{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TGO6ADEH4ZQNWC7K6CKBWUUZH6","short_pith_number":"pith:TGO6ADEH","schema_version":"1.0","canonical_sha256":"999de00c87e660db0beaf0941b52993fb15acddef950d1310db01abe8e5396f8","source":{"kind":"arxiv","id":"2505.02071","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Compact Clustering Attention (COCA) for Unsupervised Object-Centric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Can K\\\"u\\c{c}\\\"uks\\\"ozen, Y\\\"ucel Yemez","submitted_at":"2025-05-04T11:42:04Z","abstract_excerpt":"We propose the Compact Clustering Attention (COCA) layer, an effective building block that introduces a hierarchical strategy for object-centric representation learning, while solving the unsupervised object discovery task on single images. COCA is an attention-based clustering module capable of extracting object-centric representations from multi-object scenes, when cascaded into a bottom-up hierarchical network architecture, referred to as COCA-Net. At its core, COCA utilizes a novel clustering algorithm that leverages the physical concept of compactness, to highlight distinct object centroi"},"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":"2505.02071","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-04T11:42:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5bab5aeeaf305a58dd90ea3ce84671aa3da6bd813dab1a3c34f2be0d2f33c7b6","abstract_canon_sha256":"0a132a5646d59edfb84fa1c00af1ad1c0ad6ee5b7afa870a740b5a1c61d97b73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:31.363124Z","signature_b64":"f4MlCABJHR9luQj5UvjA3/ASxADqo8b2b7PdIq5l0bu96TjwICUXhCovHLdB+duytURvCBJVCik/gHFvsbS0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"999de00c87e660db0beaf0941b52993fb15acddef950d1310db01abe8e5396f8","last_reissued_at":"2026-07-05T10:58:31.362613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:31.362613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Compact Clustering Attention (COCA) for Unsupervised Object-Centric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Can K\\\"u\\c{c}\\\"uks\\\"ozen, Y\\\"ucel Yemez","submitted_at":"2025-05-04T11:42:04Z","abstract_excerpt":"We propose the Compact Clustering Attention (COCA) layer, an effective building block that introduces a hierarchical strategy for object-centric representation learning, while solving the unsupervised object discovery task on single images. COCA is an attention-based clustering module capable of extracting object-centric representations from multi-object scenes, when cascaded into a bottom-up hierarchical network architecture, referred to as COCA-Net. At its core, COCA utilizes a novel clustering algorithm that leverages the physical concept of compactness, to highlight distinct object centroi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02071","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/2505.02071/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":"2505.02071","created_at":"2026-07-05T10:58:31.362671+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02071v1","created_at":"2026-07-05T10:58:31.362671+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02071","created_at":"2026-07-05T10:58:31.362671+00:00"},{"alias_kind":"pith_short_12","alias_value":"TGO6ADEH4ZQN","created_at":"2026-07-05T10:58:31.362671+00:00"},{"alias_kind":"pith_short_16","alias_value":"TGO6ADEH4ZQNWC7K","created_at":"2026-07-05T10:58:31.362671+00:00"},{"alias_kind":"pith_short_8","alias_value":"TGO6ADEH","created_at":"2026-07-05T10:58:31.362671+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/TGO6ADEH4ZQNWC7K6CKBWUUZH6","json":"https://pith.science/pith/TGO6ADEH4ZQNWC7K6CKBWUUZH6.json","graph_json":"https://pith.science/api/pith-number/TGO6ADEH4ZQNWC7K6CKBWUUZH6/graph.json","events_json":"https://pith.science/api/pith-number/TGO6ADEH4ZQNWC7K6CKBWUUZH6/events.json","paper":"https://pith.science/paper/TGO6ADEH"},"agent_actions":{"view_html":"https://pith.science/pith/TGO6ADEH4ZQNWC7K6CKBWUUZH6","download_json":"https://pith.science/pith/TGO6ADEH4ZQNWC7K6CKBWUUZH6.json","view_paper":"https://pith.science/paper/TGO6ADEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02071&json=true","fetch_graph":"https://pith.science/api/pith-number/TGO6ADEH4ZQNWC7K6CKBWUUZH6/graph.json","fetch_events":"https://pith.science/api/pith-number/TGO6ADEH4ZQNWC7K6CKBWUUZH6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TGO6ADEH4ZQNWC7K6CKBWUUZH6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TGO6ADEH4ZQNWC7K6CKBWUUZH6/action/storage_attestation","attest_author":"https://pith.science/pith/TGO6ADEH4ZQNWC7K6CKBWUUZH6/action/author_attestation","sign_citation":"https://pith.science/pith/TGO6ADEH4ZQNWC7K6CKBWUUZH6/action/citation_signature","submit_replication":"https://pith.science/pith/TGO6ADEH4ZQNWC7K6CKBWUUZH6/action/replication_record"}},"created_at":"2026-07-05T10:58:31.362671+00:00","updated_at":"2026-07-05T10:58:31.362671+00:00"}