{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C4UL7QAB62CSKVMFOQDPPI7QL5","short_pith_number":"pith:C4UL7QAB","schema_version":"1.0","canonical_sha256":"1728bfc001f6852555857406f7a3f05f52a47fc8a4e64ba2a805117cbfb3172d","source":{"kind":"arxiv","id":"2606.30384","version":1},"attestation_state":"computed","paper":{"title":"Scalar Representations of Neural Network Training Dynamics","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":"Lucas Lacasa, Miguel C. Soriano, Pedro Jim\\'enez-Gonz\\'alez","submitted_at":"2026-06-29T14:40:03Z","abstract_excerpt":"Training in artificial neural networks can be viewed as a trajectory evolving through a high-dimensional loss landscape. However, the large number of trainable parameters makes the direct analysis of these dynamics challenging. In this work, we treat such training trajectories as temporal networks and apply recently proposed strategies for the scalar embedding of temporal networks. We investigate whether such a scalar embedding provides a meaningful low-dimensional representation of neural network training dynamics. Using a multilayer perceptron trained on the MNIST classification task, we sho"},"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":"2606.30384","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T14:40:03Z","cross_cats_sorted":["cond-mat.dis-nn","nlin.CD","physics.data-an"],"title_canon_sha256":"6963db57a50a33c7d79ed4b49411469752333e8b8dba385eda2878fee28c9199","abstract_canon_sha256":"a8c3fc8c6672ad1abf8c987ecd5debb495076d29d84f1e906a03df2355c234ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:12.804973Z","signature_b64":"QsD+ybDhrn0VUEDceEub5UrhfPRlia/fVNrGyTZld+dLIxOjJEqj8CMJ514UF286io8w7HWSsHZW3ZPVGjWUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1728bfc001f6852555857406f7a3f05f52a47fc8a4e64ba2a805117cbfb3172d","last_reissued_at":"2026-06-30T02:18:12.804499Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:12.804499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalar Representations of Neural Network Training Dynamics","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":"Lucas Lacasa, Miguel C. Soriano, Pedro Jim\\'enez-Gonz\\'alez","submitted_at":"2026-06-29T14:40:03Z","abstract_excerpt":"Training in artificial neural networks can be viewed as a trajectory evolving through a high-dimensional loss landscape. However, the large number of trainable parameters makes the direct analysis of these dynamics challenging. In this work, we treat such training trajectories as temporal networks and apply recently proposed strategies for the scalar embedding of temporal networks. We investigate whether such a scalar embedding provides a meaningful low-dimensional representation of neural network training dynamics. Using a multilayer perceptron trained on the MNIST classification task, we sho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30384","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/2606.30384/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":"2606.30384","created_at":"2026-06-30T02:18:12.804565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30384v1","created_at":"2026-06-30T02:18:12.804565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30384","created_at":"2026-06-30T02:18:12.804565+00:00"},{"alias_kind":"pith_short_12","alias_value":"C4UL7QAB62CS","created_at":"2026-06-30T02:18:12.804565+00:00"},{"alias_kind":"pith_short_16","alias_value":"C4UL7QAB62CSKVMF","created_at":"2026-06-30T02:18:12.804565+00:00"},{"alias_kind":"pith_short_8","alias_value":"C4UL7QAB","created_at":"2026-06-30T02:18:12.804565+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/C4UL7QAB62CSKVMFOQDPPI7QL5","json":"https://pith.science/pith/C4UL7QAB62CSKVMFOQDPPI7QL5.json","graph_json":"https://pith.science/api/pith-number/C4UL7QAB62CSKVMFOQDPPI7QL5/graph.json","events_json":"https://pith.science/api/pith-number/C4UL7QAB62CSKVMFOQDPPI7QL5/events.json","paper":"https://pith.science/paper/C4UL7QAB"},"agent_actions":{"view_html":"https://pith.science/pith/C4UL7QAB62CSKVMFOQDPPI7QL5","download_json":"https://pith.science/pith/C4UL7QAB62CSKVMFOQDPPI7QL5.json","view_paper":"https://pith.science/paper/C4UL7QAB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30384&json=true","fetch_graph":"https://pith.science/api/pith-number/C4UL7QAB62CSKVMFOQDPPI7QL5/graph.json","fetch_events":"https://pith.science/api/pith-number/C4UL7QAB62CSKVMFOQDPPI7QL5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C4UL7QAB62CSKVMFOQDPPI7QL5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C4UL7QAB62CSKVMFOQDPPI7QL5/action/storage_attestation","attest_author":"https://pith.science/pith/C4UL7QAB62CSKVMFOQDPPI7QL5/action/author_attestation","sign_citation":"https://pith.science/pith/C4UL7QAB62CSKVMFOQDPPI7QL5/action/citation_signature","submit_replication":"https://pith.science/pith/C4UL7QAB62CSKVMFOQDPPI7QL5/action/replication_record"}},"created_at":"2026-06-30T02:18:12.804565+00:00","updated_at":"2026-06-30T02:18:12.804565+00:00"}