{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:4JKHZ2J2NJSDR6Q6RHCKTE74JR","short_pith_number":"pith:4JKHZ2J2","canonical_record":{"source":{"id":"2003.11652","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-25T21:42:48Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"a7c98693a200859d225af215c2e2839e6c3af103b410403607386c689317fd89","abstract_canon_sha256":"d212f95f8ae6c00e38c7c24c935b5653d7fa9cb4d2a8788a323d065d4ca2f39d"},"schema_version":"1.0"},"canonical_sha256":"e2547ce93a6a6438fa1e89c4a993fc4c5b04fd65e79a2d4c85e154bc64ce8dd6","source":{"kind":"arxiv","id":"2003.11652","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.11652","created_at":"2026-07-05T00:50:46Z"},{"alias_kind":"arxiv_version","alias_value":"2003.11652v1","created_at":"2026-07-05T00:50:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.11652","created_at":"2026-07-05T00:50:46Z"},{"alias_kind":"pith_short_12","alias_value":"4JKHZ2J2NJSD","created_at":"2026-07-05T00:50:46Z"},{"alias_kind":"pith_short_16","alias_value":"4JKHZ2J2NJSDR6Q6","created_at":"2026-07-05T00:50:46Z"},{"alias_kind":"pith_short_8","alias_value":"4JKHZ2J2","created_at":"2026-07-05T00:50:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:4JKHZ2J2NJSDR6Q6RHCKTE74JR","target":"record","payload":{"canonical_record":{"source":{"id":"2003.11652","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-25T21:42:48Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"a7c98693a200859d225af215c2e2839e6c3af103b410403607386c689317fd89","abstract_canon_sha256":"d212f95f8ae6c00e38c7c24c935b5653d7fa9cb4d2a8788a323d065d4ca2f39d"},"schema_version":"1.0"},"canonical_sha256":"e2547ce93a6a6438fa1e89c4a993fc4c5b04fd65e79a2d4c85e154bc64ce8dd6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:50:46.303071Z","signature_b64":"uTsdjW1ClOeeKIcumMWrWFeZ1pmCaP9HDd8kV1adP8wPdmjVXObXVLePaQuidiI6PWoC6D/ZQvP2CZUtpc5sBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2547ce93a6a6438fa1e89c4a993fc4c5b04fd65e79a2d4c85e154bc64ce8dd6","last_reissued_at":"2026-07-05T00:50:46.302618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:50:46.302618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.11652","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:50:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H3zhHUn+u7jShh/UrHme+QIOhakMv4O0/o5UdKL5lE1ihgXtjW6QBhSj0MY49z1zWBZ7HXAq3pApazncEUODBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:40:00.107236Z"},"content_sha256":"72d5925a1871b2ce41e7af0581bd349fcf696af7d55ead173ab336ce8fcd4d5a","schema_version":"1.0","event_id":"sha256:72d5925a1871b2ce41e7af0581bd349fcf696af7d55ead173ab336ce8fcd4d5a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:4JKHZ2J2NJSDR6Q6RHCKTE74JR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"iTAML: An Incremental Task-Agnostic Meta-learning Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fahad Shahbaz Khan, Jathushan Rajasegaran, Mubarak Shah, Munawar Hayat, Salman Khan","submitted_at":"2020-03-25T21:42:48Z","abstract_excerpt":"Humans can continuously learn new knowledge as their experience grows. In contrast, previous learning in deep neural networks can quickly fade out when they are trained on a new task. In this paper, we hypothesize this problem can be avoided by learning a set of generalized parameters, that are neither specific to old nor new tasks. In this pursuit, we introduce a novel meta-learning approach that seeks to maintain an equilibrium between all the encountered tasks. This is ensured by a new meta-update rule which avoids catastrophic forgetting. In comparison to previous meta-learning techniques,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.11652","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/2003.11652/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":"2026-07-05T00:50:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0LD/1IqnFrXfq2y8mjD7xIyAEkDdB3oLHJt2CgUzjoiAd/W5cRgeohuReCyZcrvoLGoyog1xFmYBHvGar90UBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:40:00.107641Z"},"content_sha256":"96db0c281fd20b5d44716228b6d15c65e755e2fd69a77695d5be685770fdb482","schema_version":"1.0","event_id":"sha256:96db0c281fd20b5d44716228b6d15c65e755e2fd69a77695d5be685770fdb482"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4JKHZ2J2NJSDR6Q6RHCKTE74JR/bundle.json","state_url":"https://pith.science/pith/4JKHZ2J2NJSDR6Q6RHCKTE74JR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4JKHZ2J2NJSDR6Q6RHCKTE74JR/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":"2026-07-06T18:40:00Z","links":{"resolver":"https://pith.science/pith/4JKHZ2J2NJSDR6Q6RHCKTE74JR","bundle":"https://pith.science/pith/4JKHZ2J2NJSDR6Q6RHCKTE74JR/bundle.json","state":"https://pith.science/pith/4JKHZ2J2NJSDR6Q6RHCKTE74JR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4JKHZ2J2NJSDR6Q6RHCKTE74JR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4JKHZ2J2NJSDR6Q6RHCKTE74JR","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":"d212f95f8ae6c00e38c7c24c935b5653d7fa9cb4d2a8788a323d065d4ca2f39d","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-25T21:42:48Z","title_canon_sha256":"a7c98693a200859d225af215c2e2839e6c3af103b410403607386c689317fd89"},"schema_version":"1.0","source":{"id":"2003.11652","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.11652","created_at":"2026-07-05T00:50:46Z"},{"alias_kind":"arxiv_version","alias_value":"2003.11652v1","created_at":"2026-07-05T00:50:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.11652","created_at":"2026-07-05T00:50:46Z"},{"alias_kind":"pith_short_12","alias_value":"4JKHZ2J2NJSD","created_at":"2026-07-05T00:50:46Z"},{"alias_kind":"pith_short_16","alias_value":"4JKHZ2J2NJSDR6Q6","created_at":"2026-07-05T00:50:46Z"},{"alias_kind":"pith_short_8","alias_value":"4JKHZ2J2","created_at":"2026-07-05T00:50:46Z"}],"graph_snapshots":[{"event_id":"sha256:96db0c281fd20b5d44716228b6d15c65e755e2fd69a77695d5be685770fdb482","target":"graph","created_at":"2026-07-05T00:50:46Z","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/2003.11652/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans can continuously learn new knowledge as their experience grows. In contrast, previous learning in deep neural networks can quickly fade out when they are trained on a new task. In this paper, we hypothesize this problem can be avoided by learning a set of generalized parameters, that are neither specific to old nor new tasks. In this pursuit, we introduce a novel meta-learning approach that seeks to maintain an equilibrium between all the encountered tasks. This is ensured by a new meta-update rule which avoids catastrophic forgetting. In comparison to previous meta-learning techniques,","authors_text":"Fahad Shahbaz Khan, Jathushan Rajasegaran, Mubarak Shah, Munawar Hayat, Salman Khan","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-25T21:42:48Z","title":"iTAML: An Incremental Task-Agnostic Meta-learning Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.11652","kind":"arxiv","version":1},"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":"sha256:72d5925a1871b2ce41e7af0581bd349fcf696af7d55ead173ab336ce8fcd4d5a","target":"record","created_at":"2026-07-05T00:50:46Z","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":"d212f95f8ae6c00e38c7c24c935b5653d7fa9cb4d2a8788a323d065d4ca2f39d","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-25T21:42:48Z","title_canon_sha256":"a7c98693a200859d225af215c2e2839e6c3af103b410403607386c689317fd89"},"schema_version":"1.0","source":{"id":"2003.11652","kind":"arxiv","version":1}},"canonical_sha256":"e2547ce93a6a6438fa1e89c4a993fc4c5b04fd65e79a2d4c85e154bc64ce8dd6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2547ce93a6a6438fa1e89c4a993fc4c5b04fd65e79a2d4c85e154bc64ce8dd6","first_computed_at":"2026-07-05T00:50:46.302618Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:50:46.302618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uTsdjW1ClOeeKIcumMWrWFeZ1pmCaP9HDd8kV1adP8wPdmjVXObXVLePaQuidiI6PWoC6D/ZQvP2CZUtpc5sBA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:50:46.303071Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.11652","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72d5925a1871b2ce41e7af0581bd349fcf696af7d55ead173ab336ce8fcd4d5a","sha256:96db0c281fd20b5d44716228b6d15c65e755e2fd69a77695d5be685770fdb482"],"state_sha256":"7881f32a32cff374bf8c9218f62de9078290082257a93f501e1b4b1bbc982aec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uSLB/jbPKotwVcW15fAKV6XWBle3uKlCRYvt7ok9lvbV133f5PWOMlBhAlfTA5EUCUNGAPMhM33ra1U728PFBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:40:00.109710Z","bundle_sha256":"f76f1f276e9dfd79cfe225b3af1ccfed8fc699a39293ba01d2e09dfbce58f891"}}