{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5MQQMQ46JDVKNYFATTG3BCAG3M","short_pith_number":"pith:5MQQMQ46","canonical_record":{"source":{"id":"2307.08504","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-17T14:08:17Z","cross_cats_sorted":[],"title_canon_sha256":"af06938a4583582f7bbe3ac0fc40dec815a2c05af902c590d799093356066cea","abstract_canon_sha256":"60462a910a95e14fcf6827009aac8f4688936b53ffeceb0e170fe5282dc1395e"},"schema_version":"1.0"},"canonical_sha256":"eb2106439e48eaa6e0a09ccdb08806db27afa8b9c9227e24a596dc1ae48f4667","source":{"kind":"arxiv","id":"2307.08504","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.08504","created_at":"2026-07-05T07:48:47Z"},{"alias_kind":"arxiv_version","alias_value":"2307.08504v2","created_at":"2026-07-05T07:48:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08504","created_at":"2026-07-05T07:48:47Z"},{"alias_kind":"pith_short_12","alias_value":"5MQQMQ46JDVK","created_at":"2026-07-05T07:48:47Z"},{"alias_kind":"pith_short_16","alias_value":"5MQQMQ46JDVKNYFA","created_at":"2026-07-05T07:48:47Z"},{"alias_kind":"pith_short_8","alias_value":"5MQQMQ46","created_at":"2026-07-05T07:48:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5MQQMQ46JDVKNYFATTG3BCAG3M","target":"record","payload":{"canonical_record":{"source":{"id":"2307.08504","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-17T14:08:17Z","cross_cats_sorted":[],"title_canon_sha256":"af06938a4583582f7bbe3ac0fc40dec815a2c05af902c590d799093356066cea","abstract_canon_sha256":"60462a910a95e14fcf6827009aac8f4688936b53ffeceb0e170fe5282dc1395e"},"schema_version":"1.0"},"canonical_sha256":"eb2106439e48eaa6e0a09ccdb08806db27afa8b9c9227e24a596dc1ae48f4667","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:47.397663Z","signature_b64":"7Bh3knNGrA9VzClfFl6EdVWTciOzfvovZruXuBbc1k2vLbqAt9hcC98qds4HQAcYpS7tX9swzt39hsIRP2LPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb2106439e48eaa6e0a09ccdb08806db27afa8b9c9227e24a596dc1ae48f4667","last_reissued_at":"2026-07-05T07:48:47.397243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:47.397243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.08504","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":"2026-07-05T07:48:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CrUIFcCAQmb/gkIkw6t4M5eAeXUb0kU52resPnllOpXtzhdVQtpujfbZzKkNja+0WhQii2fAi6YbG6QQ3nMhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T01:55:20.668361Z"},"content_sha256":"53dd3db311e216e913cb83acc8c80f8895f39fa452a696192673efc4ad250dcd","schema_version":"1.0","event_id":"sha256:53dd3db311e216e913cb83acc8c80f8895f39fa452a696192673efc4ad250dcd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5MQQMQ46JDVKNYFATTG3BCAG3M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BUS:Efficient and Effective Vision-language Pre-training with Bottom-Up Patch Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Bi, Chaoya Jiang, Chenliang Li, Fei Huang, Haiyang Xu, Ming Yan, Qinghao Ye, Shikun Zhang, Songfang Huang, Wei Ye","submitted_at":"2023-07-17T14:08:17Z","abstract_excerpt":"Vision Transformer (ViT) based Vision-Language Pre-training (VLP) models have demonstrated impressive performance in various tasks. However, the lengthy visual token sequences fed into ViT can lead to training inefficiency and ineffectiveness. Existing efforts address the challenge by either bottom-level patch extraction in the ViT backbone or top-level patch abstraction outside, not balancing training efficiency and effectiveness well. Inspired by text summarization in natural language processing, we propose a Bottom-Up Patch Summarization approach named BUS, coordinating bottom-level extract"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08504","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/2307.08504/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":"2026-07-05T07:48:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9EUiRjUxqvRuMgPmBiYB0XFgn4ZnpYmi2yuC6BsC5cEMV7eh7L9pz31jeLl7GVl50+daRS6nEoT1vlba+eHxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T01:55:20.668833Z"},"content_sha256":"e5a2abf49a58ef4c03597b7ae4440dae8a64ec37cac928012baf496335cb47e5","schema_version":"1.0","event_id":"sha256:e5a2abf49a58ef4c03597b7ae4440dae8a64ec37cac928012baf496335cb47e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5MQQMQ46JDVKNYFATTG3BCAG3M/bundle.json","state_url":"https://pith.science