{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GQUANC4TYEUC4KGUZAVLTFJREL","short_pith_number":"pith:GQUANC4T","canonical_record":{"source":{"id":"2106.13488","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T08:04:25Z","cross_cats_sorted":[],"title_canon_sha256":"e1ae491c2fdb2f550fbe1d265d46fb1e2321cb9b4dbbcb8eccebdf01af2dbf76","abstract_canon_sha256":"69bc26fb5568cc1925f31ac566e9cb0ecb91936fc85ac32dedb3f333daed151e"},"schema_version":"1.0"},"canonical_sha256":"3428068b93c1282e28d4c82ab9953122f34d2d810b13404f0bae47270f66cad3","source":{"kind":"arxiv","id":"2106.13488","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13488","created_at":"2026-07-05T03:30:13Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13488v4","created_at":"2026-07-05T03:30:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13488","created_at":"2026-07-05T03:30:13Z"},{"alias_kind":"pith_short_12","alias_value":"GQUANC4TYEUC","created_at":"2026-07-05T03:30:13Z"},{"alias_kind":"pith_short_16","alias_value":"GQUANC4TYEUC4KGU","created_at":"2026-07-05T03:30:13Z"},{"alias_kind":"pith_short_8","alias_value":"GQUANC4T","created_at":"2026-07-05T03:30:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GQUANC4TYEUC4KGUZAVLTFJREL","target":"record","payload":{"canonical_record":{"source":{"id":"2106.13488","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T08:04:25Z","cross_cats_sorted":[],"title_canon_sha256":"e1ae491c2fdb2f550fbe1d265d46fb1e2321cb9b4dbbcb8eccebdf01af2dbf76","abstract_canon_sha256":"69bc26fb5568cc1925f31ac566e9cb0ecb91936fc85ac32dedb3f333daed151e"},"schema_version":"1.0"},"canonical_sha256":"3428068b93c1282e28d4c82ab9953122f34d2d810b13404f0bae47270f66cad3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:30:13.225266Z","signature_b64":"XShHCPQ4irjZDwsVxx02JG3yAk9RKas9/MiCBk9Z6NA8kheFWOJnNiUhwb2U/aBMCmC/SaLCE/7wIMSXJ6yhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3428068b93c1282e28d4c82ab9953122f34d2d810b13404f0bae47270f66cad3","last_reissued_at":"2026-07-05T03:30:13.224790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:30:13.224790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.13488","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:30:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KiBDnPmos0QUVPHp63kb8E1aeYY7r5+C3S3LhArNNfivydGbiHNZ+mxxdKjsFQONoDVZEFLCfpWjOYCgzcrFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:27:23.994756Z"},"content_sha256":"7da0aff25e0fa1e02d234cfe251febd4b8504146640aee026de5e2e24df25b45","schema_version":"1.0","event_id":"sha256:7da0aff25e0fa1e02d234cfe251febd4b8504146640aee026de5e2e24df25b45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GQUANC4TYEUC4KGUZAVLTFJREL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bei Liu, Hongwei Xue, Houqiang Li, Houwen Peng, Jianlong Fu, Jiebo Luo, Yupan Huang","submitted_at":"2021-06-25T08:04:25Z","abstract_excerpt":"Vision-Language Pre-training (VLP) aims to learn multi-modal representations from image-text pairs and serves for downstream vision-language tasks in a fine-tuning fashion. The dominant VLP models adopt a CNN-Transformer architecture, which embeds images with a CNN, and then aligns images and text with a Transformer. Visual relationship between visual contents plays an important role in image understanding and is the basic for inter-modal alignment learning. However, CNNs have limitations in visual relation learning due to local receptive field's weakness in modeling long-range dependencies. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13488","kind":"arxiv","version":4},"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/2106.13488/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":"2026-07-05T03:30:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P7OpyYbyUDa64yydUPWBjjCztu1DAtQJ1wQLCOLuntYrsslSmp7MqQ5mB/EiXuLYENOH/PW5i7c5b9vWU1chCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:27:23.995716Z"},"content_sha256":"eb2cabfc5dc48ab7624be403bdd3d6d8ea7366d673586665c7b1bd3cbffba942","schema_version":"1.0","event_id":"sha256:eb2cabfc5dc48ab7624be403bdd3d6d8ea7366d673586665c7b1bd3cbffba942"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GQUANC4TYEUC4KGUZAVLTFJREL/bundle.json","state_url":"https://pith.science/pith/GQUANC4TYEUC4KGUZAVLTFJREL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GQUANC4TYEUC4KGUZAVLTFJREL/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":"2026-08-04T22:27:24Z","links":{"resolver":"https://pith.science/pith/GQUANC4TYEUC4KGUZAVLTFJREL","bundle":"https://pith.science/pith/GQUANC4TYEUC4KGUZAVLTFJREL/bundle.json","state":"https://pith.science/pith/GQUANC4TYEUC4KGUZAVLTFJREL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GQUANC4TYEUC4KGUZAVLTFJREL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GQUANC4TYEUC4KGUZAVLTFJREL","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":"69bc26fb5568cc1925f31ac566e9cb0ecb91936fc85ac32dedb3f333daed151e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T08:04:25Z","title_canon_sha256":"e1ae491c2fdb2f550fbe1d265d46fb1e2321cb9b4dbbcb8eccebdf01af2dbf76"},"schema_version":"1.0","source":{"id":"2106.13488","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13488","created_at":"2026-07-05T03:30:13Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13488v4","created_at":"2026-07-05T03:30:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13488","created_at":"2026-07-05T03:30:13Z"},{"alias_kind":"pith_short_12","alias_value":"GQUANC4TYEUC","created_at":"2026-07-05T03:30:13Z"},{"alias_kind":"pith_short_16","alias_value":"GQUANC4TYEUC4KGU","created_at":"2026-07-05T03:30:13Z"},{"alias_kind":"pith_short_8","alias_value":"GQUANC4T","created_at":"2026-07-05T03:30:13Z"}],"graph_snapshots":[{"event_id":"sha256:eb2cabfc5dc48ab7624be403bdd3d6d8ea7366d673586665c7b1bd3cbffba942","target":"graph","created_at":"2026-07-05T03:30:13Z","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/2106.13488/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Pre-training (VLP) aims to learn multi-modal representations from image-text pairs and serves for downstream vision-language tasks in a fine-tuning fashion. The dominant VLP models adopt a CNN-Transformer architecture, which embeds images with a CNN, and then aligns images and text with a Transformer. Visual relationship between visual contents plays an important role in image understanding and is the basic for inter-modal alignment learning. However, CNNs have limitations in visual relation learning due to local receptive field's weakness in modeling long-range dependencies. T","authors_text":"Bei Liu, Hongwei Xue, Houqiang Li, Houwen Peng, Jianlong Fu, Jiebo Luo, Yupan Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T08:04:25Z","title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13488","kind":"arxiv","version":4},"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":"sha256:7da0aff25e0fa1e02d234cfe251febd4b8504146640aee026de5e2e24df25b45","target":"record","created_at":"2026-07-05T03:30:13Z","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":"69bc26fb5568cc1925f31ac566e9cb0ecb91936fc85ac32dedb3f333daed151e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T08:04:25Z","title_canon_sha256":"e1ae491c2fdb2f550fbe1d265d46fb1e2321cb9b4dbbcb8eccebdf01af2dbf76"},"schema_version":"1.0","source":{"id":"2106.13488","kind":"arxiv","version":4}},"canonical_sha256":"3428068b93c1282e28d4c82ab9953122f34d2d810b13404f0bae47270f66cad3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3428068b93c1282e28d4c82ab9953122f34d2d810b13404f0bae47270f66cad3","first_computed_at":"2026-07-05T03:30:13.224790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:30:13.224790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XShHCPQ4irjZDwsVxx02JG3yAk9RKas9/MiCBk9Z6NA8kheFWOJnNiUhwb2U/aBMCmC/SaLCE/7wIMSXJ6yhBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:30:13.225266Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.13488","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7da0aff25e0fa1e02d234cfe251febd4b8504146640aee026de5e2e24df25b45","sha256:eb2cabfc5dc48ab7624be403bdd3d6d8ea7366d673586665c7b1bd3cbffba942"],"state_sha256":"ba7ad68fdbda462942ffd7aa0e7ee75ea2a153a07ea5196921448856910daa2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"deqH00VZ7ATz+a2sp1xy97hZ/9qkQaQKJHC83hGn4fbPmOntkn7r8b3SbymJulq8P5st1wJaOsnDcPWWIcT8Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:27:24.005080Z","bundle_sha256":"8e67b037de694b696c49c1e7a142151ddc83d7190bf1226bf4edf9f37490af55"}}