{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:66RH4OIZHWDIII4U7VIB4M3XBP","short_pith_number":"pith:66RH4OIZ","schema_version":"1.0","canonical_sha256":"f7a27e39193d86842394fd501e33770bfc29a819c949215317ff1a9c56de9f8d","source":{"kind":"arxiv","id":"2309.09122","version":1},"attestation_state":"computed","paper":{"title":"FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Byeongkeun Kang, Sejin Park, Taehyung Lee, Yeejin Lee","submitted_at":"2023-09-17T01:10:45Z","abstract_excerpt":"This work addresses the task of class-incremental weakly supervised object localization (CI-WSOL). The goal is to incrementally learn object localization for novel classes using only image-level annotations while retaining the ability to localize previously learned classes. This task is important because annotating bounding boxes for every new incoming data is expensive, although object localization is crucial in various applications. To the best of our knowledge, we are the first to address this task. Thus, we first present a strong baseline method for CI-WSOL by adapting the strategies of cl"},"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":"2309.09122","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-17T01:10:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e2a6444b15b6168499c5cd2ba50bb4cb86234b4ba0170cc51450cb34a402454e","abstract_canon_sha256":"faddf38dcf6b126893510296a57df8d6e2d3dc9318c35db8aff34ca5dac04fe7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:34.962244Z","signature_b64":"1lHgde1gMxCiRk7ojf9eUbRuwnaZ9aPB3Lg5r7mOH9E+olubxKq2eTgRrqUEJiFMqGzURsyITglgoXxKHpEmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7a27e39193d86842394fd501e33770bfc29a819c949215317ff1a9c56de9f8d","last_reissued_at":"2026-07-05T06:51:34.961802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:34.961802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Byeongkeun Kang, Sejin Park, Taehyung Lee, Yeejin Lee","submitted_at":"2023-09-17T01:10:45Z","abstract_excerpt":"This work addresses the task of class-incremental weakly supervised object localization (CI-WSOL). The goal is to incrementally learn object localization for novel classes using only image-level annotations while retaining the ability to localize previously learned classes. This task is important because annotating bounding boxes for every new incoming data is expensive, although object localization is crucial in various applications. To the best of our knowledge, we are the first to address this task. Thus, we first present a strong baseline method for CI-WSOL by adapting the strategies of cl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09122","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/2309.09122/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":"2309.09122","created_at":"2026-07-05T06:51:34.961861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09122v1","created_at":"2026-07-05T06:51:34.961861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09122","created_at":"2026-07-05T06:51:34.961861+00:00"},{"alias_kind":"pith_short_12","alias_value":"66RH4OIZHWDI","created_at":"2026-07-05T06:51:34.961861+00:00"},{"alias_kind":"pith_short_16","alias_value":"66RH4OIZHWDIII4U","created_at":"2026-07-05T06:51:34.961861+00:00"},{"alias_kind":"pith_short_8","alias_value":"66RH4OIZ","created_at":"2026-07-05T06:51:34.961861+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02491","citing_title":"From Experimental Limits to Physical Insight: A Retrieval-Augmented Multi-Agent Framework for Interpreting Searches Beyond the Standard Model","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/66RH4OIZHWDIII4U7VIB4M3XBP","json":"https://pith.science/pith/66RH4OIZHWDIII4U7VIB4M3XBP.json","graph_json":"https://pith.science/api/pith-number/66RH4OIZHWDIII4U7VIB4M3XBP/graph.json","events_json":"https://pith.science/api/pith-number/66RH4OIZHWDIII4U7VIB4M3XBP/events.json","paper":"https://pith.science/paper/66RH4OIZ"},"agent_actions":{"view_html":"https://pith.science/pith/66RH4OIZHWDIII4U7VIB4M3XBP","download_json":"https://pith.science/pith/66RH4OIZHWDIII4U7VIB4M3XBP.json","view_paper":"https://pith.science/paper/66RH4OIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09122&json=true","fetch_graph":"https://pith.science/api/pith-number/66RH4OIZHWDIII4U7VIB4M3XBP/graph.json","fetch_events":"https://pith.science/api/pith-number/66RH4OIZHWDIII4U7VIB4M3XBP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66RH4OIZHWDIII4U7VIB4M3XBP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66RH4OIZHWDIII4U7VIB4M3XBP/action/storage_attestation","attest_author":"https://pith.science/pith/66RH4OIZHWDIII4U7VIB4M3XBP/action/author_attestation","sign_citation":"https://pith.science/pith/66RH4OIZHWDIII4U7VIB4M3XBP/action/citation_signature","submit_replication":"https://pith.science/pith/66RH4OIZHWDIII4U7VIB4M3XBP/action/replication_record"}},"created_at":"2026-07-05T06:51:34.961861+00:00","updated_at":"2026-07-05T06:51:34.961861+00:00"}