{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CT3RJZQEAKYDSTTTNEJYQQJTKA","short_pith_number":"pith:CT3RJZQE","canonical_record":{"source":{"id":"2310.18049","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-27T10:52:50Z","cross_cats_sorted":[],"title_canon_sha256":"56a36ff2eb0b3ce8fc30d58e627219535b3d3893bf6f99cf9f37aeb4e2824dfd","abstract_canon_sha256":"c348c871e4f2dff004ecf34717795a5bbc45d20591410b54be141c42f7cdadbe"},"schema_version":"1.0"},"canonical_sha256":"14f714e60402b0394e7369138841335020cd58fdab09133b88fd0a90034e064d","source":{"kind":"arxiv","id":"2310.18049","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.18049","created_at":"2026-07-05T07:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2310.18049v1","created_at":"2026-07-05T07:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18049","created_at":"2026-07-05T07:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"CT3RJZQEAKYD","created_at":"2026-07-05T07:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"CT3RJZQEAKYDSTTT","created_at":"2026-07-05T07:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"CT3RJZQE","created_at":"2026-07-05T07:05:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CT3RJZQEAKYDSTTTNEJYQQJTKA","target":"record","payload":{"canonical_record":{"source":{"id":"2310.18049","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-27T10:52:50Z","cross_cats_sorted":[],"title_canon_sha256":"56a36ff2eb0b3ce8fc30d58e627219535b3d3893bf6f99cf9f37aeb4e2824dfd","abstract_canon_sha256":"c348c871e4f2dff004ecf34717795a5bbc45d20591410b54be141c42f7cdadbe"},"schema_version":"1.0"},"canonical_sha256":"14f714e60402b0394e7369138841335020cd58fdab09133b88fd0a90034e064d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:56.442697Z","signature_b64":"UdYeyldENfcKlC8kH1WLuP+eyhyGUJ+0W69uwSjNkLJXQasqpj5YwWatJ6VqgKXT5/8mne6FBjmTiU+DJJDFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14f714e60402b0394e7369138841335020cd58fdab09133b88fd0a90034e064d","last_reissued_at":"2026-07-05T07:05:56.442104Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:56.442104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.18049","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":"2026-07-05T07:05:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/ZEZYlrj380C8RdAle3MowuxxUx4ahUSQoF7ZJUl1CA2yGhnUeDAeaOC6wgdTaWCTaLeoKyBvrbHGIoQA5fxAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T01:18:30.358366Z"},"content_sha256":"e1bf0c31a2dec6fac30401c7bbfafef3d6cdd639f74327da89c82ca8a4e9aa6c","schema_version":"1.0","event_id":"sha256:e1bf0c31a2dec6fac30401c7bbfafef3d6cdd639f74327da89c82ca8a4e9aa6c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CT3RJZQEAKYDSTTTNEJYQQJTKA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text Augmented Spatial-aware Zero-shot Referring Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Linchao Zhu, Yi Yang, Yucheng Suo","submitted_at":"2023-10-27T10:52:50Z","abstract_excerpt":"In this paper, we study a challenging task of zero-shot referring image segmentation. This task aims to identify the instance mask that is most related to a referring expression without training on pixel-level annotations. Previous research takes advantage of pre-trained cross-modal models, e.g., CLIP, to align instance-level masks with referring expressions. %Yet, CLIP only considers image-text pair level alignment, which neglects fine-grained image region and complex sentence matching. Yet, CLIP only considers the global-level alignment of image-text pairs, neglecting fine-grained matching b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18049","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/2310.18049/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":"2026-07-05T07:05:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"03Ei2cSk3OOvdqfnE84upuvCX5ZubQfmtYOJn+1KOimh0FJgCv9BIeTbCbcM2T3N5KSzE2yIKTu+WFdfyp0ODg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T01:18:30.358861Z"},"content_sha256":"9fff41c9da75cb3398550846ebe54369118ebbe4833d8e4bdd1d27f9d528ddad","schema_version":"1.0","event_id":"sha256:9fff41c9da75cb3398550846ebe54369118ebbe4833d8e4bdd1d27f9d528ddad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CT3RJZQEAKYDSTTTNEJYQQJTKA/bundle.json","state_url":"https