{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FN7VHESC24ORCXUXQW5HGHQ5ZC","short_pith_number":"pith:FN7VHESC","schema_version":"1.0","canonical_sha256":"2b7f539242d71d115e9785ba731e1dc89787ce7fde47213f22c8a439f2b7e741","source":{"kind":"arxiv","id":"2508.06995","version":2},"attestation_state":"computed","paper":{"title":"S2-UniSeg: Fast Universal Agglomerative Pooling for Scalable Segment Anything without Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changkai Ji, Chenglong Ma, Hongqiu Wang, Huihui Xu, Jiashi Lin, Jin Ye, Junjun He, Lei Zhu, Lihao Liu, Ming Hu, Tianbin Li, Ying Chen, Ziyan Huang","submitted_at":"2025-08-09T14:12:39Z","abstract_excerpt":"Recent self-supervised image segmentation models have achieved promising performance on semantic segmentation and class-agnostic instance segmentation. However, their pretraining schedule is multi-stage, requiring a time-consuming pseudo-masks generation process between each training epoch. This time-consuming offline process not only makes it difficult to scale with training dataset size, but also leads to sub-optimal solutions due to its discontinuous optimization routine. To solve these, we first present a novel pseudo-mask algorithm, Fast Universal Agglomerative Pooling (UniAP). Each layer"},"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":"2508.06995","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-09T14:12:39Z","cross_cats_sorted":[],"title_canon_sha256":"9ea38651dbcf53a347ac5910f2b119af809bef2ad7f2c40fc43c6a6e1f4b8772","abstract_canon_sha256":"19cc268812e1f1929fbb176a36730c70b81271d5ecabe8e75d152a508ec72cec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:28.470991Z","signature_b64":"cjkDpgR7G42DosetOn4jBZMM56KRSdVUtp0kVMp0fykpa+VLYdNC2C0g0rktOamWyPkT6d6sIkJYVwDHCaoJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b7f539242d71d115e9785ba731e1dc89787ce7fde47213f22c8a439f2b7e741","last_reissued_at":"2026-07-05T11:53:28.470500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:28.470500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"S2-UniSeg: Fast Universal Agglomerative Pooling for Scalable Segment Anything without Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changkai Ji, Chenglong Ma, Hongqiu Wang, Huihui Xu, Jiashi Lin, Jin Ye, Junjun He, Lei Zhu, Lihao Liu, Ming Hu, Tianbin Li, Ying Chen, Ziyan Huang","submitted_at":"2025-08-09T14:12:39Z","abstract_excerpt":"Recent self-supervised image segmentation models have achieved promising performance on semantic segmentation and class-agnostic instance segmentation. However, their pretraining schedule is multi-stage, requiring a time-consuming pseudo-masks generation process between each training epoch. This time-consuming offline process not only makes it difficult to scale with training dataset size, but also leads to sub-optimal solutions due to its discontinuous optimization routine. To solve these, we first present a novel pseudo-mask algorithm, Fast Universal Agglomerative Pooling (UniAP). Each layer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06995","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/2508.06995/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":"2508.06995","created_at":"2026-07-05T11:53:28.470556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.06995v2","created_at":"2026-07-05T11:53:28.470556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06995","created_at":"2026-07-05T11:53:28.470556+00:00"},{"alias_kind":"pith_short_12","alias_value":"FN7VHESC24OR","created_at":"2026-07-05T11:53:28.470556+00:00"},{"alias_kind":"pith_short_16","alias_value":"FN7VHESC24ORCXUX","created_at":"2026-07-05T11:53:28.470556+00:00"},{"alias_kind":"pith_short_8","alias_value":"FN7VHESC","created_at":"2026-07-05T11:53:28.470556+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06997","citing_title":"Conformal Set-based Human-AI Complementarity with Multiple Experts","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FN7VHESC24ORCXUXQW5HGHQ5ZC","json":"https://pith.science/pith/FN7VHESC24ORCXUXQW5HGHQ5ZC.json","graph_json":"https://pith.science/api/pith-number/FN7VHESC24ORCXUXQW5HGHQ5ZC/graph.json","events_json":"https://pith.science/api/pith-number/FN7VHESC24ORCXUXQW5HGHQ5ZC/events.json","paper":"https://pith.science/paper/FN7VHESC"},"agent_actions":{"view_html":"https://pith.science/pith/FN7VHESC24ORCXUXQW5HGHQ5ZC","download_json":"https://pith.science/pith/FN7VHESC24ORCXUXQW5HGHQ5ZC.json","view_paper":"https://pith.science/paper/FN7VHESC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.06995&json=true","fetch_graph":"https://pith.science/api/pith-number/FN7VHESC24ORCXUXQW5HGHQ5ZC/graph.json","fetch_events":"https://pith.science/api/pith-number/FN7VHESC24ORCXUXQW5HGHQ5ZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FN7VHESC24ORCXUXQW5HGHQ5ZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FN7VHESC24ORCXUXQW5HGHQ5ZC/action/storage_attestation","attest_author":"https://pith.science/pith/FN7VHESC24ORCXUXQW5HGHQ5ZC/action/author_attestation","sign_citation":"https://pith.science/pith/FN7VHESC24ORCXUXQW5HGHQ5ZC/action/citation_signature","submit_replication":"https://pith.science/pith/FN7VHESC24ORCXUXQW5HGHQ5ZC/action/replication_record"}},"created_at":"2026-07-05T11:53:28.470556+00:00","updated_at":"2026-07-05T11:53:28.470556+00:00"}