{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:C5GU3BJRY7XMSKMQZ3G7DV7V4S","short_pith_number":"pith:C5GU3BJR","canonical_record":{"source":{"id":"2304.03768","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-07T17:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"8225579b5d07c5cec0947a367c2962aff6181889067fbae1b6c086902025dbe4","abstract_canon_sha256":"734165869ff7d655d8d354c50cea698af05a958384b619e207cd200dc829b408"},"schema_version":"1.0"},"canonical_sha256":"174d4d8531c7eec92990cecdf1d7f5e4bb47eb29c099c79457313f36524e728e","source":{"kind":"arxiv","id":"2304.03768","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03768","created_at":"2026-07-05T05:59:00Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03768v1","created_at":"2026-07-05T05:59:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03768","created_at":"2026-07-05T05:59:00Z"},{"alias_kind":"pith_short_12","alias_value":"C5GU3BJRY7XM","created_at":"2026-07-05T05:59:00Z"},{"alias_kind":"pith_short_16","alias_value":"C5GU3BJRY7XMSKMQ","created_at":"2026-07-05T05:59:00Z"},{"alias_kind":"pith_short_8","alias_value":"C5GU3BJR","created_at":"2026-07-05T05:59:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:C5GU3BJRY7XMSKMQZ3G7DV7V4S","target":"record","payload":{"canonical_record":{"source":{"id":"2304.03768","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-07T17:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"8225579b5d07c5cec0947a367c2962aff6181889067fbae1b6c086902025dbe4","abstract_canon_sha256":"734165869ff7d655d8d354c50cea698af05a958384b619e207cd200dc829b408"},"schema_version":"1.0"},"canonical_sha256":"174d4d8531c7eec92990cecdf1d7f5e4bb47eb29c099c79457313f36524e728e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:00.168743Z","signature_b64":"neItAyR/yPt0r0Imdjzz6/EB2uemJLotcxiM67AU9vXLeJ8UL5WC17koYb/w9H04/pQgZHqt/hvYeAd2Tla/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"174d4d8531c7eec92990cecdf1d7f5e4bb47eb29c099c79457313f36524e728e","last_reissued_at":"2026-07-05T05:59:00.168332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:00.168332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.03768","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":"2026-07-05T05:59:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zFDKkK0p03iijyS7Z4EbmQRsJepUdwp+Qb1pl0AWEhV9ouNym9k17oOnHinCLwrQe0P82+hJxjX0in4iYdBPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:31:29.989807Z"},"content_sha256":"705de82f135e17c22708c0b9a2c304afc39e4dffea31370368c9d83f1d33893f","schema_version":"1.0","event_id":"sha256:705de82f135e17c22708c0b9a2c304afc39e4dffea31370368c9d83f1d33893f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:C5GU3BJRY7XMSKMQZ3G7DV7V4S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SparseFormer: Sparse Visual Recognition via Limited Latent Tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Limin Wang, Mike Zheng Shou, Zhan Tong, Ziteng Gao","submitted_at":"2023-04-07T17:59:58Z","abstract_excerpt":"Human visual recognition is a sparse process, where only a few salient visual cues are attended to rather than traversing every detail uniformly. However, most current vision networks follow a dense paradigm, processing every single visual unit (e.g,, pixel or patch) in a uniform manner. In this paper, we challenge this dense paradigm and present a new method, coined SparseFormer, to imitate human's sparse visual recognition in an end-to-end manner. SparseFormer learns to represent images using a highly limited number of tokens (down to 49) in the latent space with sparse feature sampling proc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03768","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/2304.03768/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":"2026-07-05T05:59:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WqsnL4OIvdX5j9lKOUX0BzdU4YLxf40zn6qmxELdLYZpIoYaaFqq+PScnVUwY6HRnXPM10DjLWBIHejECDmXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:31:29.990324Z"},"content_sha256":"667d46e4dc073883e215f91d327463249f29a2c3c8b31ff1ae932383cea19d77","schema_version":"1.0","event_id":"sha256:667d46e4dc073883e215f91d327463249f29a2c3c8b31ff1ae932383cea19d77"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C5GU3BJRY7XMSKMQZ3G7DV7V4S/bundle.json","state_url":"https://pith.science