{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VBQW652NBBN4POEBZ3HU6LFQWB","short_pith_number":"pith:VBQW652N","schema_version":"1.0","canonical_sha256":"a8616f774d085bc7b881cecf4f2cb0b06e01375a9fb4f2b4267810964d9aa5c4","source":{"kind":"arxiv","id":"2405.11067","version":3},"attestation_state":"computed","paper":{"title":"Bayesian Learning-driven Prototypical Contrastive Loss for Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alexander R\\\"ugamer, Christopher Mutschler, Felix Ott, Lucas Heublein, Nisha L. Raichur, Tobias Feigl","submitted_at":"2024-05-17T19:49:02Z","abstract_excerpt":"The primary objective of methods in continual learning is to learn tasks in a sequential manner over time (sometimes from a stream of data), while mitigating the detrimental phenomenon of catastrophic forgetting. This paper proposes a method to learn an effective representation between previous and newly encountered class prototypes. We propose a prototypical network with a Bayesian learning-driven contrastive loss (BLCL), tailored specifically for class-incremental learning scenarios. We introduce a contrastive loss that incorporates novel classes into the latent representation by reducing in"},"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":"2405.11067","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-17T19:49:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fd753b92e80230165f0b9ab59235458d17272e6f76ee7efba666c08a84128f11","abstract_canon_sha256":"0250c6f77a565375bebe5650457494d1bf21a24838fd9feb8f4061c6e91a29b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:46.560149Z","signature_b64":"C598ehHrGxIHWhJemYtCgisIOFEZGUjr0jNuuQzESkGH5DTd94sQIh3KYahQF4xQV8zkWJw8WcxeBPttwOn5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8616f774d085bc7b881cecf4f2cb0b06e01375a9fb4f2b4267810964d9aa5c4","last_reissued_at":"2026-07-05T10:41:46.559651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:46.559651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Learning-driven Prototypical Contrastive Loss for Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alexander R\\\"ugamer, Christopher Mutschler, Felix Ott, Lucas Heublein, Nisha L. Raichur, Tobias Feigl","submitted_at":"2024-05-17T19:49:02Z","abstract_excerpt":"The primary objective of methods in continual learning is to learn tasks in a sequential manner over time (sometimes from a stream of data), while mitigating the detrimental phenomenon of catastrophic forgetting. This paper proposes a method to learn an effective representation between previous and newly encountered class prototypes. We propose a prototypical network with a Bayesian learning-driven contrastive loss (BLCL), tailored specifically for class-incremental learning scenarios. We introduce a contrastive loss that incorporates novel classes into the latent representation by reducing in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11067","kind":"arxiv","version":3},"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/2405.11067/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":"2405.11067","created_at":"2026-07-05T10:41:46.559711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.11067v3","created_at":"2026-07-05T10:41:46.559711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11067","created_at":"2026-07-05T10:41:46.559711+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBQW652NBBN4","created_at":"2026-07-05T10:41:46.559711+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBQW652NBBN4POEB","created_at":"2026-07-05T10:41:46.559711+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBQW652N","created_at":"2026-07-05T10:41:46.559711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.05079","citing_title":"Multimodal-to-Text Prompt Engineering in Large Language Models Using Feature Embeddings for GNSS Interference Characterization","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VBQW652NBBN4POEBZ3HU6LFQWB","json":"https://pith.science/pith/VBQW652NBBN4POEBZ3HU6LFQWB.json","graph_json":"https://pith.science/api/pith-number/VBQW652NBBN4POEBZ3HU6LFQWB/graph.json","events_json":"https://pith.science/api/pith-number/VBQW652NBBN4POEBZ3HU6LFQWB/events.json","paper":"https://pith.science/paper/VBQW652N"},"agent_actions":{"view_html":"https://pith.science/pith/VBQW652NBBN4POEBZ3HU6LFQWB","download_json":"https://pith.science/pith/VBQW652NBBN4POEBZ3HU6LFQWB.json","view_paper":"https://pith.science/paper/VBQW652N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.11067&json=true","fetch_graph":"https://pith.science/api/pith-number/VBQW652NBBN4POEBZ3HU6LFQWB/graph.json","fetch_events":"https://pith.science/api/pith-number/VBQW652NBBN4POEBZ3HU6LFQWB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBQW652NBBN4POEBZ3HU6LFQWB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBQW652NBBN4POEBZ3HU6LFQWB/action/storage_attestation","attest_author":"https://pith.science/pith/VBQW652NBBN4POEBZ3HU6LFQWB/action/author_attestation","sign_citation":"https://pith.science/pith/VBQW652NBBN4POEBZ3HU6LFQWB/action/citation_signature","submit_replication":"https://pith.science/pith/VBQW652NBBN4POEBZ3HU6LFQWB/action/replication_record"}},"created_at":"2026-07-05T10:41:46.559711+00:00","updated_at":"2026-07-05T10:41:46.559711+00:00"}