{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XZF5JM37AXCISRWA2R6Y55B6LB","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":"b6b12b3881dd4223a9fc48052d20907da7c1763caab065bc47306abf43b30f08","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T14:09:33Z","title_canon_sha256":"09164ef804a9849ed982a8cf3759371e12b02a39750ab6d3f917eab9251f591e"},"schema_version":"1.0","source":{"id":"2508.05417","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.05417","created_at":"2026-05-28T02:04:42Z"},{"alias_kind":"arxiv_version","alias_value":"2508.05417v5","created_at":"2026-05-28T02:04:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05417","created_at":"2026-05-28T02:04:42Z"},{"alias_kind":"pith_short_12","alias_value":"XZF5JM37AXCI","created_at":"2026-05-28T02:04:42Z"},{"alias_kind":"pith_short_16","alias_value":"XZF5JM37AXCISRWA","created_at":"2026-05-28T02:04:42Z"},{"alias_kind":"pith_short_8","alias_value":"XZF5JM37","created_at":"2026-05-28T02:04:42Z"}],"graph_snapshots":[{"event_id":"sha256:268ac4f4655ae6997e030c62e55797d34c01f6725102e874a7aad5c8ceff47cb","target":"graph","created_at":"2026-05-28T02:04:42Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We address these issues with our SmoothSA: (1) To smooth SA iterations on image or video's first frame, we preheat cold-start queries with rich input-feature information, by a tiny module self-distilled inside OCL; (2) To smooth SA recurrences across video's first and non-first frames, we differentiate the homogeneous aggregation transforms by using full and single iterations respectively."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that a self-distilled tiny module can reliably inject useful sample-specific cues into cold-start queries without introducing new biases or requiring extra supervision, and that switching between full and single iterations is sufficient to handle the information difference between first and non-first frames."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SmoothSA improves slot attention by preheating cold-start queries on first frames and applying full iterations there versus single iterations on subsequent video frames."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"SmoothSA improves object-centric learning by smoothing slot attention iterations and recurrences."}],"snapshot_sha256":"ea8afb5ba87e619f22c3f43262e79208116852dd298a3a96d0619d5be91d1f46"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.05417/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Slot Attention (SA) lies at the heart of mainstream Object-Centric Learning (OCL). Image features can be aggregated into object-level representations by SA \\textit{iteratively} refining cold-start query slots. For video, such aggregation proceeds by SA \\textit{recurrently} shared across frames, with queries cold-started on the first frame while transitioned from the previous frame's slots thereafter. However, cold-start queries lack sample-specific cues thus hindering precise aggregation on image or video's first frame; Non-first frames' queries are already sample-specific thus requiring aggre","authors_text":"Joni Pajarinen, Juho Kannala, Rongzhen Zhao, Wenyan Yang","cross_cats":[],"headline":"SmoothSA improves object-centric learning by smoothing slot attention iterations and recurrences.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T14:09:33Z","title":"Smoothing Slot Attention Iterations and Recurrences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05417","kind":"arxiv","version":5},"verdict":{"created_at":"2026-05-18T23:55:55.082406Z","id":"cc500e45-6c67-46a0-b4c7-4e15c0e6fcbf","model_set":{"reader":"grok-4.3"},"one_line_summary":"SmoothSA improves slot attention by preheating cold-start queries on first frames and applying full iterations there versus single iterations on subsequent video frames.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"SmoothSA improves object-centric learning by smoothing slot attention iterations and recurrences.","strongest_claim":"We address these issues with our SmoothSA: (1) To smooth SA iterations on image or video's first frame, we preheat cold-start queries with rich input-feature information, by a tiny module self-distilled inside OCL; (2) To smooth SA recurrences across video's first and non-first frames, we differentiate the homogeneous aggregation transforms by using full and single iterations respectively.","weakest_assumption":"The assumption that a self-distilled tiny module can reliably inject useful sample-specific cues into cold-start queries without introducing new biases or requiring extra supervision, and that switching between full and single iterations is sufficient to handle the information difference between first and non-first frames."}},"verdict_id":"cc500e45-6c67-46a0-b4c7-4e15c0e6fcbf"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:65a7209bfab73733e3f23c8af869b8527d8aa226afb8e57dcbee02f21e713282","target":"record","created_at":"2026-05-28T02:04:42Z","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":"b6b12b3881dd4223a9fc48052d20907da7c1763caab065bc47306abf43b30f08","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T14:09:33Z","title_canon_sha256":"09164ef804a9849ed982a8cf3759371e12b02a39750ab6d3f917eab9251f591e"},"schema_version":"1.0","source":{"id":"2508.05417","kind":"arxiv","version":5}},"canonical_sha256":"be4bd4b37f05c48946c0d47d8ef43e584d04f13eac4f0899cc4ca4b6857926d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be4bd4b37f05c48946c0d47d8ef43e584d04f13eac4f0899cc4ca4b6857926d0","first_computed_at":"2026-05-28T02:04:42.176377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:04:42.176377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kGKHyYrPkipoqNy2wieFlrLo1eCrwif9HoA/YebGzdhhdxotsakaw5ogBN5AM0NtuncbMRPsKxj6p55/YJadBw==","signature_status":"signed_v1","signed_at":"2026-05-28T02:04:42.176889Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.05417","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65a7209bfab73733e3f23c8af869b8527d8aa226afb8e57dcbee02f21e713282","sha256:268ac4f4655ae6997e030c62e55797d34c01f6725102e874a7aad5c8ceff47cb"],"state_sha256":"152933058d6c7b121992840e2eb921e0a915a43dd82baa380abc50e91597982c"}