{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QAZRJV56TQ2AMAWPUMD42BSPSP","short_pith_number":"pith:QAZRJV56","canonical_record":{"source":{"id":"2407.12753","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T17:22:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"262445c2c2b7c7f3af1d9f3031eb9c8970ec550f52dcaa86da3370b36e777967","abstract_canon_sha256":"21ba3e58aedbce3918798e100ab4932019e518103de77a20c491ab32e89ef77f"},"schema_version":"1.0"},"canonical_sha256":"803314d7be9c340602cfa307cd064f93dab5b323ce25e3572af2118e84c8c676","source":{"kind":"arxiv","id":"2407.12753","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12753","created_at":"2026-07-05T08:45:09Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12753v1","created_at":"2026-07-05T08:45:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12753","created_at":"2026-07-05T08:45:09Z"},{"alias_kind":"pith_short_12","alias_value":"QAZRJV56TQ2A","created_at":"2026-07-05T08:45:09Z"},{"alias_kind":"pith_short_16","alias_value":"QAZRJV56TQ2AMAWP","created_at":"2026-07-05T08:45:09Z"},{"alias_kind":"pith_short_8","alias_value":"QAZRJV56","created_at":"2026-07-05T08:45:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QAZRJV56TQ2AMAWPUMD42BSPSP","target":"record","payload":{"canonical_record":{"source":{"id":"2407.12753","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T17:22:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"262445c2c2b7c7f3af1d9f3031eb9c8970ec550f52dcaa86da3370b36e777967","abstract_canon_sha256":"21ba3e58aedbce3918798e100ab4932019e518103de77a20c491ab32e89ef77f"},"schema_version":"1.0"},"canonical_sha256":"803314d7be9c340602cfa307cd064f93dab5b323ce25e3572af2118e84c8c676","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:09.317819Z","signature_b64":"M6OAw3QaRyv0k14GczX26Be55QHUEvSVG0hPXEuOgQv6M6WyxQJ0SUj95RAHbRm7LhxYlzDZJTkyZpRlkpQfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"803314d7be9c340602cfa307cd064f93dab5b323ce25e3572af2118e84c8c676","last_reissued_at":"2026-07-05T08:45:09.317426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:09.317426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.12753","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":"2026-07-05T08:45:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DYT/ZXK77seP9+nqokGnxZCF3ETxbFouPuMyD6NNdjLz0e4sHtagl+o2wpyhKCdPY5isxFW2OGeQ0HGzG36GCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:27:55.463792Z"},"content_sha256":"e05bc59e65c1d46384adc7e16b66a72edf9497edd9f4632f29c0f1d7f7d4c631","schema_version":"1.0","event_id":"sha256:e05bc59e65c1d46384adc7e16b66a72edf9497edd9f4632f29c0f1d7f7d4c631"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QAZRJV56TQ2AMAWPUMD42BSPSP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LookupViT: Compressing visual information to a limited number of tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gagan Jain, Prateek Jain, Rajat Koner, Sujoy Paul, Volker Tresp","submitted_at":"2024-07-17T17:22:43Z","abstract_excerpt":"Vision Transformers (ViT) have emerged as the de-facto choice for numerous industry grade vision solutions. But their inference cost can be prohibitive for many settings, as they compute self-attention in each layer which suffers from quadratic computational complexity in the number of tokens. On the other hand, spatial information in images and spatio-temporal information in videos is usually sparse and redundant. In this work, we introduce LookupViT, that aims to exploit this information sparsity to reduce ViT inference cost. LookupViT provides a novel general purpose vision transformer bloc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12753","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/2407.12753/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":"2026-07-05T08:45:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xYGC+nJwlZm/ch1OJDd5+EUVPMP+a93VSik60S8suIJNfuaj0nj8IM2acTrLYI0R4xeGra0tYMH7KUEBrhYxAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:27:55.464335Z"},"content_sha256":"93e7eb8b4953e56423483dfa15d65b71c815d5cbe58654147338867f26394c07","schema_version":"1.0","event_id":"sha256:93e7eb8b4953e56423483dfa15d65b71c815d5cbe58654147338867f26394c07"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QAZRJV56TQ2AMAWPUMD42BSPSP/bundle.json","state_url":"https