{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:HEVGBUR46HSNUNIHYI7JWGBCIU","short_pith_number":"pith:HEVGBUR4","canonical_record":{"source":{"id":"2311.18598","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-30T14:45:51Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"8cf84008dfbca7e13f7132c24ac6b080be2c71f5df1021f8a2d48b38bb1b7200","abstract_canon_sha256":"bdc6e790e8304255a05f044580b94dac705cecf9b822bc9158c255a97c91933b"},"schema_version":"1.0"},"canonical_sha256":"392a60d23cf1e4da3507c23e9b18224506ed6a4acae37804693381437d59ad09","source":{"kind":"arxiv","id":"2311.18598","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.18598","created_at":"2026-07-05T07:59:19Z"},{"alias_kind":"arxiv_version","alias_value":"2311.18598v2","created_at":"2026-07-05T07:59:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18598","created_at":"2026-07-05T07:59:19Z"},{"alias_kind":"pith_short_12","alias_value":"HEVGBUR46HSN","created_at":"2026-07-05T07:59:19Z"},{"alias_kind":"pith_short_16","alias_value":"HEVGBUR46HSNUNIH","created_at":"2026-07-05T07:59:19Z"},{"alias_kind":"pith_short_8","alias_value":"HEVGBUR4","created_at":"2026-07-05T07:59:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:HEVGBUR46HSNUNIHYI7JWGBCIU","target":"record","payload":{"canonical_record":{"source":{"id":"2311.18598","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-30T14:45:51Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"8cf84008dfbca7e13f7132c24ac6b080be2c71f5df1021f8a2d48b38bb1b7200","abstract_canon_sha256":"bdc6e790e8304255a05f044580b94dac705cecf9b822bc9158c255a97c91933b"},"schema_version":"1.0"},"canonical_sha256":"392a60d23cf1e4da3507c23e9b18224506ed6a4acae37804693381437d59ad09","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:19.834488Z","signature_b64":"9zE6NmIZ6Axk9VstcB8O3Q54BhRCWjSOSc3ThroCQZWFgrMfYyRctd6XDRxZRgdVlhP4GDytfpKBDmQTfjpgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"392a60d23cf1e4da3507c23e9b18224506ed6a4acae37804693381437d59ad09","last_reissued_at":"2026-07-05T07:59:19.833911Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:19.833911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.18598","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":"2026-07-05T07:59:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g1vERxx7FKQCujQvUL0+pGmHKc+glLBT/TV9fBXnb8T+fY0ZHJjnT4b6IC5BBBRBV8pTUIzfytvc9TqOSuIuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T02:12:32.832033Z"},"content_sha256":"8f2f735b730c1a202751b0f250480fb0663e5c97e3d16ddf81575a1e0c3e5223","schema_version":"1.0","event_id":"sha256:8f2f735b730c1a202751b0f250480fb0663e5c97e3d16ddf81575a1e0c3e5223"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:HEVGBUR46HSNUNIHYI7JWGBCIU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalisable Agents for Neural Network Optimisation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Arnu Pretorius, Benjamin Rosman, Callum Rhys Tilbury, Kale-ab Tessera, Omayma Mahjoub, Ruan de Kock, Sara Hooker, Sasha Abramowitz","submitted_at":"2023-11-30T14:45:51Z","abstract_excerpt":"Optimising deep neural networks is a challenging task due to complex training dynamics, high computational requirements, and long training times. To address this difficulty, we propose the framework of Generalisable Agents for Neural Network Optimisation (GANNO) -- a multi-agent reinforcement learning (MARL) approach that learns to improve neural network optimisation by dynamically and responsively scheduling hyperparameters during training. GANNO utilises an agent per layer that observes localised network dynamics and accordingly takes actions to adjust these dynamics at a layerwise level to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18598","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/2311.18598/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":"2026-07-05T07:59:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6zHzwzu0g8Y/Y044u0JG4LmrHSrw3kv7+7Rj5GUneJ9mdhbgJee5DQLBrNQUH9MSfr0gdo6gqBIJUzVH8F79CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T02:12:32.832424Z"},"content_sha256":"29469461400078a0a71fe4e3e599df80070b0ced7f52578ca219d497e1354c65","schema_version":"1.0","event_id":"sha256:29469461400078a0a71fe4e3e599df80070b0ced7f52578ca219d497e1354c65"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HEVGBUR46HSNUNIHYI7JWGBCIU/bundle.json","state_url":"https://pith.science/pith/HEVGBUR46HSNUNIHYI7JWGBCIU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HEVGBUR46HSNUNIHYI7JWGBCIU/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":"2026-07-08T02:12:32Z","links":{"resolver":"https://pith.science/pith/HEVGBUR46HSNUNIHYI7JWGBCIU","bundle":"https://pith.science/pith/HEVGBUR46HSNUNIHYI7JWGBCIU/bundle.json","state":"https://pith.science/pith/HEVGBUR46HSNUNIHYI7JWGBCIU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HEVGBUR46HSNUNIHYI7JWGBCIU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HEVGBUR46HSNUNIHYI7JWGBCIU","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":"bdc6e790e8304255a05f044580b94dac705cecf9b822bc9158c255a97c91933b","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-30T14:45:51Z","title_canon_sha256":"8cf84008dfbca7e13f7132c24ac6b080be2c71f5df1021f8a2d48b38bb1b7200"},"schema_version":"1.0","source":{"id":"2311.18598","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.18598","created_at":"2026-07-05T07:59:19Z"},{"alias_kind":"arxiv_version","alias_value":"2311.18598v2","created_at":"2026-07-05T07:59:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18598","created_at":"2026-07-05T07:59:19Z"},{"alias_kind":"pith_short_12","alias_value":"HEVGBUR46HSN","created_at":"2026-07-05T07:59:19Z"},{"alias_kind":"pith_short_16","alias_value":"HEVGBUR46HSNUNIH","created_at":"2026-07-05T07:59:19Z"},{"alias_kind":"pith_short_8","alias_value":"HEVGBUR4","created_at":"2026-07-05T07:59:19Z"}],"graph_snapshots":[{"event_id":"sha256:29469461400078a0a71fe4e3e599df80070b0ced7f52578ca219d497e1354c65","target":"graph","created_at":"2026-07-05T07:59:19Z","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/2311.18598/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimising deep neural networks is a challenging task due to complex training dynamics, high computational requirements, and long training times. To address this difficulty, we propose the framework of Generalisable Agents for Neural Network Optimisation (GANNO) -- a multi-agent reinforcement learning (MARL) approach that learns to improve neural network optimisation by dynamically and responsively scheduling hyperparameters during training. GANNO utilises an agent per layer that observes localised network dynamics and accordingly takes actions to adjust these dynamics at a layerwise level to ","authors_text":"Arnu Pretorius, Benjamin Rosman, Callum Rhys Tilbury, Kale-ab Tessera, Omayma Mahjoub, Ruan de Kock, Sara Hooker, Sasha Abramowitz","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-30T14:45:51Z","title":"Generalisable Agents for Neural Network Optimisation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18598","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":"sha256:8f2f735b730c1a202751b0f250480fb0663e5c97e3d16ddf81575a1e0c3e5223","target":"record","created_at":"2026-07-05T07:59:19Z","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":"bdc6e790e8304255a05f044580b94dac705cecf9b822bc9158c255a97c91933b","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-30T14:45:51Z","title_canon_sha256":"8cf84008dfbca7e13f7132c24ac6b080be2c71f5df1021f8a2d48b38bb1b7200"},"schema_version":"1.0","source":{"id":"2311.18598","kind":"arxiv","version":2}},"canonical_sha256":"392a60d23cf1e4da3507c23e9b18224506ed6a4acae37804693381437d59ad09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"392a60d23cf1e4da3507c23e9b18224506ed6a4acae37804693381437d59ad09","first_computed_at":"2026-07-05T07:59:19.833911Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:19.833911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9zE6NmIZ6Axk9VstcB8O3Q54BhRCWjSOSc3ThroCQZWFgrMfYyRctd6XDRxZRgdVlhP4GDytfpKBDmQTfjpgCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:19.834488Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.18598","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f2f735b730c1a202751b0f250480fb0663e5c97e3d16ddf81575a1e0c3e5223","sha256:29469461400078a0a71fe4e3e599df80070b0ced7f52578ca219d497e1354c65"],"state_sha256":"2ebe9a4343c8bee626fe3682b620bbc124a68dfcc3657b9bf3e4a0edadea7e44"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VwyyyalkZWrq+9vUuAXPfQ7mpxts6p6aeScvUPJWVEdWEiaW/+J6tdzxFqvdhpjTy+PmuHuTUhf+drA/wMn8DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T02:12:32.834807Z","bundle_sha256":"1d4272539fa4ddb9e63d25196b29e7d20853f9b8505a079877e377ee4c578850"}}