{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L6QINLTYUUXRZNR6LYSOOXMTVA","short_pith_number":"pith:L6QINLTY","schema_version":"1.0","canonical_sha256":"5fa086ae78a52f1cb63e5e24e75d93a83709fa4d29a316e1aa7a865c11380ad4","source":{"kind":"arxiv","id":"2606.12601","version":1},"attestation_state":"computed","paper":{"title":"Dual-State Slot Attention: Decoupling Appearance and Identity for Video Object-Centric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Duc Nguyen, Hao Vo, Khoa Vo, Ngan Le, Sieu Tran","submitted_at":"2026-06-10T19:00:47Z","abstract_excerpt":"Unsupervised video object-centric learning aims to decompose dynamic scenes into persistent, object-level representations without supervision. However, existing slot-based methods struggle to maintain stable object identity in challenging settings such as rapid motion and partial occlusion. First, they typically encode both the per-frame appearance of an object and its identity across frames in a single slot vector, creating an objective conflict that leads to slot swapping: reconstruction requires sensitivity to transient visual changes, whereas temporal consistency requires invariance to the"},"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":"2606.12601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T19:00:47Z","cross_cats_sorted":[],"title_canon_sha256":"4b1429a00533486140146a50d5c03133fd4fa61a68ea9c07460e203bd380cfa7","abstract_canon_sha256":"1bb3bac8db8c264277556557c4aa88c93f246b6748ce8f3296c5c41d2dd4f7e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T00:07:55.992711Z","signature_b64":"8eklNpFEXRmWjBQWPcxLClJY8TCh1qlt8oekdYgvTzIvf1BgiK31qbJxup/BGnsKEONSIQBOB/bYF66/iESMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fa086ae78a52f1cb63e5e24e75d93a83709fa4d29a316e1aa7a865c11380ad4","last_reissued_at":"2026-06-12T00:07:55.992258Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T00:07:55.992258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual-State Slot Attention: Decoupling Appearance and Identity for Video Object-Centric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Duc Nguyen, Hao Vo, Khoa Vo, Ngan Le, Sieu Tran","submitted_at":"2026-06-10T19:00:47Z","abstract_excerpt":"Unsupervised video object-centric learning aims to decompose dynamic scenes into persistent, object-level representations without supervision. However, existing slot-based methods struggle to maintain stable object identity in challenging settings such as rapid motion and partial occlusion. First, they typically encode both the per-frame appearance of an object and its identity across frames in a single slot vector, creating an objective conflict that leads to slot swapping: reconstruction requires sensitivity to transient visual changes, whereas temporal consistency requires invariance to the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12601","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/2606.12601/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":"2606.12601","created_at":"2026-06-12T00:07:55.992348+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12601v1","created_at":"2026-06-12T00:07:55.992348+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12601","created_at":"2026-06-12T00:07:55.992348+00:00"},{"alias_kind":"pith_short_12","alias_value":"L6QINLTYUUXR","created_at":"2026-06-12T00:07:55.992348+00:00"},{"alias_kind":"pith_short_16","alias_value":"L6QINLTYUUXRZNR6","created_at":"2026-06-12T00:07:55.992348+00:00"},{"alias_kind":"pith_short_8","alias_value":"L6QINLTY","created_at":"2026-06-12T00:07:55.992348+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/L6QINLTYUUXRZNR6LYSOOXMTVA","json":"https://pith.science/pith/L6QINLTYUUXRZNR6LYSOOXMTVA.json","graph_json":"https://pith.science/api/pith-number/L6QINLTYUUXRZNR6LYSOOXMTVA/graph.json","events_json":"https://pith.science/api/pith-number/L6QINLTYUUXRZNR6LYSOOXMTVA/events.json","paper":"https://pith.science/paper/L6QINLTY"},"agent_actions":{"view_html":"https://pith.science/pith/L6QINLTYUUXRZNR6LYSOOXMTVA","download_json":"https://pith.science/pith/L6QINLTYUUXRZNR6LYSOOXMTVA.json","view_paper":"https://pith.science/paper/L6QINLTY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12601&json=true","fetch_graph":"https://pith.science/api/pith-number/L6QINLTYUUXRZNR6LYSOOXMTVA/graph.json","fetch_events":"https://pith.science/api/pith-number/L6QINLTYUUXRZNR6LYSOOXMTVA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L6QINLTYUUXRZNR6LYSOOXMTVA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L6QINLTYUUXRZNR6LYSOOXMTVA/action/storage_attestation","attest_author":"https://pith.science/pith/L6QINLTYUUXRZNR6LYSOOXMTVA/action/author_attestation","sign_citation":"https://pith.science/pith/L6QINLTYUUXRZNR6LYSOOXMTVA/action/citation_signature","submit_replication":"https://pith.science/pith/L6QINLTYUUXRZNR6LYSOOXMTVA/action/replication_record"}},"created_at":"2026-06-12T00:07:55.992348+00:00","updated_at":"2026-06-12T00:07:55.992348+00:00"}