{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WH7HJ4557VJRTS4JLX5F3FO5ZJ","short_pith_number":"pith:WH7HJ455","canonical_record":{"source":{"id":"2108.03428","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-07T11:30:54Z","cross_cats_sorted":[],"title_canon_sha256":"4c6117d40ad971d444517210e72bbe60a618a26bbc34c49fba05c8aa573c6580","abstract_canon_sha256":"8ebed4df3ecf52a53a7f9232cf9b0e7cdcd180b8fe8f888edc2a8392ca42cf05"},"schema_version":"1.0"},"canonical_sha256":"b1fe74f3bdfd5319cb895dfa5d95ddca6fb7b17547fc963de71ea81c0e8b1dfa","source":{"kind":"arxiv","id":"2108.03428","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.03428","created_at":"2026-07-05T03:03:52Z"},{"alias_kind":"arxiv_version","alias_value":"2108.03428v1","created_at":"2026-07-05T03:03:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.03428","created_at":"2026-07-05T03:03:52Z"},{"alias_kind":"pith_short_12","alias_value":"WH7HJ4557VJR","created_at":"2026-07-05T03:03:52Z"},{"alias_kind":"pith_short_16","alias_value":"WH7HJ4557VJRTS4J","created_at":"2026-07-05T03:03:52Z"},{"alias_kind":"pith_short_8","alias_value":"WH7HJ455","created_at":"2026-07-05T03:03:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WH7HJ4557VJRTS4JLX5F3FO5ZJ","target":"record","payload":{"canonical_record":{"source":{"id":"2108.03428","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-07T11:30:54Z","cross_cats_sorted":[],"title_canon_sha256":"4c6117d40ad971d444517210e72bbe60a618a26bbc34c49fba05c8aa573c6580","abstract_canon_sha256":"8ebed4df3ecf52a53a7f9232cf9b0e7cdcd180b8fe8f888edc2a8392ca42cf05"},"schema_version":"1.0"},"canonical_sha256":"b1fe74f3bdfd5319cb895dfa5d95ddca6fb7b17547fc963de71ea81c0e8b1dfa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:52.677937Z","signature_b64":"/fuVtlq9czoPuLC1h/3kqYuvgCE8hBbZnt9rqLSk0Pf/Al/OELksydmicaXqHTBFTkz6f683ilg48h4PTGc0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1fe74f3bdfd5319cb895dfa5d95ddca6fb7b17547fc963de71ea81c0e8b1dfa","last_reissued_at":"2026-07-05T03:03:52.677475Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:52.677475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.03428","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":"2026-07-05T03:03:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vBqjj+SHDkAn5zoMGiUcyf4GHu0hZur3XziwfWMa+m5k5O4zidiLJkboRe8B6rJblhau1bbGfiZ6xys1ErlfDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:44:56.907350Z"},"content_sha256":"875301e7d217bacec01ef5b67c13f8cfff66e8872a6b911e1b1be584a8f2a995","schema_version":"1.0","event_id":"sha256:875301e7d217bacec01ef5b67c13f8cfff66e8872a6b911e1b1be584a8f2a995"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WH7HJ4557VJRTS4JLX5F3FO5ZJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PSViT: Better Vision Transformer via Token Pooling and Attention Sharing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baopu Li, Boyu Chen, Chen Lin, Chuming Li, Junjie Yan, Lei Bai, Ming Sun, Peixia Li, Wanli Ouyang","submitted_at":"2021-08-07T11:30:54Z","abstract_excerpt":"In this paper, we observe two levels of redundancies when applying vision transformers (ViT) for image recognition. First, fixing the number of tokens through the whole network produces redundant features at the spatial level. Second, the attention maps among different transformer layers are redundant. Based on the observations above, we propose a PSViT: a ViT with token Pooling and attention Sharing to reduce the redundancy, effectively enhancing the feature representation ability, and achieving a better speed-accuracy trade-off. Specifically, in our PSViT, token pooling can be defined as the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.03428","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/2108.03428/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":"2026-07-05T03:03:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QE1Q7DX6vx3lOX8yOeYBuVntRAfIvOJC1enIhMRNkJNBZFNrnq3GrLhLZb7bdEQG0T77brdsnNLja1sAdizXAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:44:56.908250Z"},"content_sha256":"5d79afbe988ec09b4846bb697145520be0cb5fe53b45c618f190b1f014be6264","schema_version":"1.0","event_id":"sha256:5d79afbe988ec09b4846bb697145520be0cb5fe53b45c618f190b1f014be6264"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WH7HJ4557VJRTS4JLX5F3FO5ZJ/bundle.json","state_url":"https://pith.science