{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:75EIM3AWANMU4AZ22LFOHVXY7B","short_pith_number":"pith:75EIM3AW","schema_version":"1.0","canonical_sha256":"ff48866c1603594e033ad2cae3d6f8f84f40e58ec554914500c28adcfd1f8f5e","source":{"kind":"arxiv","id":"2205.08013","version":2},"attestation_state":"computed","paper":{"title":"Continual learning on 3D point clouds with random compressed rehearsal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Konrad Karanowski, Maciej Zamorski, Maciej Zi\\k{e}ba, Micha{\\l} Stypu{\\l}kowski, Tomasz Trzci\\'nski","submitted_at":"2022-05-16T22:59:52Z","abstract_excerpt":"Contemporary deep neural networks offer state-of-the-art results when applied to visual reasoning, e.g., in the context of 3D point cloud data. Point clouds are important datatype for precise modeling of three-dimensional environments, but effective processing of this type of data proves to be challenging. In the world of large, heavily-parameterized network architectures and continuously-streamed data, there is an increasing need for machine learning models that can be trained on additional data. Unfortunately, currently available models cannot fully leverage training on additional data witho"},"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":"2205.08013","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-16T22:59:52Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"c3da195b52629e6007088fad30bc2c723755dc6c6cc37be87ea492afba44718c","abstract_canon_sha256":"b28bd0031a9691e95107795672c42217db5add8a3146097835ce210cdb57aa90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:59.771115Z","signature_b64":"u343wn+RsZMBx0C0K1bX0ANahEmo3iYY5Vqi+k/PP/Er0+3FIVlZrZXwRdQU8lmOUfxqG7L/VWgvI6FInBx7Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff48866c1603594e033ad2cae3d6f8f84f40e58ec554914500c28adcfd1f8f5e","last_reissued_at":"2026-07-05T04:24:59.770690Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:59.770690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual learning on 3D point clouds with random compressed rehearsal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Konrad Karanowski, Maciej Zamorski, Maciej Zi\\k{e}ba, Micha{\\l} Stypu{\\l}kowski, Tomasz Trzci\\'nski","submitted_at":"2022-05-16T22:59:52Z","abstract_excerpt":"Contemporary deep neural networks offer state-of-the-art results when applied to visual reasoning, e.g., in the context of 3D point cloud data. Point clouds are important datatype for precise modeling of three-dimensional environments, but effective processing of this type of data proves to be challenging. In the world of large, heavily-parameterized network architectures and continuously-streamed data, there is an increasing need for machine learning models that can be trained on additional data. Unfortunately, currently available models cannot fully leverage training on additional data witho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.08013","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/2205.08013/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":"2205.08013","created_at":"2026-07-05T04:24:59.770752+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.08013v2","created_at":"2026-07-05T04:24:59.770752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.08013","created_at":"2026-07-05T04:24:59.770752+00:00"},{"alias_kind":"pith_short_12","alias_value":"75EIM3AWANMU","created_at":"2026-07-05T04:24:59.770752+00:00"},{"alias_kind":"pith_short_16","alias_value":"75EIM3AWANMU4AZ2","created_at":"2026-07-05T04:24:59.770752+00:00"},{"alias_kind":"pith_short_8","alias_value":"75EIM3AW","created_at":"2026-07-05T04:24:59.770752+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/75EIM3AWANMU4AZ22LFOHVXY7B","json":"https://pith.science/pith/75EIM3AWANMU4AZ22LFOHVXY7B.json","graph_json":"https://pith.science/api/pith-number/75EIM3AWANMU4AZ22LFOHVXY7B/graph.json","events_json":"https://pith.science/api/pith-number/75EIM3AWANMU4AZ22LFOHVXY7B/events.json","paper":"https://pith.science/paper/75EIM3AW"},"agent_actions":{"view_html":"https://pith.science/pith/75EIM3AWANMU4AZ22LFOHVXY7B","download_json":"https://pith.science/pith/75EIM3AWANMU4AZ22LFOHVXY7B.json","view_paper":"https://pith.science/paper/75EIM3AW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.08013&json=true","fetch_graph":"https://pith.science/api/pith-number/75EIM3AWANMU4AZ22LFOHVXY7B/graph.json","fetch_events":"https://pith.science/api/pith-number/75EIM3AWANMU4AZ22LFOHVXY7B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75EIM3AWANMU4AZ22LFOHVXY7B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75EIM3AWANMU4AZ22LFOHVXY7B/action/storage_attestation","attest_author":"https://pith.science/pith/75EIM3AWANMU4AZ22LFOHVXY7B/action/author_attestation","sign_citation":"https://pith.science/pith/75EIM3AWANMU4AZ22LFOHVXY7B/action/citation_signature","submit_replication":"https://pith.science/pith/75EIM3AWANMU4AZ22LFOHVXY7B/action/replication_record"}},"created_at":"2026-07-05T04:24:59.770752+00:00","updated_at":"2026-07-05T04:24:59.770752+00:00"}