{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:G2U5NFXUCULWXJ4D3IHLPWJI27","short_pith_number":"pith:G2U5NFXU","canonical_record":{"source":{"id":"2306.08498","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-14T13:27:28Z","cross_cats_sorted":[],"title_canon_sha256":"6dd8ddd454f85e4e176aad2cdde33506ff4989044d7de2f43685c5b5b4f717f5","abstract_canon_sha256":"ab284a1aa27c0ce94e4d7611de8b352a4be0de401b9f8f79edc0c07a4c871a58"},"schema_version":"1.0"},"canonical_sha256":"36a9d696f415176ba783da0eb7d928d7f620c118c0950293e9fb06918fb7277a","source":{"kind":"arxiv","id":"2306.08498","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08498","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08498v2","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08498","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"pith_short_12","alias_value":"G2U5NFXUCULW","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"pith_short_16","alias_value":"G2U5NFXUCULWXJ4D","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"pith_short_8","alias_value":"G2U5NFXU","created_at":"2026-07-05T08:04:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:G2U5NFXUCULWXJ4D3IHLPWJI27","target":"record","payload":{"canonical_record":{"source":{"id":"2306.08498","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-14T13:27:28Z","cross_cats_sorted":[],"title_canon_sha256":"6dd8ddd454f85e4e176aad2cdde33506ff4989044d7de2f43685c5b5b4f717f5","abstract_canon_sha256":"ab284a1aa27c0ce94e4d7611de8b352a4be0de401b9f8f79edc0c07a4c871a58"},"schema_version":"1.0"},"canonical_sha256":"36a9d696f415176ba783da0eb7d928d7f620c118c0950293e9fb06918fb7277a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:59.149806Z","signature_b64":"RO49YePPJ/yckVVyvnfiayM8eyT1+vLin7znOH6eeJk9UOaAs7eJw+J/fWZsrZq6Xh2+bqUhmn6LHRLQ2oMFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36a9d696f415176ba783da0eb7d928d7f620c118c0950293e9fb06918fb7277a","last_reissued_at":"2026-07-05T08:04:59.149393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:59.149393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.08498","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":"2026-07-05T08:04:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JD977P5+oMykhLX6KPMivXaPddqsYFonpKZkEacmqKzrtU/O1SnoY2VpUapEzPk5YjdffFYXv54njafu/HmmDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T01:12:59.939063Z"},"content_sha256":"3e283fc2f6cd34c775aa1b65905204673fef93274dc6c80148db63f55b2e2c25","schema_version":"1.0","event_id":"sha256:3e283fc2f6cd34c775aa1b65905204673fef93274dc6c80148db63f55b2e2c25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:G2U5NFXUCULWXJ4D3IHLPWJI27","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extending CLIP's Image-Text Alignment to Referring Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongwon Kim, Jaesik Park, Minguk Kang, Seoyeon Kim, Suha Kwak","submitted_at":"2023-06-14T13:27:28Z","abstract_excerpt":"Referring Image Segmentation (RIS) is a cross-modal task that aims to segment an instance described by a natural language expression. Recent methods leverage large-scale pretrained unimodal models as backbones along with fusion techniques for joint reasoning across modalities. However, the inherent cross-modal nature of RIS raises questions about the effectiveness of unimodal backbones. We propose RISCLIP, a novel framework that effectively leverages the cross-modal nature of CLIP for RIS. Observing CLIP's inherent alignment between image and text features, we capitalize on this starting point"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08498","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.08498/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":"2026-07-05T08:04:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OUzGjyjcHhChZQLDPi6+PAcRfqyhwFzkva8RuyFhTJ9XIchbhbMd7Ft8vdsLA+P38VHAtn2/DZYGQTsUK34fCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T01:12:59.939442Z"},"content_sha256":"340c638b25b2016cb718a9b430bc37eb9968f80eebce701913cd3e6b8400f1ed","schema_version":"1.0","event_id":"sha256:340c638b25b2016cb718a9b430bc37eb9968f80eebce701913cd3e6b8400f1ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G2U5NFXUCULWXJ4D3IHLPWJI27/bundle.json","state_url":"https://pith.science/pith