{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SESIWFIOKMMCY7EEKW3SYO7JGK","short_pith_number":"pith:SESIWFIO","schema_version":"1.0","canonical_sha256":"91248b150e53182c7c8455b72c3be9328c727661a3724bfc82baf469682dae89","source":{"kind":"arxiv","id":"2305.19550","version":1},"attestation_state":"computed","paper":{"title":"Spotlight Attention: Robust Object-Centric Learning With a Spatial Locality Prior","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anirudh Goyal, Ayush Chakravarthy, Michael C. Mozer, Trang Nguyen, Yoshua Bengio","submitted_at":"2023-05-31T04:35:50Z","abstract_excerpt":"The aim of object-centric vision is to construct an explicit representation of the objects in a scene. This representation is obtained via a set of interchangeable modules called \\emph{slots} or \\emph{object files} that compete for local patches of an image. The competition has a weak inductive bias to preserve spatial continuity; consequently, one slot may claim patches scattered diffusely throughout the image. In contrast, the inductive bias of human vision is strong, to the degree that attention has classically been described with a spotlight metaphor. We incorporate a spatial-locality prio"},"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":"2305.19550","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-31T04:35:50Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1b8227339d90c37d2789cda82ea4c51612eba10d8dc4ed78f0fae65308c36ebf","abstract_canon_sha256":"b144dfc8dd55d59b326f170d01630ea2509e03598d9c4e21893e9c7455cd0559"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:08.227507Z","signature_b64":"5uanUc7pXV6GWUzNQ3cwjVB0DdkAg1hw+VCL4Oka/shHEP7+f23YJEjH/iZGoS++21ZTRJdwLyvmLZ2jBC8iCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91248b150e53182c7c8455b72c3be9328c727661a3724bfc82baf469682dae89","last_reissued_at":"2026-07-05T06:17:08.227075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:08.227075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spotlight Attention: Robust Object-Centric Learning With a Spatial Locality Prior","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anirudh Goyal, Ayush Chakravarthy, Michael C. Mozer, Trang Nguyen, Yoshua Bengio","submitted_at":"2023-05-31T04:35:50Z","abstract_excerpt":"The aim of object-centric vision is to construct an explicit representation of the objects in a scene. This representation is obtained via a set of interchangeable modules called \\emph{slots} or \\emph{object files} that compete for local patches of an image. The competition has a weak inductive bias to preserve spatial continuity; consequently, one slot may claim patches scattered diffusely throughout the image. In contrast, the inductive bias of human vision is strong, to the degree that attention has classically been described with a spotlight metaphor. We incorporate a spatial-locality prio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19550","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/2305.19550/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":"2305.19550","created_at":"2026-07-05T06:17:08.227137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.19550v1","created_at":"2026-07-05T06:17:08.227137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19550","created_at":"2026-07-05T06:17:08.227137+00:00"},{"alias_kind":"pith_short_12","alias_value":"SESIWFIOKMMC","created_at":"2026-07-05T06:17:08.227137+00:00"},{"alias_kind":"pith_short_16","alias_value":"SESIWFIOKMMCY7EE","created_at":"2026-07-05T06:17:08.227137+00:00"},{"alias_kind":"pith_short_8","alias_value":"SESIWFIO","created_at":"2026-07-05T06:17:08.227137+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04364","citing_title":"Spatially Grounded Concept Bottleneck Models via Part-Factorized Attention","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SESIWFIOKMMCY7EEKW3SYO7JGK","json":"https://pith.science/pith/SESIWFIOKMMCY7EEKW3SYO7JGK.json","graph_json":"https://pith.science/api/pith-number/SESIWFIOKMMCY7EEKW3SYO7JGK/graph.json","events_json":"https://pith.science/api/pith-number/SESIWFIOKMMCY7EEKW3SYO7JGK/events.json","paper":"https://pith.science/paper/SESIWFIO"},"agent_actions":{"view_html":"https://pith.science/pith/SESIWFIOKMMCY7EEKW3SYO7JGK","download_json":"https://pith.science/pith/SESIWFIOKMMCY7EEKW3SYO7JGK.json","view_paper":"https://pith.science/paper/SESIWFIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.19550&json=true","fetch_graph":"https://pith.science/api/pith-number/SESIWFIOKMMCY7EEKW3SYO7JGK/graph.json","fetch_events":"https://pith.science/api/pith-number/SESIWFIOKMMCY7EEKW3SYO7JGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SESIWFIOKMMCY7EEKW3SYO7JGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SESIWFIOKMMCY7EEKW3SYO7JGK/action/storage_attestation","attest_author":"https://pith.science/pith/SESIWFIOKMMCY7EEKW3SYO7JGK/action/author_attestation","sign_citation":"https://pith.science/pith/SESIWFIOKMMCY7EEKW3SYO7JGK/action/citation_signature","submit_replication":"https://pith.science/pith/SESIWFIOKMMCY7EEKW3SYO7JGK/action/replication_record"}},"created_at":"2026-07-05T06:17:08.227137+00:00","updated_at":"2026-07-05T06:17:08.227137+00:00"}