{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:H6L6STUVJ2TPXVMPYYSIKBEBAM","short_pith_number":"pith:H6L6STUV","canonical_record":{"source":{"id":"1702.07191","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-23T12:28:18Z","cross_cats_sorted":[],"title_canon_sha256":"a5ed5cbe4620c3d01c1fcdac8e52c14eec5c6c2ca8dc0730f0aee3d15481e58e","abstract_canon_sha256":"db847b4adc3ab24c95b4a17454a05f2df6a1b8c6f9c0d1a7eb5c30b5910c4e61"},"schema_version":"1.0"},"canonical_sha256":"3f97e94e954ea6fbd58fc6248504810331140e417f673113209fc02565ecf5d8","source":{"kind":"arxiv","id":"1702.07191","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.07191","created_at":"2026-05-18T00:46:43Z"},{"alias_kind":"arxiv_version","alias_value":"1702.07191v2","created_at":"2026-05-18T00:46:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.07191","created_at":"2026-05-18T00:46:43Z"},{"alias_kind":"pith_short_12","alias_value":"H6L6STUVJ2TP","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"H6L6STUVJ2TPXVMP","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"H6L6STUV","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:H6L6STUVJ2TPXVMPYYSIKBEBAM","target":"record","payload":{"canonical_record":{"source":{"id":"1702.07191","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-23T12:28:18Z","cross_cats_sorted":[],"title_canon_sha256":"a5ed5cbe4620c3d01c1fcdac8e52c14eec5c6c2ca8dc0730f0aee3d15481e58e","abstract_canon_sha256":"db847b4adc3ab24c95b4a17454a05f2df6a1b8c6f9c0d1a7eb5c30b5910c4e61"},"schema_version":"1.0"},"canonical_sha256":"3f97e94e954ea6fbd58fc6248504810331140e417f673113209fc02565ecf5d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:43.955051Z","signature_b64":"J5qaNeqmIalxIy7ykU5IFA2aDQpu7QMvA0IMPY3/O7RoUOxoLVCopGnzoxvsXTfNkvG98N1c54LH/Q88ksb4Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f97e94e954ea6fbd58fc6248504810331140e417f673113209fc02565ecf5d8","last_reissued_at":"2026-05-18T00:46:43.954363Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:43.954363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.07191","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":"2026-05-18T00:46:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8YRR25cdjIS6wet+BlLUH8ztfNyH0fBo7EJ8i3eJSzKCDLAg6cFrgI7KIpB70SMurrL1t4aIYs6fYUVZ2mG1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T06:10:41.764024Z"},"content_sha256":"7470d6df44b6fc1ff8a8b706554c38424a323a7496d778ea7685d2c3b674ad51","schema_version":"1.0","event_id":"sha256:7470d6df44b6fc1ff8a8b706554c38424a323a7496d778ea7685d2c3b674ad51"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:H6L6STUVJ2TPXVMPYYSIKBEBAM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ViP-CNN: Visual Phrase Guided Convolutional Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wanli Ouyang, Xiaogang Wang, Xiao'ou Tang, Yikang Li","submitted_at":"2017-02-23T12:28:18Z","abstract_excerpt":"As the intermediate level task connecting image captioning and object detection, visual relationship detection started to catch researchers' attention because of its descriptive power and clear structure. It detects the objects and captures their pair-wise interactions with a subject-predicate-object triplet, e.g. person-ride-horse. In this paper, each visual relationship is considered as a phrase with three components. We formulate the visual relationship detection as three inter-connected recognition problems and propose a Visual Phrase guided Convolutional Neural Network (ViP-CNN) to addres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.07191","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":""},"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":"2026-05-18T00:46:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5b0ySlvFehAHdfrRt6b4UOlM8FREJa+vTafe1Z7tRXB84uKQDKkXM3ODlTrqCvFIUeM16NrxLSKYreqCFB+qDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T06:10:41.764388Z"},"content_sha256":"2252cee948ad3c7509f57c1b8de78f2af03b1d142806ef3b78e90e57dd0f94b0","schema_version":"1.0","event_id":"sha256:2252cee948ad3c7509f57c1b8de78f2af03b1d142806ef3b78e90e57dd0f94b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H6L6STUVJ2TPXVMPYYSIKBEBAM/bundle.json","state_url":"https://