{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z4PMQVT3WEW5TEPKXISEG7MTWQ","short_pith_number":"pith:Z4PMQVT3","schema_version":"1.0","canonical_sha256":"cf1ec8567bb12dd991eaba24437d93b4332153aa9bd6eac3d5c8a8b1ef66f1d8","source":{"kind":"arxiv","id":"2607.07230","version":1},"attestation_state":"computed","paper":{"title":"`Attention-Guided Cross-Temporal Clustering for Self-Supervised Video Object Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Wee-Chung Liew, Mohammad Awrangjeb, Waqas Arshid, Yongsheng Gao","submitted_at":"2026-07-08T10:13:20Z","abstract_excerpt":"Video object segmentation (VOS) is a fundamental task in video understanding, requiring accurate delineation and consistent tracking of objects across frames. While supervised methods achieve strong performance, they rely on densely annotated datasets that are costly to obtain and have limited domain coverage. Self-supervised learning offers a promising alternative by removing the need for manual labels; however, existing approaches often struggle to jointly maintain spatial accuracy and temporal coherence, particularly in unconstrained multi-object scenarios. Many rely on optical flow, synthe"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.07230","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-08T10:13:20Z","cross_cats_sorted":[],"title_canon_sha256":"1299a0cc339024b4dc7970a19a576d24c71d5604291e55c31cabf1ded55a7325","abstract_canon_sha256":"10aece1a105eec96d900128d972e8edd83dde09627543c620839dc2b0b541dff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:20:18.340851Z","signature_b64":"PPqVTUQmGhMHSnbEnVmOa/71xzwVQp74rwRsxe+xy7A1g4mJlRVJFdrc0sM7/rX+uyA8eer+qqyhabKoEs9GAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf1ec8567bb12dd991eaba24437d93b4332153aa9bd6eac3d5c8a8b1ef66f1d8","last_reissued_at":"2026-07-09T01:20:18.340469Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:20:18.340469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"`Attention-Guided Cross-Temporal Clustering for Self-Supervised Video Object Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Wee-Chung Liew, Mohammad Awrangjeb, Waqas Arshid, Yongsheng Gao","submitted_at":"2026-07-08T10:13:20Z","abstract_excerpt":"Video object segmentation (VOS) is a fundamental task in video understanding, requiring accurate delineation and consistent tracking of objects across frames. While supervised methods achieve strong performance, they rely on densely annotated datasets that are costly to obtain and have limited domain coverage. Self-supervised learning offers a promising alternative by removing the need for manual labels; however, existing approaches often struggle to jointly maintain spatial accuracy and temporal coherence, particularly in unconstrained multi-object scenarios. Many rely on optical flow, synthe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07230","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/2607.07230/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.07230","created_at":"2026-07-09T01:20:18.340521+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.07230v1","created_at":"2026-07-09T01:20:18.340521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07230","created_at":"2026-07-09T01:20:18.340521+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4PMQVT3WEW5","created_at":"2026-07-09T01:20:18.340521+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4PMQVT3WEW5TEPK","created_at":"2026-07-09T01:20:18.340521+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4PMQVT3","created_at":"2026-07-09T01:20:18.340521+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z4PMQVT3WEW5TEPKXISEG7MTWQ","json":"https://pith.science/pith/Z4PMQVT3WEW5TEPKXISEG7MTWQ.json","graph_json":"https://pith.science/api/pith-number/Z4PMQVT3WEW5TEPKXISEG7MTWQ/graph.json","events_json":"https://pith.science/api/pith-number/Z4PMQVT3WEW5TEPKXISEG7MTWQ/events.json","paper":"https://pith.science/paper/Z4PMQVT3"},"agent_actions":{"view_html":"https://pith.science/pith/Z4PMQVT3WEW5TEPKXISEG7MTWQ","download_json":"https://pith.science/pith/Z4PMQVT3WEW5TEPKXISEG7MTWQ.json","view_paper":"https://pith.science/paper/Z4PMQVT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.07230&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4PMQVT3WEW5TEPKXISEG7MTWQ/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4PMQVT3WEW5TEPKXISEG7MTWQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4PMQVT3WEW5TEPKXISEG7MTWQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4PMQVT3WEW5TEPKXISEG7MTWQ/action/storage_attestation","attest_author":"https://pith.science/pith/Z4PMQVT3WEW5TEPKXISEG7MTWQ/action/author_attestation","sign_citation":"https://pith.science/pith/Z4PMQVT3WEW5TEPKXISEG7MTWQ/action/citation_signature","submit_replication":"https://pith.science/pith/Z4PMQVT3WEW5TEPKXISEG7MTWQ/action/replication_record"}},"created_at":"2026-07-09T01:20:18.340521+00:00","updated_at":"2026-07-09T01:20:18.340521+00:00"}