{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CMSZOGTZMBD4ESXCWMBBKGHZOW","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":"fd98374e904c2c512737e4048a03b18e4a83c28acd37d3b4761618f94cf948e7","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T13:26:41Z","title_canon_sha256":"834a2ba721f638b2d34e6ab0127b73e9f95303b6771d499883e6003f74532198"},"schema_version":"1.0","source":{"id":"2210.07795","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.07795","created_at":"2026-07-05T05:06:41Z"},{"alias_kind":"arxiv_version","alias_value":"2210.07795v1","created_at":"2026-07-05T05:06:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07795","created_at":"2026-07-05T05:06:41Z"},{"alias_kind":"pith_short_12","alias_value":"CMSZOGTZMBD4","created_at":"2026-07-05T05:06:41Z"},{"alias_kind":"pith_short_16","alias_value":"CMSZOGTZMBD4ESXC","created_at":"2026-07-05T05:06:41Z"},{"alias_kind":"pith_short_8","alias_value":"CMSZOGTZ","created_at":"2026-07-05T05:06:41Z"}],"graph_snapshots":[{"event_id":"sha256:86930b6ef41d28614e6c9bc978d46584db45e8a18178671d48a878da22ccce59","target":"graph","created_at":"2026-07-05T05:06:41Z","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/2210.07795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained vision-language models (VLMs) have achieved impressive results in a range of vision-language tasks. However, popular VLMs usually consist of hundreds of millions of parameters which brings challenges for fine-tuning and deployment in real-world applications due to space, memory, and latency constraints. In this work, we introduce a distilling then pruning framework to compress large vision-language models into smaller, faster, and more accurate ones. We first shrink the size of a pre-trained large VLM and apply knowledge distillation in the vision-language pre-training stage to obt","authors_text":"Tiannan Wang, Wangchunshu Zhou, Xinsong Zhang, Yan Zeng","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T13:26:41Z","title":"EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07795","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":"sha256:5374695775a0d2d51f2081d17f4529ab0af9509a35b2fae9e7df0c915b0d6ed0","target":"record","created_at":"2026-07-05T05:06:41Z","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":"fd98374e904c2c512737e4048a03b18e4a83c28acd37d3b4761618f94cf948e7","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T13:26:41Z","title_canon_sha256":"834a2ba721f638b2d34e6ab0127b73e9f95303b6771d499883e6003f74532198"},"schema_version":"1.0","source":{"id":"2210.07795","kind":"arxiv","version":1}},"canonical_sha256":"1325971a796047c24ae2b3021518f975969f19940eff23a65cdfbbd65a1a11ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1325971a796047c24ae2b3021518f975969f19940eff23a65cdfbbd65a1a11ed","first_computed_at":"2026-07-05T05:06:41.066082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:41.066082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fy1s6hTSIO3XS+EroOxX8OS3Gx2xAEBiRqHitbPkiKsmGgrSejtPps0Qa4UTTl/rrqwi8BvYO3vhG7/AyjPiCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:41.066500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.07795","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5374695775a0d2d51f2081d17f4529ab0af9509a35b2fae9e7df0c915b0d6ed0","sha256:86930b6ef41d28614e6c9bc978d46584db45e8a18178671d48a878da22ccce59"],"state_sha256":"4ed67a7521236a5f5db876239a9074d06817864b9b600b24429f06e0183fb5a7"}