{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HKPVBG3LCJNCFXLZHTBIL4CVTL","short_pith_number":"pith:HKPVBG3L","schema_version":"1.0","canonical_sha256":"3a9f509b6b125a22dd793cc285f0559ac8157d150735c9279b21fa88e586ebf2","source":{"kind":"arxiv","id":"2404.05782","version":1},"attestation_state":"computed","paper":{"title":"Dynamical stability and chaos in artificial neural network trajectories along training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","nlin.CD","physics.data-an"],"primary_cat":"cs.LG","authors_text":"Kaloyan Danovski, Lucas Lacasa, Miguel C. Soriano","submitted_at":"2024-04-08T17:33:11Z","abstract_excerpt":"The process of training an artificial neural network involves iteratively adapting its parameters so as to minimize the error of the network's prediction, when confronted with a learning task. This iterative change can be naturally interpreted as a trajectory in network space -- a time series of networks -- and thus the training algorithm (e.g. gradient descent optimization of a suitable loss function) can be interpreted as a dynamical system in graph space. In order to illustrate this interpretation, here we study the dynamical properties of this process by analyzing through this lens the net"},"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":"2404.05782","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-08T17:33:11Z","cross_cats_sorted":["cond-mat.dis-nn","nlin.CD","physics.data-an"],"title_canon_sha256":"e697ab8edb77d2a41b7e46ea26eeaecc35561516aee388ee5fc09b85fbad59b1","abstract_canon_sha256":"6146b239981a97a949aec7ac61fcaeb7e2a69060619b1f32e94bc14d5cbee159"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:59.526903Z","signature_b64":"QuhFbFtKpz1mNgOvR8oZxmvMHEJmO2vb2+K+3gvC87Gv1bK5ADUcug0Guew6mbvl731OfpAx6nwRUAN7nLTECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a9f509b6b125a22dd793cc285f0559ac8157d150735c9279b21fa88e586ebf2","last_reissued_at":"2026-07-05T08:05:59.526501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:59.526501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamical stability and chaos in artificial neural network trajectories along training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","nlin.CD","physics.data-an"],"primary_cat":"cs.LG","authors_text":"Kaloyan Danovski, Lucas Lacasa, Miguel C. Soriano","submitted_at":"2024-04-08T17:33:11Z","abstract_excerpt":"The process of training an artificial neural network involves iteratively adapting its parameters so as to minimize the error of the network's prediction, when confronted with a learning task. This iterative change can be naturally interpreted as a trajectory in network space -- a time series of networks -- and thus the training algorithm (e.g. gradient descent optimization of a suitable loss function) can be interpreted as a dynamical system in graph space. In order to illustrate this interpretation, here we study the dynamical properties of this process by analyzing through this lens the net"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05782","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/2404.05782/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":"2404.05782","created_at":"2026-07-05T08:05:59.526577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05782v1","created_at":"2026-07-05T08:05:59.526577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05782","created_at":"2026-07-05T08:05:59.526577+00:00"},{"alias_kind":"pith_short_12","alias_value":"HKPVBG3LCJNC","created_at":"2026-07-05T08:05:59.526577+00:00"},{"alias_kind":"pith_short_16","alias_value":"HKPVBG3LCJNCFXLZ","created_at":"2026-07-05T08:05:59.526577+00:00"},{"alias_kind":"pith_short_8","alias_value":"HKPVBG3L","created_at":"2026-07-05T08:05:59.526577+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HKPVBG3LCJNCFXLZHTBIL4CVTL","json":"https://pith.science/pith/HKPVBG3LCJNCFXLZHTBIL4CVTL.json","graph_json":"https://pith.science/api/pith-number/HKPVBG3LCJNCFXLZHTBIL4CVTL/graph.json","events_json":"https://pith.science/api/pith-number/HKPVBG3LCJNCFXLZHTBIL4CVTL/events.json","paper":"https://pith.science/paper/HKPVBG3L"},"agent_actions":{"view_html":"https://pith.science/pith/HKPVBG3LCJNCFXLZHTBIL4CVTL","download_json":"https://pith.science/pith/HKPVBG3LCJNCFXLZHTBIL4CVTL.json","view_paper":"https://pith.science/paper/HKPVBG3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05782&json=true","fetch_graph":"https://pith.science/api/pith-number/HKPVBG3LCJNCFXLZHTBIL4CVTL/graph.json","fetch_events":"https://pith.science/api/pith-number/HKPVBG3LCJNCFXLZHTBIL4CVTL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HKPVBG3LCJNCFXLZHTBIL4CVTL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HKPVBG3LCJNCFXLZHTBIL4CVTL/action/storage_attestation","attest_author":"https://pith.science/pith/HKPVBG3LCJNCFXLZHTBIL4CVTL/action/author_attestation","sign_citation":"https://pith.science/pith/HKPVBG3LCJNCFXLZHTBIL4CVTL/action/citation_signature","submit_replication":"https://pith.science/pith/HKPVBG3LCJNCFXLZHTBIL4CVTL/action/replication_record"}},"created_at":"2026-07-05T08:05:59.526577+00:00","updated_at":"2026-07-05T08:05:59.526577+00:00"}