{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:SUEKKN5TZBPTMRLD3JFQ5IESTU","short_pith_number":"pith:SUEKKN5T","canonical_record":{"source":{"id":"2203.02026","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-03T21:23:08Z","cross_cats_sorted":[],"title_canon_sha256":"960bad7b3d8b8086b186889fbf6c25abb82a6ef0b6607c01c1ab3e544a040e5b","abstract_canon_sha256":"a60d739d9026cf9a53202bc0df150a87230538b097558ee35e5190a610fc75b2"},"schema_version":"1.0"},"canonical_sha256":"9508a537b3c85f364563da4b0ea0929d1a990b1d86a30ea2abe7e395c5ebc5ef","source":{"kind":"arxiv","id":"2203.02026","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02026","created_at":"2026-07-05T05:13:32Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02026v2","created_at":"2026-07-05T05:13:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02026","created_at":"2026-07-05T05:13:32Z"},{"alias_kind":"pith_short_12","alias_value":"SUEKKN5TZBPT","created_at":"2026-07-05T05:13:32Z"},{"alias_kind":"pith_short_16","alias_value":"SUEKKN5TZBPTMRLD","created_at":"2026-07-05T05:13:32Z"},{"alias_kind":"pith_short_8","alias_value":"SUEKKN5T","created_at":"2026-07-05T05:13:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:SUEKKN5TZBPTMRLD3JFQ5IESTU","target":"record","payload":{"canonical_record":{"source":{"id":"2203.02026","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-03T21:23:08Z","cross_cats_sorted":[],"title_canon_sha256":"960bad7b3d8b8086b186889fbf6c25abb82a6ef0b6607c01c1ab3e544a040e5b","abstract_canon_sha256":"a60d739d9026cf9a53202bc0df150a87230538b097558ee35e5190a610fc75b2"},"schema_version":"1.0"},"canonical_sha256":"9508a537b3c85f364563da4b0ea0929d1a990b1d86a30ea2abe7e395c5ebc5ef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:32.116386Z","signature_b64":"xh17LrNpNxB3nUXA+aXtWlaVBsyGVW/PngedJJCPru4nD+nyNYZWBI6nizOsJ2Vxi1i8/RRT7NcOckKVmHhcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9508a537b3c85f364563da4b0ea0929d1a990b1d86a30ea2abe7e395c5ebc5ef","last_reissued_at":"2026-07-05T05:13:32.115785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:32.115785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.02026","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:13:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1KdpbR2d017K0qnDsq1qrloyfIfGvZ22FVzYowKXezx41vKnfHl7Dc5cjEFqM6jrmUEmeOEAZj0XDmbnn0zDDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:31:34.620294Z"},"content_sha256":"3dd19f19f3fa6ec4392feecf100653670908b16bacb1ce45102608e8353141eb","schema_version":"1.0","event_id":"sha256:3dd19f19f3fa6ec4392feecf100653670908b16bacb1ce45102608e8353141eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:SUEKKN5TZBPTMRLD3JFQ5IESTU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provable and Efficient Continual Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mingchen Li, M. Salman Asif, Samet Oymak, Yingcong Li","submitted_at":"2022-03-03T21:23:08Z","abstract_excerpt":"In continual learning (CL), the goal is to design models that can learn a sequence of tasks without catastrophic forgetting. While there is a rich set of techniques for CL, relatively little understanding exists on how representations built by previous tasks benefit new tasks that are added to the network. To address this, we study the problem of continual representation learning (CRL) where we learn an evolving representation as new tasks arrive. Focusing on zero-forgetting methods where tasks are embedded in subnetworks (e.g., PackNet), we first provide experiments demonstrating CRL can sign"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02026","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/2203.02026/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:13:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C6QxfCmbuHqPa1leME1smBODuC21HstZz0JLLL31mnMSb7uya1FKaOgqD+MjxxtRHgnw7cBtYgvw692t+q9vAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:31:34.620788Z"},"content_sha256":"f22854f82ca4322a99bea49af2596c4bb8968559a8b7a4c1bf34a8e326629de4","schema_version":"1.0","event_id":"sha256:f22854f82ca4322a99bea49af2596c4bb8968559a8b7a4c1bf34a8e326629de4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SUEKKN5TZBPTMRLD3JFQ5IESTU/bundle.json","state_url":"https://