{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XZF5JM37AXCISRWA2R6Y55B6LB","short_pith_number":"pith:XZF5JM37","canonical_record":{"source":{"id":"2508.05417","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T14:09:33Z","cross_cats_sorted":[],"title_canon_sha256":"09164ef804a9849ed982a8cf3759371e12b02a39750ab6d3f917eab9251f591e","abstract_canon_sha256":"b6b12b3881dd4223a9fc48052d20907da7c1763caab065bc47306abf43b30f08"},"schema_version":"1.0"},"canonical_sha256":"be4bd4b37f05c48946c0d47d8ef43e584d04f13eac4f0899cc4ca4b6857926d0","source":{"kind":"arxiv","id":"2508.05417","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XZF5JM37AXCISRWA2R6Y55B6LB","target":"record","payload":{"canonical_record":{"source":{"id":"2508.05417","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T14:09:33Z","cross_cats_sorted":[],"title_canon_sha256":"09164ef804a9849ed982a8cf3759371e12b02a39750ab6d3f917eab9251f591e","abstract_canon_sha256":"b6b12b3881dd4223a9fc48052d20907da7c1763caab065bc47306abf43b30f08"},"schema_version":"1.0"},"canonical_sha256":"be4bd4b37f05c48946c0d47d8ef43e584d04f13eac4f0899cc4ca4b6857926d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:42.176889Z","signature_b64":"kGKHyYrPkipoqNy2wieFlrLo1eCrwif9HoA/YebGzdhhdxotsakaw5ogBN5AM0NtuncbMRPsKxj6p55/YJadBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be4bd4b37f05c48946c0d47d8ef43e584d04f13eac4f0899cc4ca4b6857926d0","last_reissued_at":"2026-05-28T02:04:42.176377Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:42.176377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.05417","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T02:04:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b3x8h6lFJJnmVi7YF+AHGE6zlyOCokZ75cuZ31zX2wncRQUGEXBGFQBVdx4QaZcSVihrbahMmg17YlpF30OODg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T11:28:04.658865Z"},"content_sha256":"65a7209bfab73733e3f23c8af869b8527d8aa226afb8e57dcbee02f21e713282","schema_version":"1.0","event_id":"sha256:65a7209bfab73733e3f23c8af869b8527d8aa226afb8e57dcbee02f21e713282"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XZF5JM37AXCISRWA2R6Y55B6LB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Smoothing Slot Attention Iterations and Recurrences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"SmoothSA improves object-centric learning by smoothing slot attention iterations and recurrences.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Joni Pajarinen, Juho Kannala, Rongzhen Zhao, Wenyan Yang","submitted_at":"2025-08-07T14:09:33Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SmoothSA improves object-centric learning by smoothing slot attention iterations and recurrences.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ea8afb5ba87e619f22c3f43262e79208116852dd298a3a96d0619d5be91d1f46"},"source":{"id":"2508.05417","kind":"arxiv","version":5},"verdict":{"id":"cc500e45-6c67-46a0-b4c7-4e15c0e6fcbf","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-18T23:55:55.082406Z","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.","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","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.","pith_extraction_headline":"SmoothSA improves object-centric learning by smoothing slot attention iterations and recurrences."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.05417/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"},"verdict_id":"cc500e45-6c67-46a0-b4c7-4e15c0e6fcbf"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T02:04:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tG/suo3zYrnI7UW8Rn9N9BwzKQqBoehDpTqsknSLfa+B9+tXIiLOAOTi6tWcKByQ+PUFiFaDu8Hsm4verGUaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T11:28:04.659375Z"},"content_sha256":"268ac4f4655ae6997e030c62e55797d34c01f6725102e874a7aad5c8ceff47cb","schema_version":"1.0","event_id":"sha256:268ac4f4655ae6997e030c62e55797d34c01f6725102e874a7aad5c8ceff47cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XZF5JM37AXCISRWA2R6Y55B6LB/bundle.json","state_url":"https://pith.science/pith/XZF5JM37AXCISRWA2R6Y55B6LB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XZF5JM37AXCISRWA2R6Y55B6LB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-04T11:28:04Z","links":{"resolver":"https://pith.science/pith/XZF5JM37AXCISRWA2R6Y55B6LB","bundle":"https://pith.science/pith/XZF5JM37AXCISRWA2R6Y55B6LB/bundle.json","state":"https://pith.science/pith/XZF5JM37AXCISRWA2R6Y55B6LB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XZF5JM37AXCISRWA2R6Y55B6LB/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/aSTnLUT02OW02oOqdE7ELNdSPuXM6C6sHratFRqykFbNAhDWmrZLOEtgQTOQd/bulrH6hc867Q2nJ0IqrxlDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T11:28:04.661726Z","bundle_sha256":"84cff2bdf10e15ef6abc3db09d9943912052c1eef0f851350a7fd4bce6dbea9e"}}