{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:NE7BUPMHYPSUCWJPXLD6X4Z5KJ","short_pith_number":"pith:NE7BUPMH","canonical_record":{"source":{"id":"2211.10801","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-19T21:15:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c02e04058c1498d2d1486dd069294d5bf85866df558675d726399aa38f528bc2","abstract_canon_sha256":"dbbe9a29d9dc7294b50bd64d690d8b1635e0073739fc16274e32a0845735fad1"},"schema_version":"1.0"},"canonical_sha256":"693e1a3d87c3e541592fbac7ebf33d526d8bbd081cea4af275aae224f39a2043","source":{"kind":"arxiv","id":"2211.10801","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.10801","created_at":"2026-07-05T05:17:34Z"},{"alias_kind":"arxiv_version","alias_value":"2211.10801v1","created_at":"2026-07-05T05:17:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.10801","created_at":"2026-07-05T05:17:34Z"},{"alias_kind":"pith_short_12","alias_value":"NE7BUPMHYPSU","created_at":"2026-07-05T05:17:34Z"},{"alias_kind":"pith_short_16","alias_value":"NE7BUPMHYPSUCWJP","created_at":"2026-07-05T05:17:34Z"},{"alias_kind":"pith_short_8","alias_value":"NE7BUPMH","created_at":"2026-07-05T05:17:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:NE7BUPMHYPSUCWJPXLD6X4Z5KJ","target":"record","payload":{"canonical_record":{"source":{"id":"2211.10801","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-19T21:15:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c02e04058c1498d2d1486dd069294d5bf85866df558675d726399aa38f528bc2","abstract_canon_sha256":"dbbe9a29d9dc7294b50bd64d690d8b1635e0073739fc16274e32a0845735fad1"},"schema_version":"1.0"},"canonical_sha256":"693e1a3d87c3e541592fbac7ebf33d526d8bbd081cea4af275aae224f39a2043","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:34.807594Z","signature_b64":"mgZRxExUDo8/Lsy2flCIv3zGa7+XNL96ed5rmcTYq3ezhWKW34KT/l03vyHVplW+xlEGsIZ1TBvhcNqwwLqVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"693e1a3d87c3e541592fbac7ebf33d526d8bbd081cea4af275aae224f39a2043","last_reissued_at":"2026-07-05T05:17:34.806994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:34.806994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.10801","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":"2026-07-05T05:17:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y2j1aOgDpFVgxYw18vOL9YrLgL9HkWzBneWXZ37mlTFeaaaP5T6XiTwJSZ8A4RaAaCR/pbA/j5K6SAlzsngoAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:53:36.805804Z"},"content_sha256":"3fd9db08eabcc64b2e6af26480d91a59d281929945746706a210a606292178d8","schema_version":"1.0","event_id":"sha256:3fd9db08eabcc64b2e6af26480d91a59d281929945746706a210a606292178d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:NE7BUPMHYPSUCWJPXLD6X4Z5KJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Geng Yuan, Hao Tang, Haoyu Ma, Mengshu Sun, Minghai Qin, Peiyan Dong, Tianlong Chen, Xiaohui Xie, Xiaolong Ma, Xin Meng, Xuan Shen, Yanyue Xie, Yanzhi Wang, Zhangyang Wang, Zhenglun Kong","submitted_at":"2022-11-19T21:15:47Z","abstract_excerpt":"Vision transformers (ViTs) have recently obtained success in many applications, but their intensive computation and heavy memory usage at both training and inference time limit their generalization. Previous compression algorithms usually start from the pre-trained dense models and only focus on efficient inference, while time-consuming training is still unavoidable. In contrast, this paper points out that the million-scale training data is redundant, which is the fundamental reason for the tedious training. To address the issue, this paper aims to introduce sparsity into data and proposes an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.10801","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/2211.10801/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":"2026-07-05T05:17:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pYo3Bvj78oKzRCv/3XOUfFjfEM3rjNoDTWBRaZ4WfxQY6AY/wWu32uPXkRx9Xb7BmJ1OsP0unsz6puk3DHX1Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:53:36.806630Z"},"content_sha256":"1b061a5ef7b9915780ec97dd83acaf5409184554fe06c2534d866caaaf10fbe2","schema_version":"1.0","event_id":"sha256:1b061a5ef7b9915780ec97dd83acaf5409184554fe06c2534d866caaaf10fbe2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NE7BUPMHYPSUCWJPXLD6X4Z5KJ/bundle.json","state_url":"https://pith.science/pith/NE7BUPMHYPSUCWJPXLD6X4Z5KJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NE7BUPMHYPSUCWJPXLD6X4Z5KJ/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":"2026-08-06T06:53:36Z","links":{"resolver":"https://pith.science/pith/NE7BUPMHYPSUCWJPXLD6X4Z5KJ","bundle":"https://pith.science/pith/NE7BUPMHYPSUCWJPXLD6X4Z5KJ/bundle.json","state":"https://pith.science/pith/NE7BUPMHYPSUCWJPXLD6X4Z5KJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NE7BUPMHYPSUCWJPXLD6X4Z5KJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NE7BUPMHYPSUCWJPXLD6X4Z5KJ","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":"dbbe9a29d9dc7294b50bd64d690d8b1635e0073739fc16274e32a0845735fad1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-19T21:15:47Z","title_canon_sha256":"c02e04058c1498d2d1486dd069294d5bf85866df558675d726399aa38f528bc2"},"schema_version":"1.0","source":{"id":"2211.10801","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.10801","created_at":"2026-07-05T05:17:34Z"},{"alias_kind":"arxiv_version","alias_value":"2211.10801v1","created_at":"2026-07-05T05:17:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.10801","created_at":"2026-07-05T05:17:34Z"},{"alias_kind":"pith_short_12","alias_value":"NE7BUPMHYPSU","created_at":"2026-07-05T05:17:34Z"},{"alias_kind":"pith_short_16","alias_value":"NE7BUPMHYPSUCWJP","created_at":"2026-07-05T05:17:34Z"},{"alias_kind":"pith_short_8","alias_value":"NE7BUPMH","created_at":"2026-07-05T05:17:34Z"}],"graph_snapshots":[{"event_id":"sha256:1b061a5ef7b9915780ec97dd83acaf5409184554fe06c2534d866caaaf10fbe2","target":"graph","created_at":"2026-07-05T05:17:34Z","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/2211.10801/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision transformers (ViTs) have recently obtained success in many applications, but their intensive computation and heavy memory usage at both training and inference time limit their generalization. Previous compression algorithms usually start from the pre-trained dense models and only focus on efficient inference, while time-consuming training is still unavoidable. In contrast, this paper points out that the million-scale training data is redundant, which is the fundamental reason for the tedious training. To address the issue, this paper aims to introduce sparsity into data and proposes an ","authors_text":"Geng Yuan, Hao Tang, Haoyu Ma, Mengshu Sun, Minghai Qin, Peiyan Dong, Tianlong Chen, Xiaohui Xie, Xiaolong Ma, Xin Meng, Xuan Shen, Yanyue Xie, Yanzhi Wang, Zhangyang Wang, Zhenglun Kong","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-19T21:15:47Z","title":"Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.10801","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":"sha256:3fd9db08eabcc64b2e6af26480d91a59d281929945746706a210a606292178d8","target":"record","created_at":"2026-07-05T05:17:34Z","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":"dbbe9a29d9dc7294b50bd64d690d8b1635e0073739fc16274e32a0845735fad1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-19T21:15:47Z","title_canon_sha256":"c02e04058c1498d2d1486dd069294d5bf85866df558675d726399aa38f528bc2"},"schema_version":"1.0","source":{"id":"2211.10801","kind":"arxiv","version":1}},"canonical_sha256":"693e1a3d87c3e541592fbac7ebf33d526d8bbd081cea4af275aae224f39a2043","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"693e1a3d87c3e541592fbac7ebf33d526d8bbd081cea4af275aae224f39a2043","first_computed_at":"2026-07-05T05:17:34.806994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:17:34.806994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mgZRxExUDo8/Lsy2flCIv3zGa7+XNL96ed5rmcTYq3ezhWKW34KT/l03vyHVplW+xlEGsIZ1TBvhcNqwwLqVAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:17:34.807594Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.10801","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fd9db08eabcc64b2e6af26480d91a59d281929945746706a210a606292178d8","sha256:1b061a5ef7b9915780ec97dd83acaf5409184554fe06c2534d866caaaf10fbe2"],"state_sha256":"6c2e5671c77a438bc5e6a11a946739242cc7ab259e1c64394d420267601e62c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qAHi8MzmnT9DJf3+gTGepVbxHWwxOm2kgmf3g8pYO3q0LVJP20GQNtdRfp9R5ZdvzvngH/boM9izi5E4PJArBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:53:36.811883Z","bundle_sha256":"2bed80ea17a9ed58f75eda5743c93393bc907a2b9037aab92ea5b91d526f7f87"}}