{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UOCWJUEXZCDZEBDJJD3433WPSQ","short_pith_number":"pith:UOCWJUEX","schema_version":"1.0","canonical_sha256":"a38564d097c88792046948f7cdeecf9409d1fbf1feb0cd175edd527e61fcfbfe","source":{"kind":"arxiv","id":"2510.09171","version":2},"attestation_state":"computed","paper":{"title":"Instance-Level Generation for Representation Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Giorgos Kordopatis-Zilos, Giorgos Tolias, Noa Garcia, Yankun Wu, Zakaria Laskar","submitted_at":"2025-10-10T09:14:33Z","abstract_excerpt":"Instance-level recognition (ILR) focuses on identifying individual objects rather than broad categories, offering the highest granularity in image classification. However, this fine-grained nature makes creating large-scale annotated datasets challenging, limiting ILR's real-world applicability across domains. To overcome this, we introduce a novel approach that synthetically generates diverse object instances from multiple domains under varied conditions and backgrounds, forming a large-scale training set. Unlike prior work on automatic data synthesis, our method is the first to address ILR-s"},"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":"2510.09171","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-10T09:14:33Z","cross_cats_sorted":[],"title_canon_sha256":"75d1a55a2a80abb2d20bafd5e3cd2f106187be10f460de3c0f3da63070224e9e","abstract_canon_sha256":"1fd3730a4b25ab706f81187deda4663bd8bbb71b44705a5f72e6fa9733d03f58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T02:21:23.199476Z","signature_b64":"biWhm0U4bD58a8hULYyzsWTbJCyg8u27y0966Tm7K91/hOlut/m604E8avU9pP5tLJ0sM68R2R1KVw3alNR8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a38564d097c88792046948f7cdeecf9409d1fbf1feb0cd175edd527e61fcfbfe","last_reissued_at":"2026-07-21T02:21:23.198600Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T02:21:23.198600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instance-Level Generation for Representation Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Giorgos Kordopatis-Zilos, Giorgos Tolias, Noa Garcia, Yankun Wu, Zakaria Laskar","submitted_at":"2025-10-10T09:14:33Z","abstract_excerpt":"Instance-level recognition (ILR) focuses on identifying individual objects rather than broad categories, offering the highest granularity in image classification. However, this fine-grained nature makes creating large-scale annotated datasets challenging, limiting ILR's real-world applicability across domains. To overcome this, we introduce a novel approach that synthetically generates diverse object instances from multiple domains under varied conditions and backgrounds, forming a large-scale training set. Unlike prior work on automatic data synthesis, our method is the first to address ILR-s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.09171","kind":"arxiv","version":2},"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/2510.09171/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":"2510.09171","created_at":"2026-07-21T02:21:23.199020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.09171v2","created_at":"2026-07-21T02:21:23.199020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.09171","created_at":"2026-07-21T02:21:23.199020+00:00"},{"alias_kind":"pith_short_12","alias_value":"UOCWJUEXZCDZ","created_at":"2026-07-21T02:21:23.199020+00:00"},{"alias_kind":"pith_short_16","alias_value":"UOCWJUEXZCDZEBDJ","created_at":"2026-07-21T02:21:23.199020+00:00"},{"alias_kind":"pith_short_8","alias_value":"UOCWJUEX","created_at":"2026-07-21T02:21:23.199020+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/UOCWJUEXZCDZEBDJJD3433WPSQ","json":"https://pith.science/pith/UOCWJUEXZCDZEBDJJD3433WPSQ.json","graph_json":"https://pith.science/api/pith-number/UOCWJUEXZCDZEBDJJD3433WPSQ/graph.json","events_json":"https://pith.science/api/pith-number/UOCWJUEXZCDZEBDJJD3433WPSQ/events.json","paper":"https://pith.science/paper/UOCWJUEX"},"agent_actions":{"view_html":"https://pith.science/pith/UOCWJUEXZCDZEBDJJD3433WPSQ","download_json":"https://pith.science/pith/UOCWJUEXZCDZEBDJJD3433WPSQ.json","view_paper":"https://pith.science/paper/UOCWJUEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.09171&json=true","fetch_graph":"https://pith.science/api/pith-number/UOCWJUEXZCDZEBDJJD3433WPSQ/graph.json","fetch_events":"https://pith.science/api/pith-number/UOCWJUEXZCDZEBDJJD3433WPSQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UOCWJUEXZCDZEBDJJD3433WPSQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UOCWJUEXZCDZEBDJJD3433WPSQ/action/storage_attestation","attest_author":"https://pith.science/pith/UOCWJUEXZCDZEBDJJD3433WPSQ/action/author_attestation","sign_citation":"https://pith.science/pith/UOCWJUEXZCDZEBDJJD3433WPSQ/action/citation_signature","submit_replication":"https://pith.science/pith/UOCWJUEXZCDZEBDJJD3433WPSQ/action/replication_record"}},"created_at":"2026-07-21T02:21:23.199020+00:00","updated_at":"2026-07-21T02:21:23.199020+00:00"}