/pith/WH7HJ4557VJRTS4JLX5F3FO5ZJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WH7HJ4557VJRTS4JLX5F3FO5ZJ/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":"2026-08-17T12:44:56Z","links":{"resolver":"https://pith.science/pith/WH7HJ4557VJRTS4JLX5F3FO5ZJ","bundle":"https://pith.science/pith/WH7HJ4557VJRTS4JLX5F3FO5ZJ/bundle.json","state":"https://pith.science/pith/WH7HJ4557VJRTS4JLX5F3FO5ZJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WH7HJ4557VJRTS4JLX5F3FO5ZJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WH7HJ4557VJRTS4JLX5F3FO5ZJ","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":"8ebed4df3ecf52a53a7f9232cf9b0e7cdcd180b8fe8f888edc2a8392ca42cf05","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-07T11:30:54Z","title_canon_sha256":"4c6117d40ad971d444517210e72bbe60a618a26bbc34c49fba05c8aa573c6580"},"schema_version":"1.0","source":{"id":"2108.03428","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.03428","created_at":"2026-07-05T03:03:52Z"},{"alias_kind":"arxiv_version","alias_value":"2108.03428v1","created_at":"2026-07-05T03:03:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.03428","created_at":"2026-07-05T03:03:52Z"},{"alias_kind":"pith_short_12","alias_value":"WH7HJ4557VJR","created_at":"2026-07-05T03:03:52Z"},{"alias_kind":"pith_short_16","alias_value":"WH7HJ4557VJRTS4J","created_at":"2026-07-05T03:03:52Z"},{"alias_kind":"pith_short_8","alias_value":"WH7HJ455","created_at":"2026-07-05T03:03:52Z"}],"graph_snapshots":[{"event_id":"sha256:5d79afbe988ec09b4846bb697145520be0cb5fe53b45c618f190b1f014be6264","target":"graph","created_at":"2026-07-05T03:03:52Z","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/2108.03428/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we observe two levels of redundancies when applying vision transformers (ViT) for image recognition. First, fixing the number of tokens through the whole network produces redundant features at the spatial level. Second, the attention maps among different transformer layers are redundant. Based on the observations above, we propose a PSViT: a ViT with token Pooling and attention Sharing to reduce the redundancy, effectively enhancing the feature representation ability, and achieving a better speed-accuracy trade-off. Specifically, in our PSViT, token pooling can be defined as the","authors_text":"Baopu Li, Boyu Chen, Chen Lin, Chuming Li, Junjie Yan, Lei Bai, Ming Sun, Peixia Li, Wanli Ouyang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-07T11:30:54Z","title":"PSViT: Better Vision Transformer via Token Pooling and Attention Sharing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.03428","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":"sha256:875301e7d217bacec01ef5b67c13f8cfff66e8872a6b911e1b1be584a8f2a995","target":"record","created_at":"2026-07-05T03:03:52Z","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":"8ebed4df3ecf52a53a7f9232cf9b0e7cdcd180b8fe8f888edc2a8392ca42cf05","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-07T11:30:54Z","title_canon_sha256":"4c6117d40ad971d444517210e72bbe60a618a26bbc34c49fba05c8aa573c6580"},"schema_version":"1.0","source":{"id":"2108.03428","kind":"arxiv","version":1}},"canonical_sha256":"b1fe74f3bdfd5319cb895dfa5d95ddca6fb7b17547fc963de71ea81c0e8b1dfa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1fe74f3bdfd5319cb895dfa5d95ddca6fb7b17547fc963de71ea81c0e8b1dfa","first_computed_at":"2026-07-05T03:03:52.677475Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:03:52.677475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/fuVtlq9czoPuLC1h/3kqYuvgCE8hBbZnt9rqLSk0Pf/Al/OELksydmicaXqHTBFTkz6f683ilg48h4PTGc0AA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:03:52.677937Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.03428","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:875301e7d217bacec01ef5b67c13f8cfff66e8872a6b911e1b1be584a8f2a995","sha256:5d79afbe988ec09b4846bb697145520be0cb5fe53b45c618f190b1f014be6264"],"state_sha256":"f5caee224f75b7b308de19314e96a0e3a84bb10e0a5a7777e9b0af4bc24c5d93"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wftEeR8HZUDWaVqkJpWOnZkM7+B8KuIdIO6yuUw0/hXeAM/Rkkih531/+uB2YF4f4z0dOKggdv0b/LkrLwcNBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T12:44:56.986486Z","bundle_sha256":"1173eb60ea64ab3fc11aa403e722eead2e524762dc8c0fb42e9828b74d8adb68"}}