1.0","event_id":"sha256:62b383da6547d7d83716d586cefdf8cb440176e1844c4d42f811a6e8c6f93b7b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2USCKC2LZKA3MOMDZ6NCCUTFCT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiajun Cao, Ming Lu, Ningning Ma, Qizhe Zhang, Ruichuan An, Shanghang Zhang, Tao Huang, Yuan Zhang","submitted_at":"2025-01-03T09:10:34Z","abstract_excerpt":"Visual encoders are fundamental components in vision-language models (VLMs), each showcasing unique strengths derived from various pre-trained visual foundation models. To leverage the various capabilities of these encoders, recent studies incorporate multiple encoders within a single VLM, leading to a considerable increase in computational cost. In this paper, we present Mixture-of-Visual-Encoder Knowledge Distillation (MoVE-KD), a novel framework that distills the unique proficiencies of multiple vision encoders into a single, efficient encoder model. Specifically, to mitigate conflicts and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01709","kind":"arxiv","version":3},"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/2501.01709/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":"2026-07-05T10:33:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HDJs+UDmDUZYUbXo0QUOrWfcOD9+BDHiivypIGYXxo7GmiqHkUOpvApEotYQcYFivGEYYv+dhv7hIvD44EssCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T06:28:08.183385Z"},"content_sha256":"41d3b299049f65bb83a01a1932b4607191874dcc60cd1d52eae2de51bd40af18","schema_version":"1.0","event_id":"sha256:41d3b299049f65bb83a01a1932b4607191874dcc60cd1d52eae2de51bd40af18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2USCKC2LZKA3MOMDZ6NCCUTFCT/bundle.json","state_url":"https://pith.science/pith/2USCKC2LZKA3MOMDZ6NCCUTFCT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2USCKC2LZKA3MOMDZ6NCCUTFCT/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":"2026-08-13T06:28:08Z","links":{"resolver":"https://pith.science/pith/2USCKC2LZKA3MOMDZ6NCCUTFCT","bundle":"https://pith.science/pith/2USCKC2LZKA3MOMDZ6NCCUTFCT/bundle.json","state":"https://pith.science/pith/2USCKC2LZKA3MOMDZ6NCCUTFCT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2USCKC2LZKA3MOMDZ6NCCUTFCT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2USCKC2LZKA3MOMDZ6NCCUTFCT","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":"90a0313016e547018248c0048bcf55fcc15e87cf53c35f0711210cc03788e09b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T09:10:34Z","title_canon_sha256":"ba6370fdeaf3b95f31be0d1a9b9432fce4bc6530acfd8f9c87b1a598578b22d0"},"schema_version":"1.0","source":{"id":"2501.01709","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01709","created_at":"2026-07-05T10:33:42Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01709v3","created_at":"2026-07-05T10:33:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01709","created_at":"2026-07-05T10:33:42Z"},{"alias_kind":"pith_short_12","alias_value":"2USCKC2LZKA3","created_at":"2026-07-05T10:33:42Z"},{"alias_kind":"pith_short_16","alias_value":"2USCKC2LZKA3MOMD","created_at":"2026-07-05T10:33:42Z"},{"alias_kind":"pith_short_8","alias_value":"2USCKC2L","created_at":"2026-07-05T10:33:42Z"}],"graph_snapshots":[{"event_id":"sha256:41d3b299049f65bb83a01a1932b4607191874dcc60cd1d52eae2de51bd40af18","target":"graph","created_at":"2026-07-05T10:33:42Z","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/2501.01709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual encoders are fundamental components in vision-language models (VLMs), each showcasing unique strengths derived from various pre-trained visual foundation models. To leverage the various capabilities of these encoders, recent studies incorporate multiple encoders within a single VLM, leading to a considerable increase in computational cost. In this paper, we present Mixture-of-Visual-Encoder Knowledge Distillation (MoVE-KD), a novel framework that distills the unique proficiencies of multiple vision encoders into a single, efficient encoder model. Specifically, to mitigate conflicts and ","authors_text":"Jiajun Cao, Ming Lu, Ningning Ma, Qizhe Zhang, Ruichuan An, Shanghang Zhang, Tao Huang, Yuan Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T09:10:34Z","title":"MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01709","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":"sha256:62b383da6547d7d83716d586cefdf8cb440176e1844c4d42f811a6e8c6f93b7b","target":"record","created_at":"2026-07-05T10:33:42Z","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":"90a0313016e547018248c0048bcf55fcc15e87cf53c35f0711210cc03788e09b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T09:10:34Z","title_canon_sha256":"ba6370fdeaf3b95f31be0d1a9b9432fce4bc6530acfd8f9c87b1a598578b22d0"},"schema_version":"1.0","source":{"id":"2501.01709","kind":"arxiv","version":3}},"canonical_sha256":"d524250b4bca81b63983cf9a21526514eba3d4d50b7736b3a11519e54651e2e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d524250b4bca81b63983cf9a21526514eba3d4d50b7736b3a11519e54651e2e4","first_computed_at":"2026-07-05T10:33:42.120674Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:33:42.120674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2og7wqkulcHxW9qefA75LQHALcwOEZ8qxpcZRGLbBaOTMlGTs8OSWywP2vwZCXxUYhAQZv7KOc4aKx6AQmuECA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:33:42.121155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01709","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62b383da6547d7d83716d586cefdf8cb440176e1844c4d42f811a6e8c6f93b7b","sha256:41d3b299049f65bb83a01a1932b4607191874dcc60cd1d52eae2de51bd40af18"],"state_sha256":"3dc382074e9bbda9a0455482ccacdcef383f923ddbca4f2e9616b265c10c2971"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5RRWxVbvnmzkpoS+OYk7NwVViNX6vIJ5J8wT6sG59j8iJYSqJE5rM7IyPp7CwQSvv/hTvPaaZzR2Ng6vB1jNAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T06:28:08.190424Z","bundle_sha256":"53d9a25fe9764c329ce41b8274b3163b78cae816d711c7518afbbcf926e12f4f"}}