{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZN33M54AJ4IGE5F5LUYMGDOKKY","short_pith_number":"pith:ZN33M54A","canonical_record":{"source":{"id":"2403.07883","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-11T14:31:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"36ad0225f1d697386ebe5e8b8938d842233dc6e409362fe3f9a28e7bfea2115d","abstract_canon_sha256":"5c563e36bf7877be7379de4d9de48c6112c2b3f7bee2857a531829f25db3483f"},"schema_version":"1.0"},"canonical_sha256":"cb77b677804f106274bd5d30c30dca561ee70e2206ce1f6e0cbcd15df593ce14","source":{"kind":"arxiv","id":"2403.07883","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.07883","created_at":"2026-07-05T07:55:31Z"},{"alias_kind":"arxiv_version","alias_value":"2403.07883v1","created_at":"2026-07-05T07:55:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07883","created_at":"2026-07-05T07:55:31Z"},{"alias_kind":"pith_short_12","alias_value":"ZN33M54AJ4IG","created_at":"2026-07-05T07:55:31Z"},{"alias_kind":"pith_short_16","alias_value":"ZN33M54AJ4IGE5F5","created_at":"2026-07-05T07:55:31Z"},{"alias_kind":"pith_short_8","alias_value":"ZN33M54A","created_at":"2026-07-05T07:55:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZN33M54AJ4IGE5F5LUYMGDOKKY","target":"record","payload":{"canonical_record":{"source":{"id":"2403.07883","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-11T14:31:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"36ad0225f1d697386ebe5e8b8938d842233dc6e409362fe3f9a28e7bfea2115d","abstract_canon_sha256":"5c563e36bf7877be7379de4d9de48c6112c2b3f7bee2857a531829f25db3483f"},"schema_version":"1.0"},"canonical_sha256":"cb77b677804f106274bd5d30c30dca561ee70e2206ce1f6e0cbcd15df593ce14","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:31.243864Z","signature_b64":"U4fKGVCuY3zYsorjACplCkb4Ai9vTRZG8wdkpen18z4swQzKwrm/cR2dZH+gKL2jIYWhJJKRxWLR66jRmB61BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb77b677804f106274bd5d30c30dca561ee70e2206ce1f6e0cbcd15df593ce14","last_reissued_at":"2026-07-05T07:55:31.243471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:31.243471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.07883","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":"2026-07-05T07:55:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K2ihN94ADSv3CUX01BM9v2fao/c3i86FbdNROuouyG40+1WID5E7xQ3FAH6k0UWRIPL11HX9Wwm9EGU7PxKqDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:30:01.959791Z"},"content_sha256":"9a4737c1724d02ed94ef61b7297e7cad72c0b5a2ea7c8822e3255cf3e5757675","schema_version":"1.0","event_id":"sha256:9a4737c1724d02ed94ef61b7297e7cad72c0b5a2ea7c8822e3255cf3e5757675"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZN33M54AJ4IGE5F5LUYMGDOKKY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaoya Jiang, Chenhao Ye, Chenliang Li, Fei Huang, Haiyang Xu, Ming Yan, Shikun Zhang, Songhang Huang, Wei Ye","submitted_at":"2024-01-11T14:31:30Z","abstract_excerpt":"Vision Transformers (ViTs) have become increasingly popular in large-scale Vision and Language Pre-training (VLP) models. Although previous VLP research has demonstrated the efficacy of ViTs, these efforts still struggle with computational inefficiencies caused by lengthy visual sequences. To address this challenge, we introduce an efficient VLP approach called TRIPS, which stands for Text-Relevant Image Patch Selection. TRIPS progressively reduces the visual sequence using a text-guided patch-selection layer in the visual backbone, thereby accelerating both training and inference processes. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07883","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/2403.07883/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":"2026-07-05T07:55:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uv9NNM+Y3LlTVp+Xk9koHhxsJgPwYwpDxDNtiA32ZqsQwf/3hC4zNSS6Z7mDpZLoVmQHQATqbEdxzGrbkt5dAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:30:01.960307Z"},"content_sha256":"a09d32f69159972a1d5c0586ca1b00b6a442d4f7a4d7ba7688c1ab7eb1608dc4","schema_version":"1.0","event_id":"sha256:a09d32f69159972a1d5c0586ca1b00b6a442d4f7a4d7ba7688c1ab7eb1608dc4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZN33M54AJ4IGE5F5LUYMGDOKKY/bundle.json","state_url":"https://pith.science/pith/ZN33M54AJ4IGE5F5LUYMGDOKKY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZN33M54AJ4IGE5F5LUYMGDOKKY/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":"2026-08-04T17:30:01Z","links":{"resolver":"https://pith.science/pith/ZN33M54AJ4IGE5F5LUYMGDOKKY","bundle":"https://pith.science/pith/ZN33M54AJ4IGE5F5LUYMGDOKKY/bundle.json","state":"https://pith.science/pith/ZN33M54AJ4IGE5F5LUYMGDOKKY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZN33M54AJ4IGE5F5LUYMGDOKKY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZN33M54AJ4IGE5F5LUYMGDOKKY","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":"5c563e36bf7877be7379de4d9de48c6112c2b3f7bee2857a531829f25db3483f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-11T14:31:30Z","title_canon_sha256":"36ad0225f1d697386ebe5e8b8938d842233dc6e409362fe3f9a28e7bfea2115d"},"schema_version":"1.0","source":{"id":"2403.07883","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.07883","created_at":"2026-07-05T07:55:31Z"},{"alias_kind":"arxiv_version","alias_value":"2403.07883v1","created_at":"2026-07-05T07:55:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07883","created_at":"2026-07-05T07:55:31Z"},{"alias_kind":"pith_short_12","alias_value":"ZN33M54AJ4IG","created_at":"2026-07-05T07:55:31Z"},{"alias_kind":"pith_short_16","alias_value":"ZN33M54AJ4IGE5F5","created_at":"2026-07-05T07:55:31Z"},{"alias_kind":"pith_short_8","alias_value":"ZN33M54A","created_at":"2026-07-05T07:55:31Z"}],"graph_snapshots":[{"event_id":"sha256:a09d32f69159972a1d5c0586ca1b00b6a442d4f7a4d7ba7688c1ab7eb1608dc4","target":"graph","created_at":"2026-07-05T07:55:31Z","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/2403.07883/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Transformers (ViTs) have become increasingly popular in large-scale Vision and Language Pre-training (VLP) models. Although previous VLP research has demonstrated the efficacy of ViTs, these efforts still struggle with computational inefficiencies caused by lengthy visual sequences. To address this challenge, we introduce an efficient VLP approach called TRIPS, which stands for Text-Relevant Image Patch Selection. TRIPS progressively reduces the visual sequence using a text-guided patch-selection layer in the visual backbone, thereby accelerating both training and inference processes. T","authors_text":"Chaoya Jiang, Chenhao Ye, Chenliang Li, Fei Huang, Haiyang Xu, Ming Yan, Shikun Zhang, Songhang Huang, Wei Ye","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-11T14:31:30Z","title":"Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07883","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":"sha256:9a4737c1724d02ed94ef61b7297e7cad72c0b5a2ea7c8822e3255cf3e5757675","target":"record","created_at":"2026-07-05T07:55:31Z","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":"5c563e36bf7877be7379de4d9de48c6112c2b3f7bee2857a531829f25db3483f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-11T14:31:30Z","title_canon_sha256":"36ad0225f1d697386ebe5e8b8938d842233dc6e409362fe3f9a28e7bfea2115d"},"schema_version":"1.0","source":{"id":"2403.07883","kind":"arxiv","version":1}},"canonical_sha256":"cb77b677804f106274bd5d30c30dca561ee70e2206ce1f6e0cbcd15df593ce14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb77b677804f106274bd5d30c30dca561ee70e2206ce1f6e0cbcd15df593ce14","first_computed_at":"2026-07-05T07:55:31.243471Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:31.243471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U4fKGVCuY3zYsorjACplCkb4Ai9vTRZG8wdkpen18z4swQzKwrm/cR2dZH+gKL2jIYWhJJKRxWLR66jRmB61BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:31.243864Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.07883","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a4737c1724d02ed94ef61b7297e7cad72c0b5a2ea7c8822e3255cf3e5757675","sha256:a09d32f69159972a1d5c0586ca1b00b6a442d4f7a4d7ba7688c1ab7eb1608dc4"],"state_sha256":"78e281705c90e7bad39a78bf2dd6f2b9dfe07c511fcb2a45d62e5db5502fa682"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nuGWfgEKFN2wD3puWbhrtluk1VX8o5JyUbUruVv8pXMV4JgvT6FWq86FtIDIgOK4POzo6VaGbShOr3eD8k90CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:30:01.965383Z","bundle_sha256":"fdfdcd5cdb92633fe29a4a0ec5a0e1735ecd244d6ae2502613c47d16342ea628"}}