{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4K4NXYRSWTZU6IMF2KNNUATCXT","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":"36db5879e64d059622812333adcc7f0928579edb076caa798f87d9386be224cf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-15T12:11:20Z","title_canon_sha256":"b857cd868b7c18125574b41183908c6ea811b9b12441fee9446bfc08cd00c0a5"},"schema_version":"1.0","source":{"id":"2408.08108","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08108","created_at":"2026-07-05T08:55:44Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08108v1","created_at":"2026-07-05T08:55:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08108","created_at":"2026-07-05T08:55:44Z"},{"alias_kind":"pith_short_12","alias_value":"4K4NXYRSWTZU","created_at":"2026-07-05T08:55:44Z"},{"alias_kind":"pith_short_16","alias_value":"4K4NXYRSWTZU6IMF","created_at":"2026-07-05T08:55:44Z"},{"alias_kind":"pith_short_8","alias_value":"4K4NXYRS","created_at":"2026-07-05T08:55:44Z"}],"graph_snapshots":[{"event_id":"sha256:16f1ba35328339a71716862ba106598bb7f6012374261f2e8c02ed0494b935d7","target":"graph","created_at":"2026-07-05T08:55:44Z","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/2408.08108/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Object parts serve as crucial intermediate representations in various downstream tasks, but part-level representation learning still has not received as much attention as other vision tasks. Previous research has established that Vision Transformer can learn instance-level attention without labels, extracting high-quality instance-level representations for boosting downstream tasks. In this paper, we achieve unsupervised part-specific attention learning using a novel paradigm and further employ the part representations to improve part discovery performance. Specifically, paired images are gene","authors_text":"Dong Xu, Haimin Zhang, Jiahao Xia, Jianguo Zhang, Min Xu, Wenjian Huang, Ziyu Sheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-15T12:11:20Z","title":"Unsupervised Part Discovery via Dual Representation Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08108","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":"sha256:0ba679fb28129a6653a05b556f29c573c69f04ccf4c4519b1deff0f5a6143bfa","target":"record","created_at":"2026-07-05T08:55:44Z","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":"36db5879e64d059622812333adcc7f0928579edb076caa798f87d9386be224cf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-15T12:11:20Z","title_canon_sha256":"b857cd868b7c18125574b41183908c6ea811b9b12441fee9446bfc08cd00c0a5"},"schema_version":"1.0","source":{"id":"2408.08108","kind":"arxiv","version":1}},"canonical_sha256":"e2b8dbe232b4f34f2185d29ada0262bce794eb5120786e37dd3fa11018c1fc6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2b8dbe232b4f34f2185d29ada0262bce794eb5120786e37dd3fa11018c1fc6c","first_computed_at":"2026-07-05T08:55:44.654049Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:44.654049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cZ94Im0xIMcw+38Tj9S9O5kKMNTaZBIHaBRnvrHyifKBmwQoleHdUwUFTWqk6D5lI4vjhb5NdYtMfHFZzT8DDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:44.654498Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.08108","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ba679fb28129a6653a05b556f29c573c69f04ccf4c4519b1deff0f5a6143bfa","sha256:16f1ba35328339a71716862ba106598bb7f6012374261f2e8c02ed0494b935d7"],"state_sha256":"47e9ecbdf35fbb0286eb8b6b65fdd3566c6873b1d870265c41c63641d2b26e9f"}