pith.science/pith/SUEKKN5TZBPTMRLD3JFQ5IESTU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SUEKKN5TZBPTMRLD3JFQ5IESTU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T05:31:34Z","links":{"resolver":"https://pith.science/pith/SUEKKN5TZBPTMRLD3JFQ5IESTU","bundle":"https://pith.science/pith/SUEKKN5TZBPTMRLD3JFQ5IESTU/bundle.json","state":"https://pith.science/pith/SUEKKN5TZBPTMRLD3JFQ5IESTU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SUEKKN5TZBPTMRLD3JFQ5IESTU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SUEKKN5TZBPTMRLD3JFQ5IESTU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a60d739d9026cf9a53202bc0df150a87230538b097558ee35e5190a610fc75b2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-03T21:23:08Z","title_canon_sha256":"960bad7b3d8b8086b186889fbf6c25abb82a6ef0b6607c01c1ab3e544a040e5b"},"schema_version":"1.0","source":{"id":"2203.02026","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02026","created_at":"2026-07-05T05:13:32Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02026v2","created_at":"2026-07-05T05:13:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02026","created_at":"2026-07-05T05:13:32Z"},{"alias_kind":"pith_short_12","alias_value":"SUEKKN5TZBPT","created_at":"2026-07-05T05:13:32Z"},{"alias_kind":"pith_short_16","alias_value":"SUEKKN5TZBPTMRLD","created_at":"2026-07-05T05:13:32Z"},{"alias_kind":"pith_short_8","alias_value":"SUEKKN5T","created_at":"2026-07-05T05:13:32Z"}],"graph_snapshots":[{"event_id":"sha256:f22854f82ca4322a99bea49af2596c4bb8968559a8b7a4c1bf34a8e326629de4","target":"graph","created_at":"2026-07-05T05:13:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2203.02026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In continual learning (CL), the goal is to design models that can learn a sequence of tasks without catastrophic forgetting. While there is a rich set of techniques for CL, relatively little understanding exists on how representations built by previous tasks benefit new tasks that are added to the network. To address this, we study the problem of continual representation learning (CRL) where we learn an evolving representation as new tasks arrive. Focusing on zero-forgetting methods where tasks are embedded in subnetworks (e.g., PackNet), we first provide experiments demonstrating CRL can sign","authors_text":"Mingchen Li, M. Salman Asif, Samet Oymak, Yingcong Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-03T21:23:08Z","title":"Provable and Efficient Continual Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02026","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3dd19f19f3fa6ec4392feecf100653670908b16bacb1ce45102608e8353141eb","target":"record","created_at":"2026-07-05T05:13:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a60d739d9026cf9a53202bc0df150a87230538b097558ee35e5190a610fc75b2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-03T21:23:08Z","title_canon_sha256":"960bad7b3d8b8086b186889fbf6c25abb82a6ef0b6607c01c1ab3e544a040e5b"},"schema_version":"1.0","source":{"id":"2203.02026","kind":"arxiv","version":2}},"canonical_sha256":"9508a537b3c85f364563da4b0ea0929d1a990b1d86a30ea2abe7e395c5ebc5ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9508a537b3c85f364563da4b0ea0929d1a990b1d86a30ea2abe7e395c5ebc5ef","first_computed_at":"2026-07-05T05:13:32.115785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:13:32.115785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xh17LrNpNxB3nUXA+aXtWlaVBsyGVW/PngedJJCPru4nD+nyNYZWBI6nizOsJ2Vxi1i8/RRT7NcOckKVmHhcBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:13:32.116386Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.02026","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dd19f19f3fa6ec4392feecf100653670908b16bacb1ce45102608e8353141eb","sha256:f22854f82ca4322a99bea49af2596c4bb8968559a8b7a4c1bf34a8e326629de4"],"state_sha256":"504b38dc853dc6b1129e386ee68fd8823dae02ba6f70c923682732390cc20321"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RGlZIshaHVQVmm6QGpPMNDKwIxbvQIw3WH54RohVIXMOakK2vTHy988PSNUNSF1BNCpJaRKdPMYluGRlnAaLBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:31:34.624623Z","bundle_sha256":"3bc1ff72d504d10c46f2250b70e56a256bb0306ca2003f493c1e73aee79e09ae"}}