{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GCJ2PVSPSG7TQJU2YJXO2RF4VJ","short_pith_number":"pith:GCJ2PVSP","schema_version":"1.0","canonical_sha256":"3093a7d64f91bf38269ac26eed44bcaa7cdfc63de44b31333b4484a2a2438a19","source":{"kind":"arxiv","id":"2605.31508","version":1},"attestation_state":"computed","paper":{"title":"Internalizing Temporal Consistency in Video Object-Centric Learning without Explicit Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Joni Pajarinen, Juho Kannala, Rongzhen Zhao, Zhiyuan Li","submitted_at":"2026-05-29T16:28:21Z","abstract_excerpt":"Video Object-Centric Learning (OCL) aims to represent objects as \\textit{slot} vectors and maintain their consistency across frames. Slot-Slot Contrastive (SSC) loss has become the cornerstone for state-of-the-art (SOTA) video OCL methods. While highly effective, SSC relies on one-to-one object correspondence across frames and introduces an extra loss. Following Occam's Razor, we propose a paradigm shift: temporal consistency is better enforced as an implicit model design rather than an explicit loss. To elegantly exclude SSC (\\textbf{xSSC}), we introduce two quasi-zero-overhead synergistic me"},"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":"2605.31508","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T16:28:21Z","cross_cats_sorted":[],"title_canon_sha256":"1cd0979b059263cb863aeb7887bb9026ac203036ddd6bba230a11febfc59cb7e","abstract_canon_sha256":"21d6182ab26a4fa188655e579cdad270da0e2934c092982f5a44f094c94ac55f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:04:09.918111Z","signature_b64":"eR4hRG2T5X9GrFKT/Ths8rBcggW83Y15y/ooUkB2u39IgYie2j7EX21DI4ARE8Ou5RyYwmc+N3wVw4n+lxxwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3093a7d64f91bf38269ac26eed44bcaa7cdfc63de44b31333b4484a2a2438a19","last_reissued_at":"2026-06-01T02:04:09.916956Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:04:09.916956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Internalizing Temporal Consistency in Video Object-Centric Learning without Explicit Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Joni Pajarinen, Juho Kannala, Rongzhen Zhao, Zhiyuan Li","submitted_at":"2026-05-29T16:28:21Z","abstract_excerpt":"Video Object-Centric Learning (OCL) aims to represent objects as \\textit{slot} vectors and maintain their consistency across frames. Slot-Slot Contrastive (SSC) loss has become the cornerstone for state-of-the-art (SOTA) video OCL methods. While highly effective, SSC relies on one-to-one object correspondence across frames and introduces an extra loss. Following Occam's Razor, we propose a paradigm shift: temporal consistency is better enforced as an implicit model design rather than an explicit loss. To elegantly exclude SSC (\\textbf{xSSC}), we introduce two quasi-zero-overhead synergistic me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31508","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/2605.31508/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":"2605.31508","created_at":"2026-06-01T02:04:09.917124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31508v1","created_at":"2026-06-01T02:04:09.917124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31508","created_at":"2026-06-01T02:04:09.917124+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCJ2PVSPSG7T","created_at":"2026-06-01T02:04:09.917124+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCJ2PVSPSG7TQJU2","created_at":"2026-06-01T02:04:09.917124+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCJ2PVSP","created_at":"2026-06-01T02:04:09.917124+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/GCJ2PVSPSG7TQJU2YJXO2RF4VJ","json":"https://pith.science/pith/GCJ2PVSPSG7TQJU2YJXO2RF4VJ.json","graph_json":"https://pith.science/api/pith-number/GCJ2PVSPSG7TQJU2YJXO2RF4VJ/graph.json","events_json":"https://pith.science/api/pith-number/GCJ2PVSPSG7TQJU2YJXO2RF4VJ/events.json","paper":"https://pith.science/paper/GCJ2PVSP"},"agent_actions":{"view_html":"https://pith.science/pith/GCJ2PVSPSG7TQJU2YJXO2RF4VJ","download_json":"https://pith.science/pith/GCJ2PVSPSG7TQJU2YJXO2RF4VJ.json","view_paper":"https://pith.science/paper/GCJ2PVSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31508&json=true","fetch_graph":"https://pith.science/api/pith-number/GCJ2PVSPSG7TQJU2YJXO2RF4VJ/graph.json","fetch_events":"https://pith.science/api/pith-number/GCJ2PVSPSG7TQJU2YJXO2RF4VJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCJ2PVSPSG7TQJU2YJXO2RF4VJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCJ2PVSPSG7TQJU2YJXO2RF4VJ/action/storage_attestation","attest_author":"https://pith.science/pith/GCJ2PVSPSG7TQJU2YJXO2RF4VJ/action/author_attestation","sign_citation":"https://pith.science/pith/GCJ2PVSPSG7TQJU2YJXO2RF4VJ/action/citation_signature","submit_replication":"https://pith.science/pith/GCJ2PVSPSG7TQJU2YJXO2RF4VJ/action/replication_record"}},"created_at":"2026-06-01T02:04:09.917124+00:00","updated_at":"2026-06-01T02:04:09.917124+00:00"}