/pith/5MQQMQ46JDVKNYFATTG3BCAG3M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5MQQMQ46JDVKNYFATTG3BCAG3M/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":"2026-08-01T01:55:20Z","links":{"resolver":"https://pith.science/pith/5MQQMQ46JDVKNYFATTG3BCAG3M","bundle":"https://pith.science/pith/5MQQMQ46JDVKNYFATTG3BCAG3M/bundle.json","state":"https://pith.science/pith/5MQQMQ46JDVKNYFATTG3BCAG3M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5MQQMQ46JDVKNYFATTG3BCAG3M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5MQQMQ46JDVKNYFATTG3BCAG3M","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":"60462a910a95e14fcf6827009aac8f4688936b53ffeceb0e170fe5282dc1395e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-17T14:08:17Z","title_canon_sha256":"af06938a4583582f7bbe3ac0fc40dec815a2c05af902c590d799093356066cea"},"schema_version":"1.0","source":{"id":"2307.08504","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.08504","created_at":"2026-07-05T07:48:47Z"},{"alias_kind":"arxiv_version","alias_value":"2307.08504v2","created_at":"2026-07-05T07:48:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08504","created_at":"2026-07-05T07:48:47Z"},{"alias_kind":"pith_short_12","alias_value":"5MQQMQ46JDVK","created_at":"2026-07-05T07:48:47Z"},{"alias_kind":"pith_short_16","alias_value":"5MQQMQ46JDVKNYFA","created_at":"2026-07-05T07:48:47Z"},{"alias_kind":"pith_short_8","alias_value":"5MQQMQ46","created_at":"2026-07-05T07:48:47Z"}],"graph_snapshots":[{"event_id":"sha256:e5a2abf49a58ef4c03597b7ae4440dae8a64ec37cac928012baf496335cb47e5","target":"graph","created_at":"2026-07-05T07:48:47Z","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/2307.08504/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Transformer (ViT) based Vision-Language Pre-training (VLP) models have demonstrated impressive performance in various tasks. However, the lengthy visual token sequences fed into ViT can lead to training inefficiency and ineffectiveness. Existing efforts address the challenge by either bottom-level patch extraction in the ViT backbone or top-level patch abstraction outside, not balancing training efficiency and effectiveness well. Inspired by text summarization in natural language processing, we propose a Bottom-Up Patch Summarization approach named BUS, coordinating bottom-level extract","authors_text":"Bin Bi, Chaoya Jiang, Chenliang Li, Fei Huang, Haiyang Xu, Ming Yan, Qinghao Ye, Shikun Zhang, Songfang Huang, Wei Ye","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-17T14:08:17Z","title":"BUS:Efficient and Effective Vision-language Pre-training with Bottom-Up Patch Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08504","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":"sha256:53dd3db311e216e913cb83acc8c80f8895f39fa452a696192673efc4ad250dcd","target":"record","created_at":"2026-07-05T07:48:47Z","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":"60462a910a95e14fcf6827009aac8f4688936b53ffeceb0e170fe5282dc1395e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-17T14:08:17Z","title_canon_sha256":"af06938a4583582f7bbe3ac0fc40dec815a2c05af902c590d799093356066cea"},"schema_version":"1.0","source":{"id":"2307.08504","kind":"arxiv","version":2}},"canonical_sha256":"eb2106439e48eaa6e0a09ccdb08806db27afa8b9c9227e24a596dc1ae48f4667","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb2106439e48eaa6e0a09ccdb08806db27afa8b9c9227e24a596dc1ae48f4667","first_computed_at":"2026-07-05T07:48:47.397243Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:47.397243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Bh3knNGrA9VzClfFl6EdVWTciOzfvovZruXuBbc1k2vLbqAt9hcC98qds4HQAcYpS7tX9swzt39hsIRP2LPAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:47.397663Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.08504","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53dd3db311e216e913cb83acc8c80f8895f39fa452a696192673efc4ad250dcd","sha256:e5a2abf49a58ef4c03597b7ae4440dae8a64ec37cac928012baf496335cb47e5"],"state_sha256":"dc264ff72ac06c5f1ba506c09e20b6b0cad493dc8dcca7cc189dbff01fdc5784"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oeOQXl9DtQjP5UvVY7hGnsO4cXrjoEifB754+R7btscGO3DJv12F6iARiARPAcEHKohcW4fIDvw0nsiTp7tYDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T01:55:20.675167Z","bundle_sha256":"fad8df642d131a4927ce9a343c626b491dc8d2f088710adcef4acf5d00a33d68"}}