{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IBCSQI3C44KIRADMSK3EZ7CVDH","short_pith_number":"pith:IBCSQI3C","canonical_record":{"source":{"id":"2604.27031","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-29T15:04:25Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"065bb2fe6ab368e1b639696141d7ef12c8951f1d0d331c2b38659fb2fc13a165","abstract_canon_sha256":"98257b729fda602b2e90f500fa2eaaca4ff8c2ca67a0878703e6256590bd6421"},"schema_version":"1.0"},"canonical_sha256":"4045282362e71488806c92b64cfc5519e3aa80f8b46bdf94ef7423bb2274551c","source":{"kind":"arxiv","id":"2604.27031","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.27031","created_at":"2026-07-17T01:20:50Z"},{"alias_kind":"arxiv_version","alias_value":"2604.27031v2","created_at":"2026-07-17T01:20:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.27031","created_at":"2026-07-17T01:20:50Z"},{"alias_kind":"pith_short_12","alias_value":"IBCSQI3C44KI","created_at":"2026-07-17T01:20:50Z"},{"alias_kind":"pith_short_16","alias_value":"IBCSQI3C44KIRADM","created_at":"2026-07-17T01:20:50Z"},{"alias_kind":"pith_short_8","alias_value":"IBCSQI3C","created_at":"2026-07-17T01:20:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IBCSQI3C44KIRADMSK3EZ7CVDH","target":"record","payload":{"canonical_record":{"source":{"id":"2604.27031","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-29T15:04:25Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"065bb2fe6ab368e1b639696141d7ef12c8951f1d0d331c2b38659fb2fc13a165","abstract_canon_sha256":"98257b729fda602b2e90f500fa2eaaca4ff8c2ca67a0878703e6256590bd6421"},"schema_version":"1.0"},"canonical_sha256":"4045282362e71488806c92b64cfc5519e3aa80f8b46bdf94ef7423bb2274551c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:20:50.438207Z","signature_b64":"i9p7kbn2baYFZoud2P35HXpywv+covlpwuqVrawb36f/2G66SaPt1KNB6IcnYUmZJoxmGmrQ/VzMWh4Fat3BDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4045282362e71488806c92b64cfc5519e3aa80f8b46bdf94ef7423bb2274551c","last_reissued_at":"2026-07-17T01:20:50.437417Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:20:50.437417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.27031","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":"2026-07-17T01:20:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mhpwXIyHhRUFjepTGXHaEM/GWbNvTQJ0Q/Y3mBcy+2GyDVIrPD8a9S/e752o24q3B7cWl1SW6Dzuys3r6VDADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:38:32.499124Z"},"content_sha256":"77353eb71f5d01048f654ad3fd7715f13c7489e484dc16bf4355cfd3e4f4afaf","schema_version":"1.0","event_id":"sha256:77353eb71f5d01048f654ad3fd7715f13c7489e484dc16bf4355cfd3e4f4afaf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IBCSQI3C44KIRADMSK3EZ7CVDH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NORACL: Neurogenesis for Oracle-free Resource-Adaptive Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"NORACL grows neurons on demand to match oracle-sized static networks in continual learning accuracy while using fewer parameters overall.","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Christian Metzner, Karthik Charan Raghunathan, Laura Kriener, Melika Payvand","submitted_at":"2026-04-29T15:04:25Z","abstract_excerpt":"In a continual learning setting, we require a model to be plastic enough to learn a new task and stable enough to not disturb previously learned capabilities. We argue that this dilemma has an architectural root. A finite network has limited representational and plastic resources, yet the required capacity depends on properties of the future task stream that are unknown: how many tasks will be encountered, and how much they overlap in feature space. Regularization-based methods preserve past knowledge within fixed-capacity architectures and therefore implicitly rely on an oracle architecture s"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Across all settings, NORACL achieves final average accuracies that are better than or on par with oracle-provisioned static baselines while using fewer parameters.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the two complementary saturation signals reliably detect when representational or plasticity capacity is exhausted and that selective neuronal growth preserves stability without introducing new interference or optimization issues.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"NORACL dynamically grows network capacity via neurogenesis-inspired signals to achieve oracle-level continual learning performance without pre-specifying architecture size.