{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:HRTY7XLNR7X2O26K2LOX6A54ME","short_pith_number":"pith:HRTY7XLN","canonical_record":{"source":{"id":"1712.01892","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-05T19:57:52Z","cross_cats_sorted":[],"title_canon_sha256":"42da911c76973f68da4a0fc62fe84ca9fbcd8af8d10860b320cd7ad8de9219d1","abstract_canon_sha256":"716bd2d8d2c040a491742d23ad8d067e4079b50534baacecd06a2491c2b49a2e"},"schema_version":"1.0"},"canonical_sha256":"3c678fdd6d8fefa76bcad2dd7f03bc6102f1c9329df6aa2d8b01a79ef033786f","source":{"kind":"arxiv","id":"1712.01892","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.01892","created_at":"2026-05-17T23:41:40Z"},{"alias_kind":"arxiv_version","alias_value":"1712.01892v2","created_at":"2026-05-17T23:41:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.01892","created_at":"2026-05-17T23:41:40Z"},{"alias_kind":"pith_short_12","alias_value":"HRTY7XLNR7X2","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"HRTY7XLNR7X2O26K","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"HRTY7XLN","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:HRTY7XLNR7X2O26K2LOX6A54ME","target":"record","payload":{"canonical_record":{"source":{"id":"1712.01892","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-05T19:57:52Z","cross_cats_sorted":[],"title_canon_sha256":"42da911c76973f68da4a0fc62fe84ca9fbcd8af8d10860b320cd7ad8de9219d1","abstract_canon_sha256":"716bd2d8d2c040a491742d23ad8d067e4079b50534baacecd06a2491c2b49a2e"},"schema_version":"1.0"},"canonical_sha256":"3c678fdd6d8fefa76bcad2dd7f03bc6102f1c9329df6aa2d8b01a79ef033786f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:40.053333Z","signature_b64":"qQfWkjFauCep21kmJsiVnY0BGsxvcDu4FqsG+KS9ZsMYvKHt8XUUxg5Rf9/Sc0p/lqVPojvl81izm4yO5bLtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c678fdd6d8fefa76bcad2dd7f03bc6102f1c9329df6aa2d8b01a79ef033786f","last_reissued_at":"2026-05-17T23:41:40.052787Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:40.052787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.01892","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":"2026-05-17T23:41:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IFA3RXPq6XLo7JtyzbEa+bOZWfkR+MlMmRYZ30Wcuw3LDhgVNfH5TO6ybxgmCMpb1sWwp4FtJwEm6w0GRL1FCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T03:38:02.403978Z"},"content_sha256":"652c4df34e711910824c9cf4e13bc9a4c8a7e93c5ebd11d6664b8c4580ad5c0e","schema_version":"1.0","event_id":"sha256:652c4df34e711910824c9cf4e13bc9a4c8a7e93c5ebd11d6664b8c4580ad5c0e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:HRTY7XLNR7X2O26K2LOX6A54ME","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Grounding Referring Expressions in Images by Variational Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanwang Zhang, Shih-Fu Chang, Yulei Niu","submitted_at":"2017-12-05T19:57:52Z","abstract_excerpt":"We focus on grounding (i.e., localizing or linking) referring expressions in images, e.g., \"largest elephant standing behind baby elephant\". This is a general yet challenging vision-language task since it does not only require the localization of objects, but also the multimodal comprehension of context --- visual attributes (e.g., \"largest\", \"baby\") and relationships (e.g., \"behind\") that help to distinguish the referent from other objects, especially those of the same category. Due to the exponential complexity involved in modeling the context associated with multiple image regions, existing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.01892","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":"2026-05-17T23:41:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ICMNIxNoRff+XIgSi+Mw8438Xfp9oVotCiXmNxkCft3tTFJonwCT4Q1gbiqcUmBDzeHkhzvrfKZqUcTID07GDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T03:38:02.404340Z"},"content_sha256":"30940caed4462eef6802906b8149e3108f76c310a6b34e25bb85acd01098a9ed","schema_version":"1.0","event_id":"sha256:30940caed4462eef6802906b8149e3108f76c310a6b34e25bb85acd01098a9ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HRTY7XLNR7X2O26K2LOX6A54ME/bundle.json","state_url":"https://pith.science