{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SPNFVA3YGYQSDL6AUMI4UM3Z4B","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":"2827a57de970c82bb11829f0e1fbd4a9dc4ec17d540600dd38c9d21da59fc04a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T05:31:42Z","title_canon_sha256":"38549a890a0554a0801806402eebd6d9193234a445f01f8dc6a1d457ccc27296"},"schema_version":"1.0","source":{"id":"2412.04786","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04786","created_at":"2026-07-05T09:45:23Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04786v1","created_at":"2026-07-05T09:45:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04786","created_at":"2026-07-05T09:45:23Z"},{"alias_kind":"pith_short_12","alias_value":"SPNFVA3YGYQS","created_at":"2026-07-05T09:45:23Z"},{"alias_kind":"pith_short_16","alias_value":"SPNFVA3YGYQSDL6A","created_at":"2026-07-05T09:45:23Z"},{"alias_kind":"pith_short_8","alias_value":"SPNFVA3Y","created_at":"2026-07-05T09:45:23Z"}],"graph_snapshots":[{"event_id":"sha256:904ad2f7aade6ff58b34da9ca36286b470acfa4128b8cc090f773be8c30f9401","target":"graph","created_at":"2026-07-05T09:45:23Z","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/2412.04786/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Transformers (ViT) is known for its scalability. In this work, we target to scale down a ViT to fit in an environment with dynamic-changing resource constraints. We observe that smaller ViTs are intrinsically the sub-networks of a larger ViT with different widths. Thus, we propose a general framework, named Scala, to enable a single network to represent multiple smaller ViTs with flexible inference capability, which aligns with the inherent design of ViT to vary from widths. Concretely, Scala activates several subnets during training, introduces Isolated Activation to disentangle the sm","authors_text":"Derek Hao Hu, Huan Wang, Huseyin Coskun, Ke Ma, Xi (Stephen) Chen, Xu Ma, Yitian Zhang, Yun Fu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T05:31:42Z","title":"Slicing Vision Transformer for Flexible Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04786","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":"sha256:2e533ff8c42ee4aa51d77c68a90006966408a9efdb043a519abe2d6424986af0","target":"record","created_at":"2026-07-05T09:45:23Z","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":"2827a57de970c82bb11829f0e1fbd4a9dc4ec17d540600dd38c9d21da59fc04a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T05:31:42Z","title_canon_sha256":"38549a890a0554a0801806402eebd6d9193234a445f01f8dc6a1d457ccc27296"},"schema_version":"1.0","source":{"id":"2412.04786","kind":"arxiv","version":1}},"canonical_sha256":"93da5a8378362121afc0a311ca3379e04a6155369f38e893d4cc630aa4179f74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93da5a8378362121afc0a311ca3379e04a6155369f38e893d4cc630aa4179f74","first_computed_at":"2026-07-05T09:45:23.730023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:23.730023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7GwdJVZ+VgmOYKVWQAULeika4Em7EdJoAzob189TSftwOPGw4dADwwohrkwYeizCdvjvvUvna4bPQLeuoTz4Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:23.730516Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04786","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e533ff8c42ee4aa51d77c68a90006966408a9efdb043a519abe2d6424986af0","sha256:904ad2f7aade6ff58b34da9ca36286b470acfa4128b8cc090f773be8c30f9401"],"state_sha256":"a7a3da50de1ab19673e03ded2b32d83fec4f059be01fd3c008fe7a637795a227"}