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"NORACL grows neurons on demand to match oracle-sized static networks in continual learning accuracy while using fewer parameters overall.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"16489e33e9e09ced7f67c6dc0dfeed7a92f3bfa51d36e3ba0403008e3601d3bc"},"source":{"id":"2604.27031","kind":"arxiv","version":2},"verdict":{"id":"5c49587e-a27b-44e0-81c6-7effda560d08","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T13:31:32.134191Z","strongest_claim":"Across all settings, NORACL achieves final average accuracies that are better than or on par with oracle-provisioned static baselines while using fewer parameters.","one_line_summary":"NORACL dynamically grows network capacity via neurogenesis-inspired signals to achieve oracle-level continual learning performance without pre-specifying architecture size.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the two complementary saturation signals reliably detect when representational or plasticity capacity is exhausted and that selective neuronal growth preserves stability without introducing new interference or optimization issues.","pith_extraction_headline":"NORACL grows neurons on demand to match oracle-sized static networks in continual learning accuracy while using fewer parameters overall."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.27031/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T23:42:13.568531Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T19:51:50.168796Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"37b11f2386e63769edd96bac1a943f4e9faedb9a733547480509220219e86e39"},"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":"5c49587e-a27b-44e0-81c6-7effda560d08"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-17T01:20:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sO3qh7cl9UrdG63EotHvyxJRvaBqe0AKv1ZjtdcrUhYkZ7wE7/WbXDBaNZi/8soaWb/rqWELG3BF3UU4/yAQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:38:32.500441Z"},"content_sha256":"0260be433adcded40fef2cd6f6fa0d236084409af7cde2e70785600d10e3aa32","schema_version":"1.0","event_id":"sha256:0260be433adcded40fef2cd6f6fa0d236084409af7cde2e70785600d10e3aa32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IBCSQI3C44KIRADMSK3EZ7CVDH/bundle.json","state_url":"https://pith.science/pith/IBCSQI3C44KIRADMSK3EZ7CVDH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IBCSQI3C44KIRADMSK3EZ7CVDH/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":"2026-08-07T03:38:32Z","links":{"resolver":"https://pith.science/pith/IBCSQI3C44KIRADMSK3EZ7CVDH","bundle":"https://pith.science/pith/IBCSQI3C44KIRADMSK3EZ7CVDH/bundle.json","state":"https://pith.science/pith/IBCSQI3C44KIRADMSK3EZ7CVDH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IBCSQI3C44KIRADMSK3EZ7CVDH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IBCSQI3C44KIRADMSK3EZ7CVDH","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":"98257b729fda602b2e90f500fa2eaaca4ff8c2ca67a0878703e6256590bd6421","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-29T15:04:25Z","title_canon_sha256":"065bb2fe6ab368e1b639696141d7ef12c8951f1d0d331c2b38659fb2fc13a165"},"schema_version":"1.0","source":{"id":"2604.27031","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.27031","created_at":"2026-07-17T01:20:50Z"},{"alias_kind":"arxiv_version","alias_value":"2604.27031v2","created_at":"2026-07-17T01:20:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.27031","created_at":"2026-07-17T01:20:50Z"},{"alias_kind":"pith_short_12","alias_value":"IBCSQI3C44KI","created_at":"2026-07-17T01:20:50Z"},{"alias_kind":"pith_short_16","alias_value":"IBCSQI3C44KIRADM","created_at":"2026-07-17T01:20:50Z"},{"alias_kind":"pith_short_8","alias_value":"IBCSQI3C","created_at":"2026-07-17T01:20:50Z"}],"graph_snapshots":[{"event_id":"sha256:0260be433adcded40fef2cd6f6fa0d236084409af7cde2e70785600d10e3aa32","target":"graph","created_at":"2026-07-17T01:20:50Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Across all settings, NORACL achieves final average accuracies that are better than or on par with oracle-provisioned static baselines while using fewer parameters."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the two complementary saturation signals reliably detect when representational or plasticity capacity is exhausted and that selective neuronal growth preserves stability without introducing new interference or optimization issues."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"NORACL dynamically grows network capacity via neurogenesis-inspired signals to achieve oracle-level continual learning performance without pre-specifying architecture size."