{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SCE7WBSZZVUD73FDGLDUY42ZBB","short_pith_number":"pith:SCE7WBSZ","canonical_record":{"source":{"id":"2411.14429","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:59:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5869b8fbc16e3596c210dcfea881838a079dc6a8f56029818183625468453f11","abstract_canon_sha256":"c574963b13632f9f090ee1aba607d7720a72fa339b94bfe1807840f7bc66fc80"},"schema_version":"1.0"},"canonical_sha256":"9089fb0659cd683feca332c74c7359087096226d491cb4b73f4491669309b1f9","source":{"kind":"arxiv","id":"2411.14429","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14429","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14429v1","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14429","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"SCE7WBSZZVUD","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"pith_short_16","alias_value":"SCE7WBSZZVUD73FD","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"pith_short_8","alias_value":"SCE7WBSZ","created_at":"2026-07-05T09:38:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SCE7WBSZZVUD73FDGLDUY42ZBB","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14429","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:59:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5869b8fbc16e3596c210dcfea881838a079dc6a8f56029818183625468453f11","abstract_canon_sha256":"c574963b13632f9f090ee1aba607d7720a72fa339b94bfe1807840f7bc66fc80"},"schema_version":"1.0"},"canonical_sha256":"9089fb0659cd683feca332c74c7359087096226d491cb4b73f4491669309b1f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:46.861332Z","signature_b64":"9BwFxatd498cJsYsLzSvoyUJyetezG4k/WC5w2wiQu74hHWQTQ5J6t9jeUPZkUosEMVF4Eb/gce5J9DJJcc9Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9089fb0659cd683feca332c74c7359087096226d491cb4b73f4491669309b1f9","last_reissued_at":"2026-07-05T09:38:46.860857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:46.860857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14429","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":"2026-07-05T09:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SJ6wtSoCkUMcG61Rb/24V2NTWh1M708A3glNte1fLGGZ2+Ho9/eRCCk/D8aVJwaXGNoLK+HyfuoMw979hpyuCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T01:14:13.299503Z"},"content_sha256":"55b68323ae6332f3ae0eae021c485ab42d3f591baae0d634e63d357e422df233","schema_version":"1.0","event_id":"sha256:55b68323ae6332f3ae0eae021c485ab42d3f591baae0d634e63d357e422df233"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SCE7WBSZZVUD73FDGLDUY42ZBB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revisiting the Integration of Convolution and Attention for Vision Backbone","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lei Zhu, Rynson W. H. Lau, Wayne Zhang, Xinjiang Wang","submitted_at":"2024-11-21T18:59:08Z","abstract_excerpt":"Convolutions (Convs) and multi-head self-attentions (MHSAs) are typically considered alternatives to each other for building vision backbones. Although some works try to integrate both, they apply the two operators simultaneously at the finest pixel granularity. With Convs responsible for per-pixel feature extraction already, the question is whether we still need to include the heavy MHSAs at such a fine-grained level. In fact, this is the root cause of the scalability issue w.r.t. the input resolution for vision transformers. To address this important problem, we propose in this work to use M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14429","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/2411.14429/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":"2026-07-05T09:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MK2qtVaxJS+qLkLeZxYxywg8xhu8o2DmVPfwfosMxMeMa0fYiBbT85hjU9EX4wi33uGoSYpxdJNRcYZpcUYuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T01:14:13.300261Z"},"content_sha256":"846eedf9360848b4a0d45769382fcd4b51a0115edf6c209316c2972b8e58e271","schema_version":"1.0","event_id":"sha256:846eedf9360848b4a0d45769382fcd4b51a0115edf6c209316c2972b8e58e271"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SCE7WBSZZVUD73FDGLDUY42ZBB/bundle.json","state_url":"https://pith.science/pith/SCE7WBSZZVUD73FDGLDUY42ZBB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SCE7WBSZZVUD73FDGLDUY42ZBB/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":"2026-08-13T01:14:13Z","links":{"resolver":"https://pith.science/pith/SCE7WBSZZVUD73FDGLDUY42ZBB","bundle":"https://pith.science/pith/SCE7WBSZZVUD73FDGLDUY42ZBB/bundle.json","state":"https://pith.science/pith/SCE7WBSZZVUD73FDGLDUY42ZBB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SCE7WBSZZVUD73FDGLDUY42ZBB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SCE7WBSZZVUD73FDGLDUY42ZBB","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":"c574963b13632f9f090ee1aba607d7720a72fa339b94bfe1807840f7bc66fc80","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:59:08Z","title_canon_sha256":"5869b8fbc16e3596c210dcfea881838a079dc6a8f56029818183625468453f11"},"schema_version":"1.0","source":{"id":"2411.14429","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14429","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14429v1","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14429","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"SCE7WBSZZVUD","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"pith_short_16","alias_value":"SCE7WBSZZVUD73FD","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"pith_short_8","alias_value":"SCE7WBSZ","created_at":"2026-07-05T09:38:46Z"}],"graph_snapshots":[{"event_id":"sha256:846eedf9360848b4a0d45769382fcd4b51a0115edf6c209316c2972b8e58e271","target":"graph","created_at":"2026-07-05T09:38:46Z","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/2411.14429/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Convolutions (Convs) and multi-head self-attentions (MHSAs) are typically considered alternatives to each other for building vision backbones. Although some works try to integrate both, they apply the two operators simultaneously at the finest pixel granularity. With Convs responsible for per-pixel feature extraction already, the question is whether we still need to include the heavy MHSAs at such a fine-grained level. In fact, this is the root cause of the scalability issue w.r.t. the input resolution for vision transformers. To address this important problem, we propose in this work to use M","authors_text":"Lei Zhu, Rynson W. H. Lau, Wayne Zhang, Xinjiang Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:59:08Z","title":"Revisiting the Integration of Convolution and Attention for Vision Backbone"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14429","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":"sha256:55b68323ae6332f3ae0eae021c485ab42d3f591baae0d634e63d357e422df233","target":"record","created_at":"2026-07-05T09:38:46Z","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":"c574963b13632f9f090ee1aba607d7720a72fa339b94bfe1807840f7bc66fc80","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:59:08Z","title_canon_sha256":"5869b8fbc16e3596c210dcfea881838a079dc6a8f56029818183625468453f11"},"schema_version":"1.0","source":{"id":"2411.14429","kind":"arxiv","version":1}},"canonical_sha256":"9089fb0659cd683feca332c74c7359087096226d491cb4b73f4491669309b1f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9089fb0659cd683feca332c74c7359087096226d491cb4b73f4491669309b1f9","first_computed_at":"2026-07-05T09:38:46.860857Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:46.860857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9BwFxatd498cJsYsLzSvoyUJyetezG4k/WC5w2wiQu74hHWQTQ5J6t9jeUPZkUosEMVF4Eb/gce5J9DJJcc9Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:46.861332Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14429","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55b68323ae6332f3ae0eae021c485ab42d3f591baae0d634e63d357e422df233","sha256:846eedf9360848b4a0d45769382fcd4b51a0115edf6c209316c2972b8e58e271"],"state_sha256":"20097f2415efae8b7a1c569d24132c3e701a1a78393ab8d74f86bcc2288ea976"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3PODNBm/TA+dHRj+ccMvr30n3zS9rO2npMHseXon4RMOVRGXByaLYXPGbiIAongvnoU9mCEF08LXePfD+0lCAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T01:14:13.306875Z","bundle_sha256":"4d9ea90c7a9edec56988ea518cd51b88e18194ef77ae30db33e49e79486101a0"}}