{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:H3REZGFFYDTSCMQGTSIHT7RXEO","short_pith_number":"pith:H3REZGFF","schema_version":"1.0","canonical_sha256":"3ee24c98a5c0e72132069c9079fe3723b5e22837f50ad23461773f342c5146a5","source":{"kind":"arxiv","id":"2112.03321","version":1},"attestation_state":"computed","paper":{"title":"Noether Networks: Meta-Learning Useful Conserved Quantities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Allan Zhou, Chelsea Finn, Dylan Doblar, Ferran Alet, Joshua Tenenbaum, Kenji Kawaguchi","submitted_at":"2021-12-06T19:27:43Z","abstract_excerpt":"Progress in machine learning (ML) stems from a combination of data availability, computational resources, and an appropriate encoding of inductive biases. Useful biases often exploit symmetries in the prediction problem, such as convolutional networks relying on translation equivariance. Automatically discovering these useful symmetries holds the potential to greatly improve the performance of ML systems, but still remains a challenge. In this work, we focus on sequential prediction problems and take inspiration from Noether's theorem to reduce the problem of finding inductive biases to meta-l"},"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":"2112.03321","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-06T19:27:43Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"697e27d063124e41bb0c1aaf4cc0bf644c69b878e328a258ece7898dd8b641ed","abstract_canon_sha256":"1156bb5bbc5ffd22e392c5bc2aaa1a7d13f86aac12977ea6df10a6513c73fea4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:44.322796Z","signature_b64":"EufE9V9RPdkHTnZ6OIuJb8PNGPOdKhNqD83MtV3Q7sgX4lCyF5qpyDETn3lySVu1J4WZjibGuw3XzjOYRvmQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ee24c98a5c0e72132069c9079fe3723b5e22837f50ad23461773f342c5146a5","last_reissued_at":"2026-07-05T03:38:44.322338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:44.322338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Noether Networks: Meta-Learning Useful Conserved Quantities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Allan Zhou, Chelsea Finn, Dylan Doblar, Ferran Alet, Joshua Tenenbaum, Kenji Kawaguchi","submitted_at":"2021-12-06T19:27:43Z","abstract_excerpt":"Progress in machine learning (ML) stems from a combination of data availability, computational resources, and an appropriate encoding of inductive biases. Useful biases often exploit symmetries in the prediction problem, such as convolutional networks relying on translation equivariance. Automatically discovering these useful symmetries holds the potential to greatly improve the performance of ML systems, but still remains a challenge. In this work, we focus on sequential prediction problems and take inspiration from Noether's theorem to reduce the problem of finding inductive biases to meta-l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03321","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/2112.03321/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":"2112.03321","created_at":"2026-07-05T03:38:44.322401+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.03321v1","created_at":"2026-07-05T03:38:44.322401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03321","created_at":"2026-07-05T03:38:44.322401+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3REZGFFYDTS","created_at":"2026-07-05T03:38:44.322401+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3REZGFFYDTSCMQG","created_at":"2026-07-05T03:38:44.322401+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3REZGFF","created_at":"2026-07-05T03:38:44.322401+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09471","citing_title":"The Statistical Cost of Adaptation in Multi-Source Transfer Learning","ref_index":143,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H3REZGFFYDTSCMQGTSIHT7RXEO","json":"https://pith.science/pith/H3REZGFFYDTSCMQGTSIHT7RXEO.json","graph_json":"https://pith.science/api/pith-number/H3REZGFFYDTSCMQGTSIHT7RXEO/graph.json","events_json":"https://pith.science/api/pith-number/H3REZGFFYDTSCMQGTSIHT7RXEO/events.json","paper":"https://pith.science/paper/H3REZGFF"},"agent_actions":{"view_html":"https://pith.science/pith/H3REZGFFYDTSCMQGTSIHT7RXEO","download_json":"https://pith.science/pith/H3REZGFFYDTSCMQGTSIHT7RXEO.json","view_paper":"https://pith.science/paper/H3REZGFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.03321&json=true","fetch_graph":"https://pith.science/api/pith-number/H3REZGFFYDTSCMQGTSIHT7RXEO/graph.json","fetch_events":"https://pith.science/api/pith-number/H3REZGFFYDTSCMQGTSIHT7RXEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3REZGFFYDTSCMQGTSIHT7RXEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3REZGFFYDTSCMQGTSIHT7RXEO/action/storage_attestation","attest_author":"https://pith.science/pith/H3REZGFFYDTSCMQGTSIHT7RXEO/action/author_attestation","sign_citation":"https://pith.science/pith/H3REZGFFYDTSCMQGTSIHT7RXEO/action/citation_signature","submit_replication":"https://pith.science/pith/H3REZGFFYDTSCMQGTSIHT7RXEO/action/replication_record"}},"created_at":"2026-07-05T03:38:44.322401+00:00","updated_at":"2026-07-05T03:38:44.322401+00:00"}