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"NORACL grows neurons on demand to match oracle-sized static networks in continual learning accuracy while using fewer parameters overall."}],"snapshot_sha256":"16489e33e9e09ced7f67c6dc0dfeed7a92f3bfa51d36e3ba0403008e3601d3bc"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T23:42:13.568531Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T19:51:50.168796Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.27031/integrity.json","findings":[],"snapshot_sha256":"37b11f2386e63769edd96bac1a943f4e9faedb9a733547480509220219e86e39","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In a continual learning setting, we require a model to be plastic enough to learn a new task and stable enough to not disturb previously learned capabilities. We argue that this dilemma has an architectural root. A finite network has limited representational and plastic resources, yet the required capacity depends on properties of the future task stream that are unknown: how many tasks will be encountered, and how much they overlap in feature space. Regularization-based methods preserve past knowledge within fixed-capacity architectures and therefore implicitly rely on an oracle architecture s","authors_text":"Christian Metzner, Karthik Charan Raghunathan, Laura Kriener, Melika Payvand","cross_cats":["cs.AI","cs.NE"],"headline":"NORACL grows neurons on demand to match oracle-sized static networks in continual learning accuracy while using fewer parameters overall.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-29T15:04:25Z","title":"NORACL: Neurogenesis for Oracle-free Resource-Adaptive Continual Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.27031","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-07T13:31:32.134191Z","id":"5c49587e-a27b-44e0-81c6-7effda560d08","model_set":{"reader":"grok-4.3"},"one_line_summary":"NORACL dynamically grows network capacity via neurogenesis-inspired signals to achieve oracle-level continual learning performance without pre-specifying architecture size.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"NORACL grows neurons on demand to match oracle-sized static networks in continual learning accuracy while using fewer parameters overall.","strongest_claim":"Across all settings, NORACL achieves final average accuracies that are better than or on par with oracle-provisioned static baselines while using fewer parameters.","weakest_assumption":"That the two complementary saturation signals reliably detect when representational or plasticity capacity is exhausted and that selective neuronal growth preserves stability without introducing new interference or optimization issues."}},"verdict_id":"5c49587e-a27b-44e0-81c6-7effda560d08"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:77353eb71f5d01048f654ad3fd7715f13c7489e484dc16bf4355cfd3e4f4afaf","target":"record","created_at":"2026-07-17T01:20:50Z","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":"98257b729fda602b2e90f500fa2eaaca4ff8c2ca67a0878703e6256590bd6421","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-29T15:04:25Z","title_canon_sha256":"065bb2fe6ab368e1b639696141d7ef12c8951f1d0d331c2b38659fb2fc13a165"},"schema_version":"1.0","source":{"id":"2604.27031","kind":"arxiv","version":2}},"canonical_sha256":"4045282362e71488806c92b64cfc5519e3aa80f8b46bdf94ef7423bb2274551c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4045282362e71488806c92b64cfc5519e3aa80f8b46bdf94ef7423bb2274551c","first_computed_at":"2026-07-17T01:20:50.437417Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T01:20:50.437417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i9p7kbn2baYFZoud2P35HXpywv+covlpwuqVrawb36f/2G66SaPt1KNB6IcnYUmZJoxmGmrQ/VzMWh4Fat3BDg==","signature_status":"signed_v1","signed_at":"2026-07-17T01:20:50.438207Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.27031","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77353eb71f5d01048f654ad3fd7715f13c7489e484dc16bf4355cfd3e4f4afaf","sha256:0260be433adcded40fef2cd6f6fa0d236084409af7cde2e70785600d10e3aa32"],"state_sha256":"396990754c07147af5b6caee3e0fefbee5a2828c0ba079074aa36740eb42c89c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LKfW6f7Bbd8wB0O5HTjXkaGstsuwvk4h3o5jfwaJOcKhruafXxdhWtWOmYj3HC/g7ONQf7KPVi06MaLQai4TDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T03:38:32.520105Z","bundle_sha256":"5b5847ab517c5824b684e2d418c19ea0365721956a5186d00f37ab817cbdcec0"}}