{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:55YI4USCS46NB3CBI6ZGRN6GCA","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":"8c92f2ab8e7a8a3d99117656bd74a9c2f4cb308320eac2bd9f00153ab18ab785","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-18T15:20:13Z","title_canon_sha256":"96ab7a53f3713c9db9f1664c3dc5ed9c4d27db7fb316e2966c13a6e42f1e4f21"},"schema_version":"1.0","source":{"id":"2309.09858","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.09858","created_at":"2026-07-05T08:37:04Z"},{"alias_kind":"arxiv_version","alias_value":"2309.09858v2","created_at":"2026-07-05T08:37:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09858","created_at":"2026-07-05T08:37:04Z"},{"alias_kind":"pith_short_12","alias_value":"55YI4USCS46N","created_at":"2026-07-05T08:37:04Z"},{"alias_kind":"pith_short_16","alias_value":"55YI4USCS46NB3CB","created_at":"2026-07-05T08:37:04Z"},{"alias_kind":"pith_short_8","alias_value":"55YI4USC","created_at":"2026-07-05T08:37:04Z"}],"graph_snapshots":[{"event_id":"sha256:63b8ca5a7e8b1d41f450d3d902d9001e90cbaed604848fb8ee3e598cb881a87c","target":"graph","created_at":"2026-07-05T08:37:04Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2309.09858/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we show that recent advances in video representation learning and pre-trained vision-language models allow for substantial improvements in self-supervised video object localization. We propose a method that first localizes objects in videos via an object-centric approach with slot attention and then assigns text to the obtained slots. The latter is achieved by an unsupervised way to read localized semantic information from the pre-trained CLIP model. The resulting video object localization is entirely unsupervised apart from the implicit annotation contained in CLIP, and it is e","authors_text":"Bernt Schiele, Carl-Johann Simon-Gabriel, Dominik Zietlow, Francesco Locatello, Ke Fan, Max Horn, Mike Zheng Shou, Thomas Brox, Tianjun Xiao, Tong He, Yanwei Fu, Zechen Bai, Zheng Zhang, Zixu Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-18T15:20:13Z","title":"Unsupervised Open-Vocabulary Object Localization in Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09858","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:169b61dc23a584ae2975cf34308810d95f646fe5751232f8d57b8d37f46f7643","target":"record","created_at":"2026-07-05T08:37:04Z","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":"8c92f2ab8e7a8a3d99117656bd74a9c2f4cb308320eac2bd9f00153ab18ab785","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-18T15:20:13Z","title_canon_sha256":"96ab7a53f3713c9db9f1664c3dc5ed9c4d27db7fb316e2966c13a6e42f1e4f21"},"schema_version":"1.0","source":{"id":"2309.09858","kind":"arxiv","version":2}},"canonical_sha256":"ef708e5242973cd0ec4147b268b7c6102380ec0e32074ece6f873f14e9409410","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef708e5242973cd0ec4147b268b7c6102380ec0e32074ece6f873f14e9409410","first_computed_at":"2026-07-05T08:37:04.139600Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:04.139600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OJgdt1lKB5CzL65O3m6iJySUnFEsH9CBxuTGd3CtRLb3Ul+ze20yOz9ln4zjOSz97oPM8ihebs7umzgMxYb3Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:04.140033Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.09858","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:169b61dc23a584ae2975cf34308810d95f646fe5751232f8d57b8d37f46f7643","sha256:63b8ca5a7e8b1d41f450d3d902d9001e90cbaed604848fb8ee3e598cb881a87c"],"state_sha256":"ac36d2414a4b58621a583252c5ae013be2957c6e1dfdfca7b0126a53bb1fc710"}