{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2ADZ6FYFPVIF5RZL4ORUSUXJ6Y","short_pith_number":"pith:2ADZ6FYF","schema_version":"1.0","canonical_sha256":"d0079f17057d505ec72be3a34952e9f62751ea2603f832436ff213aa75c05c24","source":{"kind":"arxiv","id":"2404.13148","version":1},"attestation_state":"computed","paper":{"title":"BACS: Background Aware Continual Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Harakeh, Liam Paull, Mostafa Elaraby","submitted_at":"2024-04-19T19:25:26Z","abstract_excerpt":"Semantic segmentation plays a crucial role in enabling comprehensive scene understanding for robotic systems. However, generating annotations is challenging, requiring labels for every pixel in an image. In scenarios like autonomous driving, there's a need to progressively incorporate new classes as the operating environment of the deployed agent becomes more complex. For enhanced annotation efficiency, ideally, only pixels belonging to new classes would be annotated. This approach is known as Continual Semantic Segmentation (CSS). Besides the common problem of classical catastrophic forgettin"},"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":"2404.13148","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-19T19:25:26Z","cross_cats_sorted":[],"title_canon_sha256":"d63f4c68db1ced7d654d75206dc8fe7f36f1408c1e8876a5e2a73dce49f50717","abstract_canon_sha256":"7def690bb5a8bb9c71a665448e63d20f2c21176f1d6fece0c8f7513d5c71a782"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:27.978636Z","signature_b64":"V15jH+VF1xt+AtqJBbX+WbaR/RDEPc8ch7IDk6uWKLQy6bTOCbFW1MMKWz4ZVYEiYjdOSPavbMVz2Z7V0qlkAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0079f17057d505ec72be3a34952e9f62751ea2603f832436ff213aa75c05c24","last_reissued_at":"2026-07-05T08:10:27.978161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:27.978161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BACS: Background Aware Continual Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Harakeh, Liam Paull, Mostafa Elaraby","submitted_at":"2024-04-19T19:25:26Z","abstract_excerpt":"Semantic segmentation plays a crucial role in enabling comprehensive scene understanding for robotic systems. However, generating annotations is challenging, requiring labels for every pixel in an image. In scenarios like autonomous driving, there's a need to progressively incorporate new classes as the operating environment of the deployed agent becomes more complex. For enhanced annotation efficiency, ideally, only pixels belonging to new classes would be annotated. This approach is known as Continual Semantic Segmentation (CSS). Besides the common problem of classical catastrophic forgettin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13148","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/2404.13148/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":"2404.13148","created_at":"2026-07-05T08:10:27.978216+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.13148v1","created_at":"2026-07-05T08:10:27.978216+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13148","created_at":"2026-07-05T08:10:27.978216+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ADZ6FYFPVIF","created_at":"2026-07-05T08:10:27.978216+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ADZ6FYFPVIF5RZL","created_at":"2026-07-05T08:10:27.978216+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ADZ6FYF","created_at":"2026-07-05T08:10:27.978216+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12451","citing_title":"FuTCR: Future-Targeted Contrast and Repulsion for Continual Panoptic Segmentation","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12451","citing_title":"FuTCR: Future-Targeted Contrast and Repulsion for Continual Panoptic Segmentation","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ADZ6FYFPVIF5RZL4ORUSUXJ6Y","json":"https://pith.science/pith/2ADZ6FYFPVIF5RZL4ORUSUXJ6Y.json","graph_json":"https://pith.science/api/pith-number/2ADZ6FYFPVIF5RZL4ORUSUXJ6Y/graph.json","events_json":"https://pith.science/api/pith-number/2ADZ6FYFPVIF5RZL4ORUSUXJ6Y/events.json","paper":"https://pith.science/paper/2ADZ6FYF"},"agent_actions":{"view_html":"https://pith.science/pith/2ADZ6FYFPVIF5RZL4ORUSUXJ6Y","download_json":"https://pith.science/pith/2ADZ6FYFPVIF5RZL4ORUSUXJ6Y.json","view_paper":"https://pith.science/paper/2ADZ6FYF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.13148&json=true","fetch_graph":"https://pith.science/api/pith-number/2ADZ6FYFPVIF5RZL4ORUSUXJ6Y/graph.json","fetch_events":"https://pith.science/api/pith-number/2ADZ6FYFPVIF5RZL4ORUSUXJ6Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ADZ6FYFPVIF5RZL4ORUSUXJ6Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ADZ6FYFPVIF5RZL4ORUSUXJ6Y/action/storage_attestation","attest_author":"https://pith.science/pith/2ADZ6FYFPVIF5RZL4ORUSUXJ6Y/action/author_attestation","sign_citation":"https://pith.science/pith/2ADZ6FYFPVIF5RZL4ORUSUXJ6Y/action/citation_signature","submit_replication":"https://pith.science/pith/2ADZ6FYFPVIF5RZL4ORUSUXJ6Y/action/replication_record"}},"created_at":"2026-07-05T08:10:27.978216+00:00","updated_at":"2026-07-05T08:10:27.978216+00:00"}