://pith.science/pith/CT3RJZQEAKYDSTTTNEJYQQJTKA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CT3RJZQEAKYDSTTTNEJYQQJTKA/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":"2026-08-21T01:18:30Z","links":{"resolver":"https://pith.science/pith/CT3RJZQEAKYDSTTTNEJYQQJTKA","bundle":"https://pith.science/pith/CT3RJZQEAKYDSTTTNEJYQQJTKA/bundle.json","state":"https://pith.science/pith/CT3RJZQEAKYDSTTTNEJYQQJTKA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CT3RJZQEAKYDSTTTNEJYQQJTKA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CT3RJZQEAKYDSTTTNEJYQQJTKA","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":"c348c871e4f2dff004ecf34717795a5bbc45d20591410b54be141c42f7cdadbe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-27T10:52:50Z","title_canon_sha256":"56a36ff2eb0b3ce8fc30d58e627219535b3d3893bf6f99cf9f37aeb4e2824dfd"},"schema_version":"1.0","source":{"id":"2310.18049","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.18049","created_at":"2026-07-05T07:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2310.18049v1","created_at":"2026-07-05T07:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18049","created_at":"2026-07-05T07:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"CT3RJZQEAKYD","created_at":"2026-07-05T07:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"CT3RJZQEAKYDSTTT","created_at":"2026-07-05T07:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"CT3RJZQE","created_at":"2026-07-05T07:05:56Z"}],"graph_snapshots":[{"event_id":"sha256:9fff41c9da75cb3398550846ebe54369118ebbe4833d8e4bdd1d27f9d528ddad","target":"graph","created_at":"2026-07-05T07:05:56Z","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/2310.18049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we study a challenging task of zero-shot referring image segmentation. This task aims to identify the instance mask that is most related to a referring expression without training on pixel-level annotations. Previous research takes advantage of pre-trained cross-modal models, e.g., CLIP, to align instance-level masks with referring expressions. %Yet, CLIP only considers image-text pair level alignment, which neglects fine-grained image region and complex sentence matching. Yet, CLIP only considers the global-level alignment of image-text pairs, neglecting fine-grained matching b","authors_text":"Linchao Zhu, Yi Yang, Yucheng Suo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-27T10:52:50Z","title":"Text Augmented Spatial-aware Zero-shot Referring Image Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18049","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:e1bf0c31a2dec6fac30401c7bbfafef3d6cdd639f74327da89c82ca8a4e9aa6c","target":"record","created_at":"2026-07-05T07:05:56Z","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":"c348c871e4f2dff004ecf34717795a5bbc45d20591410b54be141c42f7cdadbe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-27T10:52:50Z","title_canon_sha256":"56a36ff2eb0b3ce8fc30d58e627219535b3d3893bf6f99cf9f37aeb4e2824dfd"},"schema_version":"1.0","source":{"id":"2310.18049","kind":"arxiv","version":1}},"canonical_sha256":"14f714e60402b0394e7369138841335020cd58fdab09133b88fd0a90034e064d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14f714e60402b0394e7369138841335020cd58fdab09133b88fd0a90034e064d","first_computed_at":"2026-07-05T07:05:56.442104Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:56.442104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UdYeyldENfcKlC8kH1WLuP+eyhyGUJ+0W69uwSjNkLJXQasqpj5YwWatJ6VqgKXT5/8mne6FBjmTiU+DJJDFBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:56.442697Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.18049","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1bf0c31a2dec6fac30401c7bbfafef3d6cdd639f74327da89c82ca8a4e9aa6c","sha256:9fff41c9da75cb3398550846ebe54369118ebbe4833d8e4bdd1d27f9d528ddad"],"state_sha256":"b34f941c646f171b27f848a3a037c82f55c9de7673813aad5a10c4d9b2e19173"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xwDgCKBKDl6XrsCnrGyhb3TdoEG2I4vbnQeOArXIM7TPg4DDWhE5Y3DgO5hXwLe5kZ3CZoflKlw9mtJLaxUgAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T01:18:30.362551Z","bundle_sha256":"11893aacdff20a9e498f43ccf2ec11edad15519c36f8ac240fa1402244d1acc9"}}