{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:HDLTRADBTFJWLIQOPKVWH4373R","short_pith_number":"pith:HDLTRADB","canonical_record":{"source":{"id":"1707.09700","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-31T02:40:19Z","cross_cats_sorted":[],"title_canon_sha256":"ee7c327e178ca839203a9af78eff25e7ea518b03009bbf7af223875a96218dd4","abstract_canon_sha256":"b8e220dd3567530dbdbe6b59a3a6a9e1a2838b92ea4e861a7c595bc7694e54d6"},"schema_version":"1.0"},"canonical_sha256":"38d7388061995365a20e7aab63f37fdc41e11bd4d7fda907f5ba00e93d50b493","source":{"kind":"arxiv","id":"1707.09700","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.09700","created_at":"2026-05-18T00:35:08Z"},{"alias_kind":"arxiv_version","alias_value":"1707.09700v2","created_at":"2026-05-18T00:35:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09700","created_at":"2026-05-18T00:35:08Z"},{"alias_kind":"pith_short_12","alias_value":"HDLTRADBTFJW","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"HDLTRADBTFJWLIQO","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"HDLTRADB","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:HDLTRADBTFJWLIQOPKVWH4373R","target":"record","payload":{"canonical_record":{"source":{"id":"1707.09700","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-31T02:40:19Z","cross_cats_sorted":[],"title_canon_sha256":"ee7c327e178ca839203a9af78eff25e7ea518b03009bbf7af223875a96218dd4","abstract_canon_sha256":"b8e220dd3567530dbdbe6b59a3a6a9e1a2838b92ea4e861a7c595bc7694e54d6"},"schema_version":"1.0"},"canonical_sha256":"38d7388061995365a20e7aab63f37fdc41e11bd4d7fda907f5ba00e93d50b493","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:08.939415Z","signature_b64":"PBzLqx+EajQ+b4YPclj3IhvxLsASPBMBhIUSSty5cOZb0/NOCarTZe0VIlyOM1lw5FoDRO7gO1GI/N2TPGTrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38d7388061995365a20e7aab63f37fdc41e11bd4d7fda907f5ba00e93d50b493","last_reissued_at":"2026-05-18T00:35:08.938988Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:08.938988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.09700","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":"2026-05-18T00:35:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BtD+rf2bSPCypojGIO2/fG1VWmeySrU/ko7h84rPp6DdTmQVqlIZOOMwkBDwBF6n136F039RemuuwdZoGDRFCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T05:09:09.969940Z"},"content_sha256":"3f13d6acf43148ff941685be3a4ced9868ddcdad9d35ebb54e312f69342dec9e","schema_version":"1.0","event_id":"sha256:3f13d6acf43148ff941685be3a4ced9868ddcdad9d35ebb54e312f69342dec9e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:HDLTRADBTFJWLIQOPKVWH4373R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scene Graph Generation from Objects, Phrases and Region Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bolei Zhou, Kun Wang, Wanli Ouyang, Xiaogang Wang, Yikang Li","submitted_at":"2017-07-31T02:40:19Z","abstract_excerpt":"Object detection, scene graph generation and region captioning, which are three scene understanding tasks at different semantic levels, are tied together: scene graphs are generated on top of objects detected in an image with their pairwise relationship predicted, while region captioning gives a language description of the objects, their attributes, relations, and other context information. In this work, to leverage the mutual connections across semantic levels, we propose a novel neural network model, termed as Multi-level Scene Description Network (denoted as MSDN), to solve the three vision"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09700","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":"2026-05-18T00:35:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/+l8rOt3Oxt1Y5msyDxsJEDRi9GZkBASWpt8UbgCkXVi75AmtWfPwc+0rM9KNod5MWvUHcaSdOzrz8fc4ITkCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T05:09:09.970285Z"},"content_sha256":"874c64d4f00e088dd4a10b70960644b871fb31ae2b759a7cb013b5278f156838","schema_version":"1.0","event_id":"sha256:874c64d4f00e088dd4a10b70960644b871fb31ae2b759a7cb013b5278f156838"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HDLTRADBTFJWLIQOPKVWH4373R/bundle.json","state_url":"https://pith.