/pith/HRTY7XLNR7X2O26K2LOX6A54ME/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HRTY7XLNR7X2O26K2LOX6A54ME/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":"2026-05-28T03:38:02Z","links":{"resolver":"https://pith.science/pith/HRTY7XLNR7X2O26K2LOX6A54ME","bundle":"https://pith.science/pith/HRTY7XLNR7X2O26K2LOX6A54ME/bundle.json","state":"https://pith.science/pith/HRTY7XLNR7X2O26K2LOX6A54ME/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HRTY7XLNR7X2O26K2LOX6A54ME/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:HRTY7XLNR7X2O26K2LOX6A54ME","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":"716bd2d8d2c040a491742d23ad8d067e4079b50534baacecd06a2491c2b49a2e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-05T19:57:52Z","title_canon_sha256":"42da911c76973f68da4a0fc62fe84ca9fbcd8af8d10860b320cd7ad8de9219d1"},"schema_version":"1.0","source":{"id":"1712.01892","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.01892","created_at":"2026-05-17T23:41:40Z"},{"alias_kind":"arxiv_version","alias_value":"1712.01892v2","created_at":"2026-05-17T23:41:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.01892","created_at":"2026-05-17T23:41:40Z"},{"alias_kind":"pith_short_12","alias_value":"HRTY7XLNR7X2","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"HRTY7XLNR7X2O26K","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"HRTY7XLN","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:30940caed4462eef6802906b8149e3108f76c310a6b34e25bb85acd01098a9ed","target":"graph","created_at":"2026-05-17T23:41:40Z","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":"We focus on grounding (i.e., localizing or linking) referring expressions in images, e.g., \"largest elephant standing behind baby elephant\". This is a general yet challenging vision-language task since it does not only require the localization of objects, but also the multimodal comprehension of context --- visual attributes (e.g., \"largest\", \"baby\") and relationships (e.g., \"behind\") that help to distinguish the referent from other objects, especially those of the same category. Due to the exponential complexity involved in modeling the context associated with multiple image regions, existing","authors_text":"Hanwang Zhang, Shih-Fu Chang, Yulei Niu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-05T19:57:52Z","title":"Grounding Referring Expressions in Images by Variational Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.01892","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":"sha256:652c4df34e711910824c9cf4e13bc9a4c8a7e93c5ebd11d6664b8c4580ad5c0e","target":"record","created_at":"2026-05-17T23:41:40Z","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":"716bd2d8d2c040a491742d23ad8d067e4079b50534baacecd06a2491c2b49a2e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-05T19:57:52Z","title_canon_sha256":"42da911c76973f68da4a0fc62fe84ca9fbcd8af8d10860b320cd7ad8de9219d1"},"schema_version":"1.0","source":{"id":"1712.01892","kind":"arxiv","version":2}},"canonical_sha256":"3c678fdd6d8fefa76bcad2dd7f03bc6102f1c9329df6aa2d8b01a79ef033786f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c678fdd6d8fefa76bcad2dd7f03bc6102f1c9329df6aa2d8b01a79ef033786f","first_computed_at":"2026-05-17T23:41:40.052787Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:40.052787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qQfWkjFauCep21kmJsiVnY0BGsxvcDu4FqsG+KS9ZsMYvKHt8XUUxg5Rf9/Sc0p/lqVPojvl81izm4yO5bLtAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:40.053333Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.01892","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:652c4df34e711910824c9cf4e13bc9a4c8a7e93c5ebd11d6664b8c4580ad5c0e","sha256:30940caed4462eef6802906b8149e3108f76c310a6b34e25bb85acd01098a9ed"],"state_sha256":"423321c6dc6f842280be78f82674bc32ca97f0e645dd03129c20501f9d215ff2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NWNLiC9UvEd4DnuAqEY6uMuPHcQrLieGy3Sh9Q3xgyf8h8tbPtjVju74nWzFSztFgvMHqWAZfS+U0Dt5SJPQBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T03:38:02.406285Z","bundle_sha256":"f77fe341f199cc1613bda8f673fd79df29e311abd15dc59c2d006770bed4dccf"}}