{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2KTADVWTODIZHRTZDVEFDJ6TZQ","short_pith_number":"pith:2KTADVWT","canonical_record":{"source":{"id":"2410.15728","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T07:44:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"84ba63addd09e804a04a0e6d7119ebae5cea380bc392fa1e93d5d4a4cc6b3b6f","abstract_canon_sha256":"61d46e6d1baf1e37cfe3702ce96f5562e913d2943e655cbfc7e800ea75a099c1"},"schema_version":"1.0"},"canonical_sha256":"d2a601d6d370d193c6791d4851a7d3cc16aa82b79132c54598bb143c3001bf67","source":{"kind":"arxiv","id":"2410.15728","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15728","created_at":"2026-07-05T09:23:23Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15728v1","created_at":"2026-07-05T09:23:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15728","created_at":"2026-07-05T09:23:23Z"},{"alias_kind":"pith_short_12","alias_value":"2KTADVWTODIZ","created_at":"2026-07-05T09:23:23Z"},{"alias_kind":"pith_short_16","alias_value":"2KTADVWTODIZHRTZ","created_at":"2026-07-05T09:23:23Z"},{"alias_kind":"pith_short_8","alias_value":"2KTADVWT","created_at":"2026-07-05T09:23:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2KTADVWTODIZHRTZDVEFDJ6TZQ","target":"record","payload":{"canonical_record":{"source":{"id":"2410.15728","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T07:44:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"84ba63addd09e804a04a0e6d7119ebae5cea380bc392fa1e93d5d4a4cc6b3b6f","abstract_canon_sha256":"61d46e6d1baf1e37cfe3702ce96f5562e913d2943e655cbfc7e800ea75a099c1"},"schema_version":"1.0"},"canonical_sha256":"d2a601d6d370d193c6791d4851a7d3cc16aa82b79132c54598bb143c3001bf67","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:23.846675Z","signature_b64":"AThB135xQjlxSj9oEXYSnL86Ebpf1i2gIb2REWo1r+yYgXxqNhyF4wUt0CULVjJds8qeF6215NKUjnOZtx/cDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2a601d6d370d193c6791d4851a7d3cc16aa82b79132c54598bb143c3001bf67","last_reissued_at":"2026-07-05T09:23:23.846163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:23.846163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.15728","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:23:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6gRwB1J/nDbhjOSXuEGVZ+W/okLLmYQD313hHCeGsQDjJk3BVjfCmDexnpBjl8NKVNPrVq5YL8m84UswR1VzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:14:59.459876Z"},"content_sha256":"eb2e2db911c51e5097db461a9848a928f055dec6f06435a308ee92ebf7ccb97a","schema_version":"1.0","event_id":"sha256:eb2e2db911c51e5097db461a9848a928f055dec6f06435a308ee92ebf7ccb97a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2KTADVWTODIZHRTZDVEFDJ6TZQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Akihiro Nakano, Aniket Didolkar, Anirudh Goyal, Cristian Meo, Justin Dauwels, Masahiro Suzuki, Mengmi Zhang, Mircea Lic\\u{a}, Yoshua Bengio, Yutaka Matsuo","submitted_at":"2024-10-21T07:44:44Z","abstract_excerpt":"Unsupervised object-centric learning from videos is a promising approach towards learning compositional representations that can be applied to various downstream tasks, such as prediction and reasoning. Recently, it was shown that pretrained Vision Transformers (ViTs) can be useful to learn object-centric representations on real-world video datasets. However, while these approaches succeed at extracting objects from the scenes, the slot-based representations fail to maintain temporal consistency across consecutive frames in a video, i.e. the mapping of objects to slots changes across the video"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15728","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/2410.15728/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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:23:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r+FGXbskfue30Gctz/c74tapQyFBH4Wf+T//FPrDmXBpRjtTIGGTZmSTkO3Q0xWlOw0vgmxt2f//kNcJJCLwBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:14:59.460254Z"},"content_sha256":"fd42701493f4283382bc6404b6970e05a941fa22582a689d1e0f6fc80403cff6","schema_version":"1.0","event_id":"sha256:fd42701493f4283382bc6404b6970e05a941fa22582a689d1e0f6fc80403cff6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2KTADVWTODIZHRTZDVEFDJ6TZQ/bundle.json","state_url":"https://pith.science/pith/2KTADVWTODIZHRTZDVEFDJ6TZQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2KTADVWTODIZHRTZDVEFDJ6TZQ/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":"2026-07-06T18:14:59Z","links":{"resolver":"https://pith.science/pith/2KTADVWTODIZHRTZDVEFDJ6TZQ","bundle":"https://pith.science/pith/2KTADVWTODIZHRTZDVEFDJ6TZQ/bundle.json","state":"https://pith.science/pith/2KTADVWTODIZHRTZDVEFDJ6TZQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2KTADVWTODIZHRTZDVEFDJ6TZQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2KTADVWTODIZHRTZDVEFDJ6TZQ","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":"61d46e6d1baf1e37cfe3702ce96f5562e913d2943e655cbfc7e800ea75a099c1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T07:44:44Z","title_canon_sha256":"84ba63addd09e804a04a0e6d7119ebae5cea380bc392fa1e93d5d4a4cc6b3b6f"},"schema_version":"1.0","source":{"id":"2410.15728","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15728","created_at":"2026-07-05T09:23:23Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15728v1","created_at":"2026-07-05T09:23:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15728","created_at":"2026-07-05T09:23:23Z"},{"alias_kind":"pith_short_12","alias_value":"2KTADVWTODIZ","created_at":"2026-07-05T09:23:23Z"},{"alias_kind":"pith_short_16","alias_value":"2KTADVWTODIZHRTZ","created_at":"2026-07-05T09:23:23Z"},{"alias_kind":"pith_short_8","alias_value":"2KTADVWT","created_at":"2026-07-05T09:23:23Z"}],"graph_snapshots":[{"event_id":"sha256:fd42701493f4283382bc6404b6970e05a941fa22582a689d1e0f6fc80403cff6","target":"graph","created_at":"2026-07-05T09:23:23Z","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/2410.15728/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised object-centric learning from videos is a promising approach towards learning compositional representations that can be applied to various downstream tasks, such as prediction and reasoning. Recently, it was shown that pretrained Vision Transformers (ViTs) can be useful to learn object-centric representations on real-world video datasets. However, while these approaches succeed at extracting objects from the scenes, the slot-based representations fail to maintain temporal consistency across consecutive frames in a video, i.e. the mapping of objects to slots changes across the video","authors_text":"Akihiro Nakano, Aniket Didolkar, Anirudh Goyal, Cristian Meo, Justin Dauwels, Masahiro Suzuki, Mengmi Zhang, Mircea Lic\\u{a}, Yoshua Bengio, Yutaka Matsuo","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T07:44:44Z","title":"Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15728","kind":"arxiv","version":1},"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:eb2e2db911c51e5097db461a9848a928f055dec6f06435a308ee92ebf7ccb97a","target":"record","created_at":"2026-07-05T09:23:23Z","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":"61d46e6d1baf1e37cfe3702ce96f5562e913d2943e655cbfc7e800ea75a099c1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T07:44:44Z","title_canon_sha256":"84ba63addd09e804a04a0e6d7119ebae5cea380bc392fa1e93d5d4a4cc6b3b6f"},"schema_version":"1.0","source":{"id":"2410.15728","kind":"arxiv","version":1}},"canonical_sha256":"d2a601d6d370d193c6791d4851a7d3cc16aa82b79132c54598bb143c3001bf67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2a601d6d370d193c6791d4851a7d3cc16aa82b79132c54598bb143c3001bf67","first_computed_at":"2026-07-05T09:23:23.846163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:23.846163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AThB135xQjlxSj9oEXYSnL86Ebpf1i2gIb2REWo1r+yYgXxqNhyF4wUt0CULVjJds8qeF6215NKUjnOZtx/cDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:23.846675Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.15728","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb2e2db911c51e5097db461a9848a928f055dec6f06435a308ee92ebf7ccb97a","sha256:fd42701493f4283382bc6404b6970e05a941fa22582a689d1e0f6fc80403cff6"],"state_sha256":"cb7dbf2efd2b69ee4791f11a961511431bbe7589aedc83b669c1a1d1906ffc9f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QWBbcyearA6QSd/UNm1AHVvY1Uyf1RBl/j6iZzF+XEUl45GNuHPckTf8SIhcEAcTqWZUtWDw1nugbbaEXXFCCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:14:59.462207Z","bundle_sha256":"9294d05f838e478fb7089bb706e8e588ed7ef1cc03ab4990a3e7db041b200f52"}}