science/pith/HDLTRADBTFJWLIQOPKVWH4373R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HDLTRADBTFJWLIQOPKVWH4373R/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":"2026-05-30T05:09:09Z","links":{"resolver":"https://pith.science/pith/HDLTRADBTFJWLIQOPKVWH4373R","bundle":"https://pith.science/pith/HDLTRADBTFJWLIQOPKVWH4373R/bundle.json","state":"https://pith.science/pith/HDLTRADBTFJWLIQOPKVWH4373R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HDLTRADBTFJWLIQOPKVWH4373R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:HDLTRADBTFJWLIQOPKVWH4373R","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":"b8e220dd3567530dbdbe6b59a3a6a9e1a2838b92ea4e861a7c595bc7694e54d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-31T02:40:19Z","title_canon_sha256":"ee7c327e178ca839203a9af78eff25e7ea518b03009bbf7af223875a96218dd4"},"schema_version":"1.0","source":{"id":"1707.09700","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.09700","created_at":"2026-05-18T00:35:08Z"},{"alias_kind":"arxiv_version","alias_value":"1707.09700v2","created_at":"2026-05-18T00:35:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09700","created_at":"2026-05-18T00:35:08Z"},{"alias_kind":"pith_short_12","alias_value":"HDLTRADBTFJW","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"HDLTRADBTFJWLIQO","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"HDLTRADB","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:874c64d4f00e088dd4a10b70960644b871fb31ae2b759a7cb013b5278f156838","target":"graph","created_at":"2026-05-18T00:35:08Z","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":"Object detection, scene graph generation and region captioning, which are three scene understanding tasks at different semantic levels, are tied together: scene graphs are generated on top of objects detected in an image with their pairwise relationship predicted, while region captioning gives a language description of the objects, their attributes, relations, and other context information. In this work, to leverage the mutual connections across semantic levels, we propose a novel neural network model, termed as Multi-level Scene Description Network (denoted as MSDN), to solve the three vision","authors_text":"Bolei Zhou, Kun Wang, Wanli Ouyang, Xiaogang Wang, Yikang Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-31T02:40:19Z","title":"Scene Graph Generation from Objects, Phrases and Region Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09700","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":"sha256:3f13d6acf43148ff941685be3a4ced9868ddcdad9d35ebb54e312f69342dec9e","target":"record","created_at":"2026-05-18T00:35:08Z","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":"b8e220dd3567530dbdbe6b59a3a6a9e1a2838b92ea4e861a7c595bc7694e54d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-31T02:40:19Z","title_canon_sha256":"ee7c327e178ca839203a9af78eff25e7ea518b03009bbf7af223875a96218dd4"},"schema_version":"1.0","source":{"id":"1707.09700","kind":"arxiv","version":2}},"canonical_sha256":"38d7388061995365a20e7aab63f37fdc41e11bd4d7fda907f5ba00e93d50b493","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38d7388061995365a20e7aab63f37fdc41e11bd4d7fda907f5ba00e93d50b493","first_computed_at":"2026-05-18T00:35:08.938988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:08.938988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PBzLqx+EajQ+b4YPclj3IhvxLsASPBMBhIUSSty5cOZb0/NOCarTZe0VIlyOM1lw5FoDRO7gO1GI/N2TPGTrAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:08.939415Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.09700","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f13d6acf43148ff941685be3a4ced9868ddcdad9d35ebb54e312f69342dec9e","sha256:874c64d4f00e088dd4a10b70960644b871fb31ae2b759a7cb013b5278f156838"],"state_sha256":"83551edd8f4dc9cd1e51fcaeaf253778ec1b65fc6359ae96cc917bbc85a1598e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KSrNB/VzO3bNEkvveTkZkq3jILyeo8k7BQioiJwCaF+6rvFSCKZcafDLSz8ib1nVLTBXxpYVIsnmMGClykgCBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T05:09:09.972213Z","bundle_sha256":"65ef219ce8fd21501098bfdbe6e9ae1f74b9ca24a9e19f752f3d7e923d6effe2"}}