pith.science/pith/H6L6STUVJ2TPXVMPYYSIKBEBAM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H6L6STUVJ2TPXVMPYYSIKBEBAM/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":"2026-05-30T06:10:41Z","links":{"resolver":"https://pith.science/pith/H6L6STUVJ2TPXVMPYYSIKBEBAM","bundle":"https://pith.science/pith/H6L6STUVJ2TPXVMPYYSIKBEBAM/bundle.json","state":"https://pith.science/pith/H6L6STUVJ2TPXVMPYYSIKBEBAM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H6L6STUVJ2TPXVMPYYSIKBEBAM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:H6L6STUVJ2TPXVMPYYSIKBEBAM","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":"db847b4adc3ab24c95b4a17454a05f2df6a1b8c6f9c0d1a7eb5c30b5910c4e61","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-23T12:28:18Z","title_canon_sha256":"a5ed5cbe4620c3d01c1fcdac8e52c14eec5c6c2ca8dc0730f0aee3d15481e58e"},"schema_version":"1.0","source":{"id":"1702.07191","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.07191","created_at":"2026-05-18T00:46:43Z"},{"alias_kind":"arxiv_version","alias_value":"1702.07191v2","created_at":"2026-05-18T00:46:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.07191","created_at":"2026-05-18T00:46:43Z"},{"alias_kind":"pith_short_12","alias_value":"H6L6STUVJ2TP","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"H6L6STUVJ2TPXVMP","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"H6L6STUV","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:2252cee948ad3c7509f57c1b8de78f2af03b1d142806ef3b78e90e57dd0f94b0","target":"graph","created_at":"2026-05-18T00:46:43Z","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"},"paper":{"abstract_excerpt":"As the intermediate level task connecting image captioning and object detection, visual relationship detection started to catch researchers' attention because of its descriptive power and clear structure. It detects the objects and captures their pair-wise interactions with a subject-predicate-object triplet, e.g. person-ride-horse. In this paper, each visual relationship is considered as a phrase with three components. We formulate the visual relationship detection as three inter-connected recognition problems and propose a Visual Phrase guided Convolutional Neural Network (ViP-CNN) to addres","authors_text":"Wanli Ouyang, Xiaogang Wang, Xiao'ou Tang, Yikang Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-23T12:28:18Z","title":"ViP-CNN: Visual Phrase Guided Convolutional Neural Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.07191","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":"sha256:7470d6df44b6fc1ff8a8b706554c38424a323a7496d778ea7685d2c3b674ad51","target":"record","created_at":"2026-05-18T00:46:43Z","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":"db847b4adc3ab24c95b4a17454a05f2df6a1b8c6f9c0d1a7eb5c30b5910c4e61","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-23T12:28:18Z","title_canon_sha256":"a5ed5cbe4620c3d01c1fcdac8e52c14eec5c6c2ca8dc0730f0aee3d15481e58e"},"schema_version":"1.0","source":{"id":"1702.07191","kind":"arxiv","version":2}},"canonical_sha256":"3f97e94e954ea6fbd58fc6248504810331140e417f673113209fc02565ecf5d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f97e94e954ea6fbd58fc6248504810331140e417f673113209fc02565ecf5d8","first_computed_at":"2026-05-18T00:46:43.954363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:43.954363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J5qaNeqmIalxIy7ykU5IFA2aDQpu7QMvA0IMPY3/O7RoUOxoLVCopGnzoxvsXTfNkvG98N1c54LH/Q88ksb4Bg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:43.955051Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.07191","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7470d6df44b6fc1ff8a8b706554c38424a323a7496d778ea7685d2c3b674ad51","sha256:2252cee948ad3c7509f57c1b8de78f2af03b1d142806ef3b78e90e57dd0f94b0"],"state_sha256":"afbac0931e22970de8cea70d72503c2469847e88e869358ddb66f75f71f20b33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1nZ0YTPu7sbbmcB62M+TAQl49gt56z6BujK5ValJ2KfXXYozCpjpawu76pOXCa/u/XeD4Z90J0UudKGqn0clCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T06:10:41.766430Z","bundle_sha256":"4f8cb9ae5fa93300dece67c689b77eb4b026eb6341471769516d036e854fc49c"}}