{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XXNOVTNTPFQOPEUZKH7J322JRA","short_pith_number":"pith:XXNOVTNT","canonical_record":{"source":{"id":"1903.00839","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-03T05:55:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f649fdf766d7c16885afa9d1533573a699801dbf99bf6cf4aa36bb5dde951d7b","abstract_canon_sha256":"b75c4eaea6935523e3b91dc69223269e33e89728640c7f072b9f9fecb8d4c3d7"},"schema_version":"1.0"},"canonical_sha256":"bddaeacdb37960e7929951fe9deb498821246583e4e608f76b28d50031ca3986","source":{"kind":"arxiv","id":"1903.00839","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.00839","created_at":"2026-05-17T23:49:38Z"},{"alias_kind":"arxiv_version","alias_value":"1903.00839v2","created_at":"2026-05-17T23:49:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00839","created_at":"2026-05-17T23:49:38Z"},{"alias_kind":"pith_short_12","alias_value":"XXNOVTNTPFQO","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XXNOVTNTPFQOPEUZ","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XXNOVTNT","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XXNOVTNTPFQOPEUZKH7J322JRA","target":"record","payload":{"canonical_record":{"source":{"id":"1903.00839","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-03T05:55:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f649fdf766d7c16885afa9d1533573a699801dbf99bf6cf4aa36bb5dde951d7b","abstract_canon_sha256":"b75c4eaea6935523e3b91dc69223269e33e89728640c7f072b9f9fecb8d4c3d7"},"schema_version":"1.0"},"canonical_sha256":"bddaeacdb37960e7929951fe9deb498821246583e4e608f76b28d50031ca3986","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:38.713720Z","signature_b64":"Z4EWElqwexWb5YpzPA/b2LPUuwbZ1yrDOJvPSghJfwXUYjuJ0hzIfPjG8NSGX1xs7Wug+HfTRsn+9XAeAFSJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bddaeacdb37960e7929951fe9deb498821246583e4e608f76b28d50031ca3986","last_reissued_at":"2026-05-17T23:49:38.713159Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:38.713159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.00839","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":"2026-05-17T23:49:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8AHj1Pt5BftCNXz3ls0Qx72qDP0qmWXJ9GuFu1sHR4hi/p56/kwTQ3YGuMeu4dE4L1YgXgD+EH2NWcq7UqjyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:53:51.826632Z"},"content_sha256":"7d516804e19666a4e422050fca4839bcbafb5f205fafafa649053d1f01000d2a","schema_version":"1.0","event_id":"sha256:7d516804e19666a4e422050fca4839bcbafb5f205fafafa649053d1f01000d2a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XXNOVTNTPFQOPEUZKH7J322JRA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Referring Expression Grounding with Cross-modal Attention-guided Erasing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Jing Shao, Xiaogang Wang, Xihui Liu, Zihao Wang","submitted_at":"2019-03-03T05:55:15Z","abstract_excerpt":"Referring expression grounding aims at locating certain objects or persons in an image with a referring expression, where the key challenge is to comprehend and align various types of information from visual and textual domain, such as visual attributes, location and interactions with surrounding regions. Although the attention mechanism has been successfully applied for cross-modal alignments, previous attention models focus on only the most dominant features of both modalities, and neglect the fact that there could be multiple comprehensive textual-visual correspondences between images and r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00839","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":"2026-05-17T23:49:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jFm0p/dXppN/hjthrdGApyJBl+YvOpzBtXNjaf92efM7PXs+2erfYVog5wwIB7RRg8r2XjtEfYOEkGOx4gaZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:53:51.827292Z"},"content_sha256":"e9bfafa3725de17a4bf006854079833c3f5871fb0d64566fef25e980827c3224","schema_version":"1.0","event_id":"sha256:e9bfafa3725de17a4bf006854079833c3f5871fb0d64566fef25e980827c3224"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XXNOVTNTPFQOPEUZKH7J322JRA/bundle.json","state_url":"https://pith.science/pith/XXNOVTNTPFQOPEUZKH7J322JRA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XXNOVTNTPFQOPEUZKH7J322JRA/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":"2026-05-25T21:53:51Z","links":{"resolver":"https://pith.science/pith/XXNOVTNTPFQOPEUZKH7J322JRA","bundle":"https://pith.science/pith/XXNOVTNTPFQOPEUZKH7J322JRA/bundle.json","state":"https://pith.science/pith/XXNOVTNTPFQOPEUZKH7J322JRA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XXNOVTNTPFQOPEUZKH7J322JRA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XXNOVTNTPFQOPEUZKH7J322JRA","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":"b75c4eaea6935523e3b91dc69223269e33e89728640c7f072b9f9fecb8d4c3d7","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-03T05:55:15Z","title_canon_sha256":"f649fdf766d7c16885afa9d1533573a699801dbf99bf6cf4aa36bb5dde951d7b"},"schema_version":"1.0","source":{"id":"1903.00839","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.00839","created_at":"2026-05-17T23:49:38Z"},{"alias_kind":"arxiv_version","alias_value":"1903.00839v2","created_at":"2026-05-17T23:49:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00839","created_at":"2026-05-17T23:49:38Z"},{"alias_kind":"pith_short_12","alias_value":"XXNOVTNTPFQO","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XXNOVTNTPFQOPEUZ","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XXNOVTNT","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:e9bfafa3725de17a4bf006854079833c3f5871fb0d64566fef25e980827c3224","target":"graph","created_at":"2026-05-17T23:49:38Z","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":"Referring expression grounding aims at locating certain objects or persons in an image with a referring expression, where the key challenge is to comprehend and align various types of information from visual and textual domain, such as visual attributes, location and interactions with surrounding regions. Although the attention mechanism has been successfully applied for cross-modal alignments, previous attention models focus on only the most dominant features of both modalities, and neglect the fact that there could be multiple comprehensive textual-visual correspondences between images and r","authors_text":"Hongsheng Li, Jing Shao, Xiaogang Wang, Xihui Liu, Zihao Wang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-03T05:55:15Z","title":"Improving Referring Expression Grounding with Cross-modal Attention-guided Erasing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00839","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":"sha256:7d516804e19666a4e422050fca4839bcbafb5f205fafafa649053d1f01000d2a","target":"record","created_at":"2026-05-17T23:49:38Z","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":"b75c4eaea6935523e3b91dc69223269e33e89728640c7f072b9f9fecb8d4c3d7","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-03T05:55:15Z","title_canon_sha256":"f649fdf766d7c16885afa9d1533573a699801dbf99bf6cf4aa36bb5dde951d7b"},"schema_version":"1.0","source":{"id":"1903.00839","kind":"arxiv","version":2}},"canonical_sha256":"bddaeacdb37960e7929951fe9deb498821246583e4e608f76b28d50031ca3986","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bddaeacdb37960e7929951fe9deb498821246583e4e608f76b28d50031ca3986","first_computed_at":"2026-05-17T23:49:38.713159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:38.713159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z4EWElqwexWb5YpzPA/b2LPUuwbZ1yrDOJvPSghJfwXUYjuJ0hzIfPjG8NSGX1xs7Wug+HfTRsn+9XAeAFSJAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:38.713720Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.00839","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d516804e19666a4e422050fca4839bcbafb5f205fafafa649053d1f01000d2a","sha256:e9bfafa3725de17a4bf006854079833c3f5871fb0d64566fef25e980827c3224"],"state_sha256":"e5203e01b367b2ba0e84537bec5df45f827ebc1ac19aa5cdcc6a22b71e98a11e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2gTbhkOF3H7v1+yqL1kv249Lhu/v3Wg6yoX/PWYBbAcx0+/eN0a8moIwuYriWm0rAUX80uVFFdtw0q0VB3s/Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T21:53:51.830520Z","bundle_sha256":"fb53ee4e4eba0a8c0e1dd45b2bca15ab3485eede73107971536481199e0f416b"}}