://pith.science/pith/QAZRJV56TQ2AMAWPUMD42BSPSP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QAZRJV56TQ2AMAWPUMD42BSPSP/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":"2026-08-04T17:27:55Z","links":{"resolver":"https://pith.science/pith/QAZRJV56TQ2AMAWPUMD42BSPSP","bundle":"https://pith.science/pith/QAZRJV56TQ2AMAWPUMD42BSPSP/bundle.json","state":"https://pith.science/pith/QAZRJV56TQ2AMAWPUMD42BSPSP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QAZRJV56TQ2AMAWPUMD42BSPSP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QAZRJV56TQ2AMAWPUMD42BSPSP","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":"21ba3e58aedbce3918798e100ab4932019e518103de77a20c491ab32e89ef77f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T17:22:43Z","title_canon_sha256":"262445c2c2b7c7f3af1d9f3031eb9c8970ec550f52dcaa86da3370b36e777967"},"schema_version":"1.0","source":{"id":"2407.12753","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12753","created_at":"2026-07-05T08:45:09Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12753v1","created_at":"2026-07-05T08:45:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12753","created_at":"2026-07-05T08:45:09Z"},{"alias_kind":"pith_short_12","alias_value":"QAZRJV56TQ2A","created_at":"2026-07-05T08:45:09Z"},{"alias_kind":"pith_short_16","alias_value":"QAZRJV56TQ2AMAWP","created_at":"2026-07-05T08:45:09Z"},{"alias_kind":"pith_short_8","alias_value":"QAZRJV56","created_at":"2026-07-05T08:45:09Z"}],"graph_snapshots":[{"event_id":"sha256:93e7eb8b4953e56423483dfa15d65b71c815d5cbe58654147338867f26394c07","target":"graph","created_at":"2026-07-05T08:45:09Z","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/2407.12753/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Transformers (ViT) have emerged as the de-facto choice for numerous industry grade vision solutions. But their inference cost can be prohibitive for many settings, as they compute self-attention in each layer which suffers from quadratic computational complexity in the number of tokens. On the other hand, spatial information in images and spatio-temporal information in videos is usually sparse and redundant. In this work, we introduce LookupViT, that aims to exploit this information sparsity to reduce ViT inference cost. LookupViT provides a novel general purpose vision transformer bloc","authors_text":"Gagan Jain, Prateek Jain, Rajat Koner, Sujoy Paul, Volker Tresp","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T17:22:43Z","title":"LookupViT: Compressing visual information to a limited number of tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12753","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:e05bc59e65c1d46384adc7e16b66a72edf9497edd9f4632f29c0f1d7f7d4c631","target":"record","created_at":"2026-07-05T08:45:09Z","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":"21ba3e58aedbce3918798e100ab4932019e518103de77a20c491ab32e89ef77f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T17:22:43Z","title_canon_sha256":"262445c2c2b7c7f3af1d9f3031eb9c8970ec550f52dcaa86da3370b36e777967"},"schema_version":"1.0","source":{"id":"2407.12753","kind":"arxiv","version":1}},"canonical_sha256":"803314d7be9c340602cfa307cd064f93dab5b323ce25e3572af2118e84c8c676","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"803314d7be9c340602cfa307cd064f93dab5b323ce25e3572af2118e84c8c676","first_computed_at":"2026-07-05T08:45:09.317426Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:09.317426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M6OAw3QaRyv0k14GczX26Be55QHUEvSVG0hPXEuOgQv6M6WyxQJ0SUj95RAHbRm7LhxYlzDZJTkyZpRlkpQfBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:09.317819Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12753","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e05bc59e65c1d46384adc7e16b66a72edf9497edd9f4632f29c0f1d7f7d4c631","sha256:93e7eb8b4953e56423483dfa15d65b71c815d5cbe58654147338867f26394c07"],"state_sha256":"e042a82246660c12fc5d2e52212068aef6f37d5643d2cf0ae642304820a8fb9d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MB2NChEwxhikU4Xgf88dkjKEcEG4DTJTdVaZhFHCRMn9Z3AFShuoJcJKd93nSofkfnOXJyGDoxcIZW+G8Y2bAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:27:55.469966Z","bundle_sha256":"539b9cc91d68763059a2ea04177ace5e0abf259965323756addc5087f79c6091"}}