{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6GBK5GSISA5A7FOZPQGH4Z3MKT","short_pith_number":"pith:6GBK5GSI","schema_version":"1.0","canonical_sha256":"f182ae9a48903a0f95d97c0c7e676c54c531e55ff1f87e6cf2e65a1b26fd088d","source":{"kind":"arxiv","id":"2508.19864","version":1},"attestation_state":"computed","paper":{"title":"Self-supervised structured object representation learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adel Hafiane, Antoine Letienne, Mohamed Abbas Hedjazi, Oussama Hadjerci","submitted_at":"2025-08-27T13:28:05Z","abstract_excerpt":"Self-supervised learning (SSL) has emerged as a powerful technique for learning visual representations. While recent SSL approaches achieve strong results in global image understanding, they are limited in capturing the structured representation in scenes. In this work, we propose a self-supervised approach that progressively builds structured visual representations by combining semantic grouping, instance level separation, and hierarchical structuring. Our approach, based on a novel ProtoScale module, captures visual elements across multiple spatial scales. Unlike common strategies like DINO "},"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":"2508.19864","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-27T13:28:05Z","cross_cats_sorted":[],"title_canon_sha256":"3e29870e148da7893aa5cdb9acef0b2dc18a5c4dd1078c8d5f56b68c992cc0d2","abstract_canon_sha256":"df4d180800752fb2eefb8bded5a615a491cf6c417447168adeac2934c0a25bd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:18.988455Z","signature_b64":"syyI4YVc5PQIQeFIhpUXyXddGp7PCbU07c5cf85EN/fkQcjWaxQXkcNK91lNnjjcQIl2jmnuWDHceR19EdqdBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f182ae9a48903a0f95d97c0c7e676c54c531e55ff1f87e6cf2e65a1b26fd088d","last_reissued_at":"2026-07-05T12:00:18.988022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:18.988022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised structured object representation learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adel Hafiane, Antoine Letienne, Mohamed Abbas Hedjazi, Oussama Hadjerci","submitted_at":"2025-08-27T13:28:05Z","abstract_excerpt":"Self-supervised learning (SSL) has emerged as a powerful technique for learning visual representations. While recent SSL approaches achieve strong results in global image understanding, they are limited in capturing the structured representation in scenes. In this work, we propose a self-supervised approach that progressively builds structured visual representations by combining semantic grouping, instance level separation, and hierarchical structuring. Our approach, based on a novel ProtoScale module, captures visual elements across multiple spatial scales. Unlike common strategies like DINO "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19864","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/2508.19864/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":"2508.19864","created_at":"2026-07-05T12:00:18.988077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.19864v1","created_at":"2026-07-05T12:00:18.988077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19864","created_at":"2026-07-05T12:00:18.988077+00:00"},{"alias_kind":"pith_short_12","alias_value":"6GBK5GSISA5A","created_at":"2026-07-05T12:00:18.988077+00:00"},{"alias_kind":"pith_short_16","alias_value":"6GBK5GSISA5A7FOZ","created_at":"2026-07-05T12:00:18.988077+00:00"},{"alias_kind":"pith_short_8","alias_value":"6GBK5GSI","created_at":"2026-07-05T12:00:18.988077+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/6GBK5GSISA5A7FOZPQGH4Z3MKT","json":"https://pith.science/pith/6GBK5GSISA5A7FOZPQGH4Z3MKT.json","graph_json":"https://pith.science/api/pith-number/6GBK5GSISA5A7FOZPQGH4Z3MKT/graph.json","events_json":"https://pith.science/api/pith-number/6GBK5GSISA5A7FOZPQGH4Z3MKT/events.json","paper":"https://pith.science/paper/6GBK5GSI"},"agent_actions":{"view_html":"https://pith.science/pith/6GBK5GSISA5A7FOZPQGH4Z3MKT","download_json":"https://pith.science/pith/6GBK5GSISA5A7FOZPQGH4Z3MKT.json","view_paper":"https://pith.science/paper/6GBK5GSI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.19864&json=true","fetch_graph":"https://pith.science/api/pith-number/6GBK5GSISA5A7FOZPQGH4Z3MKT/graph.json","fetch_events":"https://pith.science/api/pith-number/6GBK5GSISA5A7FOZPQGH4Z3MKT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6GBK5GSISA5A7FOZPQGH4Z3MKT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6GBK5GSISA5A7FOZPQGH4Z3MKT/action/storage_attestation","attest_author":"https://pith.science/pith/6GBK5GSISA5A7FOZPQGH4Z3MKT/action/author_attestation","sign_citation":"https://pith.science/pith/6GBK5GSISA5A7FOZPQGH4Z3MKT/action/citation_signature","submit_replication":"https://pith.science/pith/6GBK5GSISA5A7FOZPQGH4Z3MKT/action/replication_record"}},"created_at":"2026-07-05T12:00:18.988077+00:00","updated_at":"2026-07-05T12:00:18.988077+00:00"}