{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IPOPPPB4CIU7YF6PCO4LJXZM6W","short_pith_number":"pith:IPOPPPB4","schema_version":"1.0","canonical_sha256":"43dcf7bc3c1229fc17cf13b8b4df2cf596c15f91d8080d83f618a8dbdf3d705b","source":{"kind":"arxiv","id":"2602.07544","version":2},"attestation_state":"computed","paper":{"title":"MUFASA: A Multi-Layer Framework for Slot Attention","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Krishnakant Singh, Leonie Sch\\\"u{\\ss}ler, Sebastian Bock, Simone Schaub-Meyer, Stefan Roth","submitted_at":"2026-02-07T13:44:56Z","abstract_excerpt":"Unsupervised object-centric learning (OCL) decomposes visual scenes into distinct entities. Slot attention is a popular approach that represents individual objects as latent vectors, called slots. Current methods obtain these slot representations solely from the last layer of a pre-trained vision transformer (ViT), ignoring valuable, semantically rich information encoded across the other layers. To better utilize this latent semantic information, we introduce MUFASA, a lightweight plug-and-play framework for slot-attention-based approaches to unsupervised object segmentation. Our model compute"},"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":"2602.07544","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-07T13:44:56Z","cross_cats_sorted":[],"title_canon_sha256":"29e1dd567257226793dad345ddc2d60800df295f37cedf97a4a8e17ea8e01aa1","abstract_canon_sha256":"bf5861403f851b9dd9609eb036cf13be930eb9a0c89e570b4d08c279938619cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:20.691438Z","signature_b64":"w2YPukOnVlxPOSvCLbIXXhi7zrEDsMsF3ivwx7NG4wQG09/QTm5JdpS3XKGjVsMN8xj/2TapOJmkzgaDaduyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43dcf7bc3c1229fc17cf13b8b4df2cf596c15f91d8080d83f618a8dbdf3d705b","last_reissued_at":"2026-06-19T16:11:20.691029Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:20.691029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MUFASA: A Multi-Layer Framework for Slot Attention","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Krishnakant Singh, Leonie Sch\\\"u{\\ss}ler, Sebastian Bock, Simone Schaub-Meyer, Stefan Roth","submitted_at":"2026-02-07T13:44:56Z","abstract_excerpt":"Unsupervised object-centric learning (OCL) decomposes visual scenes into distinct entities. Slot attention is a popular approach that represents individual objects as latent vectors, called slots. Current methods obtain these slot representations solely from the last layer of a pre-trained vision transformer (ViT), ignoring valuable, semantically rich information encoded across the other layers. To better utilize this latent semantic information, we introduce MUFASA, a lightweight plug-and-play framework for slot-attention-based approaches to unsupervised object segmentation. Our model compute"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.07544","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/2602.07544/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":"2602.07544","created_at":"2026-06-19T16:11:20.691080+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.07544v2","created_at":"2026-06-19T16:11:20.691080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07544","created_at":"2026-06-19T16:11:20.691080+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPOPPPB4CIU7","created_at":"2026-06-19T16:11:20.691080+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPOPPPB4CIU7YF6P","created_at":"2026-06-19T16:11:20.691080+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPOPPPB4","created_at":"2026-06-19T16:11:20.691080+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/IPOPPPB4CIU7YF6PCO4LJXZM6W","json":"https://pith.science/pith/IPOPPPB4CIU7YF6PCO4LJXZM6W.json","graph_json":"https://pith.science/api/pith-number/IPOPPPB4CIU7YF6PCO4LJXZM6W/graph.json","events_json":"https://pith.science/api/pith-number/IPOPPPB4CIU7YF6PCO4LJXZM6W/events.json","paper":"https://pith.science/paper/IPOPPPB4"},"agent_actions":{"view_html":"https://pith.science/pith/IPOPPPB4CIU7YF6PCO4LJXZM6W","download_json":"https://pith.science/pith/IPOPPPB4CIU7YF6PCO4LJXZM6W.json","view_paper":"https://pith.science/paper/IPOPPPB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.07544&json=true","fetch_graph":"https://pith.science/api/pith-number/IPOPPPB4CIU7YF6PCO4LJXZM6W/graph.json","fetch_events":"https://pith.science/api/pith-number/IPOPPPB4CIU7YF6PCO4LJXZM6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPOPPPB4CIU7YF6PCO4LJXZM6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPOPPPB4CIU7YF6PCO4LJXZM6W/action/storage_attestation","attest_author":"https://pith.science/pith/IPOPPPB4CIU7YF6PCO4LJXZM6W/action/author_attestation","sign_citation":"https://pith.science/pith/IPOPPPB4CIU7YF6PCO4LJXZM6W/action/citation_signature","submit_replication":"https://pith.science/pith/IPOPPPB4CIU7YF6PCO4LJXZM6W/action/replication_record"}},"created_at":"2026-06-19T16:11:20.691080+00:00","updated_at":"2026-06-19T16:11:20.691080+00:00"}