{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:7RSMOQVTR2M4SX4W7FOQOXHYRB","short_pith_number":"pith:7RSMOQVT","canonical_record":{"source":{"id":"2112.01686","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-03T02:48:51Z","cross_cats_sorted":[],"title_canon_sha256":"396b76daa0ac91db4057f101c83e9aa66d4a6c737dac0b154c9fca102f2a89de","abstract_canon_sha256":"f7d83600bc8a3462c5a1b4b424eade0be106badcf387a62b7a4835c52536d1f6"},"schema_version":"1.0"},"canonical_sha256":"fc64c742b38e99c95f96f95d075cf8885f828f043d38e3346d365b5316342b61","source":{"kind":"arxiv","id":"2112.01686","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.01686","created_at":"2026-07-05T03:37:48Z"},{"alias_kind":"arxiv_version","alias_value":"2112.01686v2","created_at":"2026-07-05T03:37:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01686","created_at":"2026-07-05T03:37:48Z"},{"alias_kind":"pith_short_12","alias_value":"7RSMOQVTR2M4","created_at":"2026-07-05T03:37:48Z"},{"alias_kind":"pith_short_16","alias_value":"7RSMOQVTR2M4SX4W","created_at":"2026-07-05T03:37:48Z"},{"alias_kind":"pith_short_8","alias_value":"7RSMOQVT","created_at":"2026-07-05T03:37:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:7RSMOQVTR2M4SX4W7FOQOXHYRB","target":"record","payload":{"canonical_record":{"source":{"id":"2112.01686","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-03T02:48:51Z","cross_cats_sorted":[],"title_canon_sha256":"396b76daa0ac91db4057f101c83e9aa66d4a6c737dac0b154c9fca102f2a89de","abstract_canon_sha256":"f7d83600bc8a3462c5a1b4b424eade0be106badcf387a62b7a4835c52536d1f6"},"schema_version":"1.0"},"canonical_sha256":"fc64c742b38e99c95f96f95d075cf8885f828f043d38e3346d365b5316342b61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:37:48.797866Z","signature_b64":"yGyxI5SZrkUsbAQnjEixhXQ1oAZ3M/1f1/ROdL6udE90/vrU4lAsXQlNrol0rTef7nJhX/WHXory9oz3YofHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc64c742b38e99c95f96f95d075cf8885f828f043d38e3346d365b5316342b61","last_reissued_at":"2026-07-05T03:37:48.797458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:37:48.797458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.01686","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:37:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iqUjKngZLJ+KrAdz8jKoPl/NR/+/je3z8B8o6LV8QUaSE1ngSR8eSKOuc+xt0NWQmh8ITTUeDEwvmGEO8SKfBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:05:21.939369Z"},"content_sha256":"ec4536e538110008928313adfca8b19edf5f5c4a996c4e8576c74b09901b4c17","schema_version":"1.0","event_id":"sha256:ec4536e538110008928313adfca8b19edf5f5c4a996c4e8576c74b09901b4c17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:7RSMOQVTR2M4SX4W7FOQOXHYRB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Make A Long Image Short: Adaptive Token Length for Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feifei Feng, Jian Tang, Jie Du, Yichen Zhu, Yi Wang, Yuqin Zhu, Zhicai Ou","submitted_at":"2021-12-03T02:48:51Z","abstract_excerpt":"The vision transformer splits each image into a sequence of tokens with fixed length and processes the tokens in the same way as words in natural language processing. More tokens normally lead to better performance but considerably increased computational cost. Motivated by the proverb \"A picture is worth a thousand words\" we aim to accelerate the ViT model by making a long image short. To this end, we propose a novel approach to assign token length adaptively during inference. Specifically, we first train a ViT model, called Resizable-ViT (ReViT), that can process any given input with diverse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01686","kind":"arxiv","version":2},"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/2112.01686/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":"2026-07-05T03:37:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iOtohv/MiCTluspY4N2bw1Ar68tpF/ewzBtoAI9V3+sQE7comqsKI4wJSUeIMu1BV7qcX+N2U8jn/iXXuWSDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:05:21.939969Z"},"content_sha256":"735922a2e01bafb29deabddf8d1a023e0b8485f5815953e9d21b39b9d80a3d6e","schema_version":"1.0","event_id":"sha256:735922a2e01bafb29deabddf8d1a023e0b8485f5815953e9d21b39b9d80a3d6e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7RSMOQVTR2M4SX4W7FOQOXHYRB/bundle.json","state_url":"https://pith.science