/pith/C5GU3BJRY7XMSKMQZ3G7DV7V4S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C5GU3BJRY7XMSKMQZ3G7DV7V4S/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":"2026-08-11T04:31:29Z","links":{"resolver":"https://pith.science/pith/C5GU3BJRY7XMSKMQZ3G7DV7V4S","bundle":"https://pith.science/pith/C5GU3BJRY7XMSKMQZ3G7DV7V4S/bundle.json","state":"https://pith.science/pith/C5GU3BJRY7XMSKMQZ3G7DV7V4S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C5GU3BJRY7XMSKMQZ3G7DV7V4S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:C5GU3BJRY7XMSKMQZ3G7DV7V4S","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":"734165869ff7d655d8d354c50cea698af05a958384b619e207cd200dc829b408","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-07T17:59:58Z","title_canon_sha256":"8225579b5d07c5cec0947a367c2962aff6181889067fbae1b6c086902025dbe4"},"schema_version":"1.0","source":{"id":"2304.03768","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03768","created_at":"2026-07-05T05:59:00Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03768v1","created_at":"2026-07-05T05:59:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03768","created_at":"2026-07-05T05:59:00Z"},{"alias_kind":"pith_short_12","alias_value":"C5GU3BJRY7XM","created_at":"2026-07-05T05:59:00Z"},{"alias_kind":"pith_short_16","alias_value":"C5GU3BJRY7XMSKMQ","created_at":"2026-07-05T05:59:00Z"},{"alias_kind":"pith_short_8","alias_value":"C5GU3BJR","created_at":"2026-07-05T05:59:00Z"}],"graph_snapshots":[{"event_id":"sha256:667d46e4dc073883e215f91d327463249f29a2c3c8b31ff1ae932383cea19d77","target":"graph","created_at":"2026-07-05T05:59:00Z","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/2304.03768/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human visual recognition is a sparse process, where only a few salient visual cues are attended to rather than traversing every detail uniformly. However, most current vision networks follow a dense paradigm, processing every single visual unit (e.g,, pixel or patch) in a uniform manner. In this paper, we challenge this dense paradigm and present a new method, coined SparseFormer, to imitate human's sparse visual recognition in an end-to-end manner. SparseFormer learns to represent images using a highly limited number of tokens (down to 49) in the latent space with sparse feature sampling proc","authors_text":"Limin Wang, Mike Zheng Shou, Zhan Tong, Ziteng Gao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-07T17:59:58Z","title":"SparseFormer: Sparse Visual Recognition via Limited Latent Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03768","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":"sha256:705de82f135e17c22708c0b9a2c304afc39e4dffea31370368c9d83f1d33893f","target":"record","created_at":"2026-07-05T05:59:00Z","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":"734165869ff7d655d8d354c50cea698af05a958384b619e207cd200dc829b408","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-07T17:59:58Z","title_canon_sha256":"8225579b5d07c5cec0947a367c2962aff6181889067fbae1b6c086902025dbe4"},"schema_version":"1.0","source":{"id":"2304.03768","kind":"arxiv","version":1}},"canonical_sha256":"174d4d8531c7eec92990cecdf1d7f5e4bb47eb29c099c79457313f36524e728e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"174d4d8531c7eec92990cecdf1d7f5e4bb47eb29c099c79457313f36524e728e","first_computed_at":"2026-07-05T05:59:00.168332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:59:00.168332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"neItAyR/yPt0r0Imdjzz6/EB2uemJLotcxiM67AU9vXLeJ8UL5WC17koYb/w9H04/pQgZHqt/hvYeAd2Tla/Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:59:00.168743Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.03768","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:705de82f135e17c22708c0b9a2c304afc39e4dffea31370368c9d83f1d33893f","sha256:667d46e4dc073883e215f91d327463249f29a2c3c8b31ff1ae932383cea19d77"],"state_sha256":"753586852d65f71e1361b6de22258faa1f308ca2465e8dd7784c1e2ff2e9cbd9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gj+JTXK7fNxIAxxe0END+4CFdS9SI5NLSnKfyGqtHHsook4r/KjVibB6cpSn657otnnBGKTbPPxNm7yah+vhDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T04:31:29.994860Z","bundle_sha256":"3fd9c601ab2d725134231f83b72dd6d3e348c2bec9bd09c397dca74c8ca55289"}}