{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:G23RMF7OI3SBMGECHVM74V7UQX","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":"4b58bd15d27f24a423feff488ce8f2c7e73b52f1d755039f85d79eb1759dc892","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-09T02:23:49Z","title_canon_sha256":"db0e4f15fd5e058ae68a6868d4e3d0fec5841d8bd9ca79f4f27957bc97302185"},"schema_version":"1.0","source":{"id":"2608.08418","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08418","created_at":"2026-08-11T01:22:35Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08418v1","created_at":"2026-08-11T01:22:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08418","created_at":"2026-08-11T01:22:35Z"},{"alias_kind":"pith_short_12","alias_value":"G23RMF7OI3SB","created_at":"2026-08-11T01:22:35Z"},{"alias_kind":"pith_short_16","alias_value":"G23RMF7OI3SBMGEC","created_at":"2026-08-11T01:22:35Z"},{"alias_kind":"pith_short_8","alias_value":"G23RMF7O","created_at":"2026-08-11T01:22:35Z"}],"graph_snapshots":[{"event_id":"sha256:26e850b9a55c396a47b5ef99843e7fa42755ff7790c28ea7da94907bab0b742f","target":"graph","created_at":"2026-08-11T01:22:35Z","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/2608.08418/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Leveraging textual information for image clustering has emerged as a promising direction, largely owing to the powerful representations learned by Vision-Language Models (VLMs). Existing approaches typically retrieve a textual counterpart for each image and then refine multimodal representations by directly enforcing cross-modal agreement, e.g., maximizing image-text similarity inherited from pretrained VLMs. However, such a strategy aligns heterogeneous representations across modalities without explicitly modeling the intrinsic structure within each modality and thus might yield unreliable al","authors_text":"Chun-Guang Li, Wei He, Xianghan Meng, Zhiyuan Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-09T02:23:49Z","title":"Learning Deep Modality-Shared Self-Expressiveness for Image Clustering with Textual Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08418","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:accb8093c4784ccc66458142e36db88f7a80942d5c3ff47461ffa76e6af4e1ca","target":"record","created_at":"2026-08-11T01:22:35Z","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":"4b58bd15d27f24a423feff488ce8f2c7e73b52f1d755039f85d79eb1759dc892","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-09T02:23:49Z","title_canon_sha256":"db0e4f15fd5e058ae68a6868d4e3d0fec5841d8bd9ca79f4f27957bc97302185"},"schema_version":"1.0","source":{"id":"2608.08418","kind":"arxiv","version":1}},"canonical_sha256":"36b71617ee46e41618823d59fe57f485feea8b01c2cdbfb9433cb60356ca6488","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36b71617ee46e41618823d59fe57f485feea8b01c2cdbfb9433cb60356ca6488","first_computed_at":"2026-08-11T01:22:35.536972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:22:35.536972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AU5bJH0uHwO/NpxCzSSkQ2PbYq8BZXXUQiPQUgD4VERGIsRl2y+r1ViMZl+QP6/OwA6qk/56rEbuPCL7Lt8/Ag==","signature_status":"signed_v1","signed_at":"2026-08-11T01:22:35.539495Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08418","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:accb8093c4784ccc66458142e36db88f7a80942d5c3ff47461ffa76e6af4e1ca","sha256:26e850b9a55c396a47b5ef99843e7fa42755ff7790c28ea7da94907bab0b742f"],"state_sha256":"15ea8c20f8101a49bb6b9a75142e41b347014d82a477922888474f18e1f7897b"}