{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:X3XAGENDCFGDMAOM33BNNRUA6D","short_pith_number":"pith:X3XAGEND","canonical_record":{"source":{"id":"2506.22864","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-28T12:19:49Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"fe161f1687e3b8b30cee73b4cf42cbbc9a1f3120083077754a35770fb19bdf6b","abstract_canon_sha256":"90b670910992e7a713876e6bc0171184af82da4d210694f69b5ca38555c8219a"},"schema_version":"1.0"},"canonical_sha256":"beee0311a3114c3601ccdec2d6c680f0d8dd5b59b8c973d1d1d5c77acc9a219d","source":{"kind":"arxiv","id":"2506.22864","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22864","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22864v1","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22864","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"pith_short_12","alias_value":"X3XAGENDCFGD","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"X3XAGENDCFGDMAOM","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"X3XAGEND","created_at":"2026-07-05T11:28:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:X3XAGENDCFGDMAOM33BNNRUA6D","target":"record","payload":{"canonical_record":{"source":{"id":"2506.22864","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-28T12:19:49Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"fe161f1687e3b8b30cee73b4cf42cbbc9a1f3120083077754a35770fb19bdf6b","abstract_canon_sha256":"90b670910992e7a713876e6bc0171184af82da4d210694f69b5ca38555c8219a"},"schema_version":"1.0"},"canonical_sha256":"beee0311a3114c3601ccdec2d6c680f0d8dd5b59b8c973d1d1d5c77acc9a219d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:46.858032Z","signature_b64":"ETO55TqzG22FAE2SvTGr7grSeF19s3+yWRstHknBUxqBdODsfv0TTfDnd3nFUnk6ENbA6nApzXh4IsFTWs8hAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"beee0311a3114c3601ccdec2d6c680f0d8dd5b59b8c973d1d1d5c77acc9a219d","last_reissued_at":"2026-07-05T11:28:46.857601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:46.857601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.22864","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":"2026-07-05T11:28:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4FVnWe88TIp8DYKg5kA2SKS+ceIlQ5iqWVRew/nG3VYJ1coQ24qkEwG0bxKdToHcR3haR1+w8bfmmCxCRbfbCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:59:44.187708Z"},"content_sha256":"a5186cabb25ae42a00b79e35cb4cc5df8ec18fb23563bc1fd2fcde6ca418e28d","schema_version":"1.0","event_id":"sha256:a5186cabb25ae42a00b79e35cb4cc5df8ec18fb23563bc1fd2fcde6ca418e28d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:X3XAGENDCFGDMAOM33BNNRUA6D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chu-Song Chen, Jih-Kang Hsieh, Li-Cheng Shen, Wei-Hua Li","submitted_at":"2025-06-28T12:19:49Z","abstract_excerpt":"Text-to-image retrieval (TIR) aims to find relevant images based on a textual query, but existing approaches are primarily based on whole-image captions and lack interpretability. Meanwhile, referring expression segmentation (RES) enables precise object localization based on natural language descriptions but is computationally expensive when applied across large image collections. To bridge this gap, we introduce Mask-aware TIR (MaTIR), a new task that unifies TIR and RES, requiring both efficient image search and accurate object segmentation. To address this task, we propose a two-stage frame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22864","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.22864/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T11:28:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5wz5KTF30tpdMI2klsar8FDpUPYJ+Ceg25ZSOAKUhvsqdsiGIzaMkUYZV0DM3+rKGzAn02h9koVITBo713AMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:59:44.188232Z"},"content_sha256":"d67a11f0c86cfc3d36861c0d94efd03586072271e75dd8d735177267b096cac2","schema_version":"1.0","event_id":"sha256:d67a11f0c86cfc3d36861c0d94efd03586072271e75dd8d735177267b096cac2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X3XAGENDCFGDMAOM33BNNRUA6D/bundle.json","state_url":"https://pith.science/pith/X3XAGENDCFGDMAOM33BNNRUA6D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X3XAGENDCFGDMAOM33BNNRUA6D/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":"2026-08-19T07:59:44Z","links":{"resolver":"https://pith.science/pith/X3XAGENDCFGDMAOM33BNNRUA6D","bundle":"https://pith.science/pith/X3XAGENDCFGDMAOM33BNNRUA6D/bundle.json","state":"https://pith.science/pith/X3XAGENDCFGDMAOM33BNNRUA6D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X3XAGENDCFGDMAOM33BNNRUA6D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X3XAGENDCFGDMAOM33BNNRUA6D","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":"90b670910992e7a713876e6bc0171184af82da4d210694f69b5ca38555c8219a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-28T12:19:49Z","title_canon_sha256":"fe161f1687e3b8b30cee73b4cf42cbbc9a1f3120083077754a35770fb19bdf6b"},"schema_version":"1.0","source":{"id":"2506.22864","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22864","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22864v1","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22864","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"pith_short_12","alias_value":"X3XAGENDCFGD","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"X3XAGENDCFGDMAOM","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"X3XAGEND","created_at":"2026-07-05T11:28:46Z"}],"graph_snapshots":[{"event_id":"sha256:d67a11f0c86cfc3d36861c0d94efd03586072271e75dd8d735177267b096cac2","target":"graph","created_at":"2026-07-05T11:28:46Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.22864/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-image retrieval (TIR) aims to find relevant images based on a textual query, but existing approaches are primarily based on whole-image captions and lack interpretability. Meanwhile, referring expression segmentation (RES) enables precise object localization based on natural language descriptions but is computationally expensive when applied across large image collections. To bridge this gap, we introduce Mask-aware TIR (MaTIR), a new task that unifies TIR and RES, requiring both efficient image search and accurate object segmentation. To address this task, we propose a two-stage frame","authors_text":"Chu-Song Chen, Jih-Kang Hsieh, Li-Cheng Shen, Wei-Hua Li","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-28T12:19:49Z","title":"Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22864","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:a5186cabb25ae42a00b79e35cb4cc5df8ec18fb23563bc1fd2fcde6ca418e28d","target":"record","created_at":"2026-07-05T11:28:46Z","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":"90b670910992e7a713876e6bc0171184af82da4d210694f69b5ca38555c8219a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-28T12:19:49Z","title_canon_sha256":"fe161f1687e3b8b30cee73b4cf42cbbc9a1f3120083077754a35770fb19bdf6b"},"schema_version":"1.0","source":{"id":"2506.22864","kind":"arxiv","version":1}},"canonical_sha256":"beee0311a3114c3601ccdec2d6c680f0d8dd5b59b8c973d1d1d5c77acc9a219d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"beee0311a3114c3601ccdec2d6c680f0d8dd5b59b8c973d1d1d5c77acc9a219d","first_computed_at":"2026-07-05T11:28:46.857601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:46.857601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ETO55TqzG22FAE2SvTGr7grSeF19s3+yWRstHknBUxqBdODsfv0TTfDnd3nFUnk6ENbA6nApzXh4IsFTWs8hAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:46.858032Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.22864","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5186cabb25ae42a00b79e35cb4cc5df8ec18fb23563bc1fd2fcde6ca418e28d","sha256:d67a11f0c86cfc3d36861c0d94efd03586072271e75dd8d735177267b096cac2"],"state_sha256":"d5f51e2d43942346e222f653169ce67f3fdb846a8e2348cd065064a0bbe3bb82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aKu5Fo/N0ji5zefhIwAKVyIjCrsFpy0eTMLNOuj6DqXAt6MVCpUsqZDBde4q2+s4UJZvv4dO/dDwF1vNAcA1BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T07:59:44.192821Z","bundle_sha256":"3405e781fa7203158583cc81425e84f315926af7924a3a318c1ea5233181d6f3"}}