/G2U5NFXUCULWXJ4D3IHLPWJI27/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G2U5NFXUCULWXJ4D3IHLPWJI27/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":"2026-08-19T01:12:59Z","links":{"resolver":"https://pith.science/pith/G2U5NFXUCULWXJ4D3IHLPWJI27","bundle":"https://pith.science/pith/G2U5NFXUCULWXJ4D3IHLPWJI27/bundle.json","state":"https://pith.science/pith/G2U5NFXUCULWXJ4D3IHLPWJI27/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G2U5NFXUCULWXJ4D3IHLPWJI27/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:G2U5NFXUCULWXJ4D3IHLPWJI27","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":"ab284a1aa27c0ce94e4d7611de8b352a4be0de401b9f8f79edc0c07a4c871a58","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-14T13:27:28Z","title_canon_sha256":"6dd8ddd454f85e4e176aad2cdde33506ff4989044d7de2f43685c5b5b4f717f5"},"schema_version":"1.0","source":{"id":"2306.08498","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08498","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08498v2","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08498","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"pith_short_12","alias_value":"G2U5NFXUCULW","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"pith_short_16","alias_value":"G2U5NFXUCULWXJ4D","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"pith_short_8","alias_value":"G2U5NFXU","created_at":"2026-07-05T08:04:59Z"}],"graph_snapshots":[{"event_id":"sha256:340c638b25b2016cb718a9b430bc37eb9968f80eebce701913cd3e6b8400f1ed","target":"graph","created_at":"2026-07-05T08:04:59Z","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/2306.08498/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring Image Segmentation (RIS) is a cross-modal task that aims to segment an instance described by a natural language expression. Recent methods leverage large-scale pretrained unimodal models as backbones along with fusion techniques for joint reasoning across modalities. However, the inherent cross-modal nature of RIS raises questions about the effectiveness of unimodal backbones. We propose RISCLIP, a novel framework that effectively leverages the cross-modal nature of CLIP for RIS. Observing CLIP's inherent alignment between image and text features, we capitalize on this starting point","authors_text":"Dongwon Kim, Jaesik Park, Minguk Kang, Seoyeon Kim, Suha Kwak","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-14T13:27:28Z","title":"Extending CLIP's Image-Text Alignment to Referring Image Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08498","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":"sha256:3e283fc2f6cd34c775aa1b65905204673fef93274dc6c80148db63f55b2e2c25","target":"record","created_at":"2026-07-05T08:04:59Z","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":"ab284a1aa27c0ce94e4d7611de8b352a4be0de401b9f8f79edc0c07a4c871a58","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-14T13:27:28Z","title_canon_sha256":"6dd8ddd454f85e4e176aad2cdde33506ff4989044d7de2f43685c5b5b4f717f5"},"schema_version":"1.0","source":{"id":"2306.08498","kind":"arxiv","version":2}},"canonical_sha256":"36a9d696f415176ba783da0eb7d928d7f620c118c0950293e9fb06918fb7277a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36a9d696f415176ba783da0eb7d928d7f620c118c0950293e9fb06918fb7277a","first_computed_at":"2026-07-05T08:04:59.149393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:04:59.149393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RO49YePPJ/yckVVyvnfiayM8eyT1+vLin7znOH6eeJk9UOaAs7eJw+J/fWZsrZq6Xh2+bqUhmn6LHRLQ2oMFBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:04:59.149806Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.08498","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e283fc2f6cd34c775aa1b65905204673fef93274dc6c80148db63f55b2e2c25","sha256:340c638b25b2016cb718a9b430bc37eb9968f80eebce701913cd3e6b8400f1ed"],"state_sha256":"7d9ab71fdc4468125dda0285fdb3b27815f4072c7cc26de75cd4b832ab45f623"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"72Pq69nTMaRa4NvZzBXfsqrRgq93Jup26JMOpYDjx7FwN6PTzwqI6NYfdt0ZsLPEN20bF8+SfqtCgqarpbjzBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T01:12:59.941907Z","bundle_sha256":"4192d4a655655040757680a0ed71d594f2157571d5a453ab18690410efce6e91"}}