/pith/7RSMOQVTR2M4SX4W7FOQOXHYRB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7RSMOQVTR2M4SX4W7FOQOXHYRB/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":"2026-08-11T10:05:21Z","links":{"resolver":"https://pith.science/pith/7RSMOQVTR2M4SX4W7FOQOXHYRB","bundle":"https://pith.science/pith/7RSMOQVTR2M4SX4W7FOQOXHYRB/bundle.json","state":"https://pith.science/pith/7RSMOQVTR2M4SX4W7FOQOXHYRB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7RSMOQVTR2M4SX4W7FOQOXHYRB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7RSMOQVTR2M4SX4W7FOQOXHYRB","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":"f7d83600bc8a3462c5a1b4b424eade0be106badcf387a62b7a4835c52536d1f6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-03T02:48:51Z","title_canon_sha256":"396b76daa0ac91db4057f101c83e9aa66d4a6c737dac0b154c9fca102f2a89de"},"schema_version":"1.0","source":{"id":"2112.01686","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.01686","created_at":"2026-07-05T03:37:48Z"},{"alias_kind":"arxiv_version","alias_value":"2112.01686v2","created_at":"2026-07-05T03:37:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01686","created_at":"2026-07-05T03:37:48Z"},{"alias_kind":"pith_short_12","alias_value":"7RSMOQVTR2M4","created_at":"2026-07-05T03:37:48Z"},{"alias_kind":"pith_short_16","alias_value":"7RSMOQVTR2M4SX4W","created_at":"2026-07-05T03:37:48Z"},{"alias_kind":"pith_short_8","alias_value":"7RSMOQVT","created_at":"2026-07-05T03:37:48Z"}],"graph_snapshots":[{"event_id":"sha256:735922a2e01bafb29deabddf8d1a023e0b8485f5815953e9d21b39b9d80a3d6e","target":"graph","created_at":"2026-07-05T03:37:48Z","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/2112.01686/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The vision transformer splits each image into a sequence of tokens with fixed length and processes the tokens in the same way as words in natural language processing. More tokens normally lead to better performance but considerably increased computational cost. Motivated by the proverb \"A picture is worth a thousand words\" we aim to accelerate the ViT model by making a long image short. To this end, we propose a novel approach to assign token length adaptively during inference. Specifically, we first train a ViT model, called Resizable-ViT (ReViT), that can process any given input with diverse","authors_text":"Feifei Feng, Jian Tang, Jie Du, Yichen Zhu, Yi Wang, Yuqin Zhu, Zhicai Ou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-03T02:48:51Z","title":"Make A Long Image Short: Adaptive Token Length for Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01686","kind":"arxiv","version":2},"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:ec4536e538110008928313adfca8b19edf5f5c4a996c4e8576c74b09901b4c17","target":"record","created_at":"2026-07-05T03:37:48Z","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":"f7d83600bc8a3462c5a1b4b424eade0be106badcf387a62b7a4835c52536d1f6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-03T02:48:51Z","title_canon_sha256":"396b76daa0ac91db4057f101c83e9aa66d4a6c737dac0b154c9fca102f2a89de"},"schema_version":"1.0","source":{"id":"2112.01686","kind":"arxiv","version":2}},"canonical_sha256":"fc64c742b38e99c95f96f95d075cf8885f828f043d38e3346d365b5316342b61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc64c742b38e99c95f96f95d075cf8885f828f043d38e3346d365b5316342b61","first_computed_at":"2026-07-05T03:37:48.797458Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:37:48.797458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yGyxI5SZrkUsbAQnjEixhXQ1oAZ3M/1f1/ROdL6udE90/vrU4lAsXQlNrol0rTef7nJhX/WHXory9oz3YofHCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:37:48.797866Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.01686","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec4536e538110008928313adfca8b19edf5f5c4a996c4e8576c74b09901b4c17","sha256:735922a2e01bafb29deabddf8d1a023e0b8485f5815953e9d21b39b9d80a3d6e"],"state_sha256":"6cb84884398e8b0b8e5696f6503918b03faa748e41495e01a571b1b3039caef2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yub9+C5SwDCf33uMQRPPOfb1HpDd4KxqakeY3bLL9f1DVjKILpLpTLShtD66zRacuDKF4Sb+HLLaCrIgzPUnDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T10:05:21.944341Z","bundle_sha256":"cf97aba0c76a822cf33d58e65aa445774451da755632bf97a58d0402f69c24c0"}}