{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:MBPQBEBZ6D6HCMFZPWWF6BOGBI","short_pith_number":"pith:MBPQBEBZ","canonical_record":{"source":{"id":"1904.04745","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-09T15:51:07Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6740c674a5afe0e5be1cf68e68a097697e4969036cdbfdfb54de2eb20396f3c3","abstract_canon_sha256":"e0dab0288e249490c30ffa1d1a52974f104ebf5f624d2a68eca5897846dd8eab"},"schema_version":"1.0"},"canonical_sha256":"605f009039f0fc7130b97dac5f05c60a3d382c56c1677c95c2d83f7be31e05f7","source":{"kind":"arxiv","id":"1904.04745","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04745","created_at":"2026-05-17T23:48:58Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04745v1","created_at":"2026-05-17T23:48:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04745","created_at":"2026-05-17T23:48:58Z"},{"alias_kind":"pith_short_12","alias_value":"MBPQBEBZ6D6H","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"MBPQBEBZ6D6HCMFZ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"MBPQBEBZ","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:MBPQBEBZ6D6HCMFZPWWF6BOGBI","target":"record","payload":{"canonical_record":{"source":{"id":"1904.04745","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-09T15:51:07Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6740c674a5afe0e5be1cf68e68a097697e4969036cdbfdfb54de2eb20396f3c3","abstract_canon_sha256":"e0dab0288e249490c30ffa1d1a52974f104ebf5f624d2a68eca5897846dd8eab"},"schema_version":"1.0"},"canonical_sha256":"605f009039f0fc7130b97dac5f05c60a3d382c56c1677c95c2d83f7be31e05f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:58.269154Z","signature_b64":"FfUkqifHCg9CRuDtxNspQ83Y9NS6ocMCNCAgR0Z26+Oo2T27h47NFtJkA5+kWVuhfN5chOSYVl02u8VWVCmDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"605f009039f0fc7130b97dac5f05c60a3d382c56c1677c95c2d83f7be31e05f7","last_reissued_at":"2026-05-17T23:48:58.268754Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:58.268754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.04745","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:48:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OVI7UAE2USAI32/z9Z6cx4NN62XKyDC9v4VE5tTvu0ol+1preJnCtmPP8/+WJ8W51631SX36ORRPvqFzl6HqCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T17:33:07.080621Z"},"content_sha256":"885c0d7a54f6103ec65ed8569228bdb87e08e1a1ec2c56f7e5c3b70a1f0d34f2","schema_version":"1.0","event_id":"sha256:885c0d7a54f6103ec65ed8569228bdb87e08e1a1ec2c56f7e5c3b70a1f0d34f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:MBPQBEBZ6D6HCMFZPWWF6BOGBI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-Modal Self-Attention Network for Referring Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Linwei Ye, Mrigank Rochan, Yang Wang, Zhi Liu","submitted_at":"2019-04-09T15:51:07Z","abstract_excerpt":"We consider the problem of referring image segmentation. Given an input image and a natural language expression, the goal is to segment the object referred by the language expression in the image. Existing works in this area treat the language expression and the input image separately in their representations. They do not sufficiently capture long-range correlations between these two modalities. In this paper, we propose a cross-modal self-attention (CMSA) module that effectively captures the long-range dependencies between linguistic and visual features. Our model can adaptively focus on info"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04745","kind":"arxiv","version":1},"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":"2026-05-17T23:48:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7X/oJ3xNiUBQore7XQs4qgCJXQROyquIeANyVPkL02PWZ1T8KlmVXlXd9pgEl45YgSnBylILzJ+fod8VR9lkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T17:33:07.081373Z"},"content_sha256":"5e7d028a18e932840de373e98f67567ec805ebd7fa2d10c34a639c86c9bf75b2","schema_version":"1.0","event_id":"sha256:5e7d028a18e932840de373e98f67567ec805ebd7fa2d10c34a639c86c9bf75b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MBPQBEBZ6D6HCMFZPWWF6BOGBI/bundle.json","state_url":"https://pith.science/pith/MBPQBEBZ6D6HCMFZPWWF6BOGBI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MBPQBEBZ6D6HCMFZPWWF6BOGBI/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":"2026-06-09T17:33:07Z","links":{"resolver":"https://pith.science/pith/MBPQBEBZ6D6HCMFZPWWF6BOGBI","bundle":"https://pith.science/pith/MBPQBEBZ6D6HCMFZPWWF6BOGBI/bundle.json","state":"https://pith.science/pith/MBPQBEBZ6D6HCMFZPWWF6BOGBI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MBPQBEBZ6D6HCMFZPWWF6BOGBI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MBPQBEBZ6D6HCMFZPWWF6BOGBI","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":"e0dab0288e249490c30ffa1d1a52974f104ebf5f624d2a68eca5897846dd8eab","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-09T15:51:07Z","title_canon_sha256":"6740c674a5afe0e5be1cf68e68a097697e4969036cdbfdfb54de2eb20396f3c3"},"schema_version":"1.0","source":{"id":"1904.04745","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04745","created_at":"2026-05-17T23:48:58Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04745v1","created_at":"2026-05-17T23:48:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04745","created_at":"2026-05-17T23:48:58Z"},{"alias_kind":"pith_short_12","alias_value":"MBPQBEBZ6D6H","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"MBPQBEBZ6D6HCMFZ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"MBPQBEBZ","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:5e7d028a18e932840de373e98f67567ec805ebd7fa2d10c34a639c86c9bf75b2","target":"graph","created_at":"2026-05-17T23:48:58Z","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 consider the problem of referring image segmentation. Given an input image and a natural language expression, the goal is to segment the object referred by the language expression in the image. Existing works in this area treat the language expression and the input image separately in their representations. They do not sufficiently capture long-range correlations between these two modalities. In this paper, we propose a cross-modal self-attention (CMSA) module that effectively captures the long-range dependencies between linguistic and visual features. Our model can adaptively focus on info","authors_text":"Linwei Ye, Mrigank Rochan, Yang Wang, Zhi Liu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-09T15:51:07Z","title":"Cross-Modal Self-Attention Network for Referring Image Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04745","kind":"arxiv","version":1},"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":"sha256:885c0d7a54f6103ec65ed8569228bdb87e08e1a1ec2c56f7e5c3b70a1f0d34f2","target":"record","created_at":"2026-05-17T23:48:58Z","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":"e0dab0288e249490c30ffa1d1a52974f104ebf5f624d2a68eca5897846dd8eab","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-09T15:51:07Z","title_canon_sha256":"6740c674a5afe0e5be1cf68e68a097697e4969036cdbfdfb54de2eb20396f3c3"},"schema_version":"1.0","source":{"id":"1904.04745","kind":"arxiv","version":1}},"canonical_sha256":"605f009039f0fc7130b97dac5f05c60a3d382c56c1677c95c2d83f7be31e05f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"605f009039f0fc7130b97dac5f05c60a3d382c56c1677c95c2d83f7be31e05f7","first_computed_at":"2026-05-17T23:48:58.268754Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:58.268754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FfUkqifHCg9CRuDtxNspQ83Y9NS6ocMCNCAgR0Z26+Oo2T27h47NFtJkA5+kWVuhfN5chOSYVl02u8VWVCmDDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:58.269154Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.04745","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:885c0d7a54f6103ec65ed8569228bdb87e08e1a1ec2c56f7e5c3b70a1f0d34f2","sha256:5e7d028a18e932840de373e98f67567ec805ebd7fa2d10c34a639c86c9bf75b2"],"state_sha256":"e2814e5d981ce38e92f4b885c3beae9d077f144588030c3f8e8f77448c9cfc02"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q8ewJNzF1+7HkjUK9FWDjt8h8bIRn07PE+19e0AFPrBLqfho2N1at23k1aNoezbimUnbBU2o1QYot41dxVF4Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T17:33:07.086079Z","bundle_sha256":"ff3c06e2dc4d30b5c1bdee6251ac83f5ea4b2d337d9d917a1714d3c3fd8d0a84"}}