{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z7E5BT2FWOGJIHBOPXPNONLRGD","short_pith_number":"pith:Z7E5BT2F","schema_version":"1.0","canonical_sha256":"cfc9d0cf45b38c941c2e7dded7357130d9c0d71c6ccf8c557cae3376afe4231e","source":{"kind":"arxiv","id":"2503.10483","version":1},"attestation_state":"computed","paper":{"title":"Grokking as an entanglement transition in tensor network machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"quant-ph","authors_text":"Alfonso Monaco, Antonio Lacalamita, Domenico Pomarico, Ernesto Picardi, Ester Pantaleo, Giuseppe Magnifico, Graziano Pesole, Loredana Bellantuono, Marianna La Rocca, Nicola Amoroso, Roberto Bellotti, Sabina Tangaro, Sebastiano Stramaglia, Tommaso Maggipinto","submitted_at":"2025-03-13T15:51:23Z","abstract_excerpt":"Grokking is a intriguing phenomenon in machine learning where a neural network, after many training iterations with negligible improvement in generalization, suddenly achieves high accuracy on unseen data. By working in the quantum-inspired machine learning framework based on tensor networks, we numerically prove that grokking phenomenon can be related to an entanglement dynamical transition in the underlying quantum many-body systems, consisting in a one-dimensional lattice with each site hosting a qubit. Two datasets are considered as use case scenarios, namely fashion MNIST and gene express"},"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":"2503.10483","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2025-03-13T15:51:23Z","cross_cats_sorted":[],"title_canon_sha256":"c2d738bf088fdd31c4d5f97d18cd908ca7e60118a0d3bc1f73602d8c473c70af","abstract_canon_sha256":"dfac0a8706b097b4171b89e7f49f4b324c338402169baa1fb3bd7ecbbbd09a5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:46.281912Z","signature_b64":"ZOxp/VRD/G5+eEyS3bqeKfBpMAz6hERaWAwqEc71e9SSbuumZDHalcCdfDpowzwiIzGbMic9iqwVMCUHKsLzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfc9d0cf45b38c941c2e7dded7357130d9c0d71c6ccf8c557cae3376afe4231e","last_reissued_at":"2026-07-05T10:30:46.281421Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:46.281421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grokking as an entanglement transition in tensor network machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"quant-ph","authors_text":"Alfonso Monaco, Antonio Lacalamita, Domenico Pomarico, Ernesto Picardi, Ester Pantaleo, Giuseppe Magnifico, Graziano Pesole, Loredana Bellantuono, Marianna La Rocca, Nicola Amoroso, Roberto Bellotti, Sabina Tangaro, Sebastiano Stramaglia, Tommaso Maggipinto","submitted_at":"2025-03-13T15:51:23Z","abstract_excerpt":"Grokking is a intriguing phenomenon in machine learning where a neural network, after many training iterations with negligible improvement in generalization, suddenly achieves high accuracy on unseen data. By working in the quantum-inspired machine learning framework based on tensor networks, we numerically prove that grokking phenomenon can be related to an entanglement dynamical transition in the underlying quantum many-body systems, consisting in a one-dimensional lattice with each site hosting a qubit. Two datasets are considered as use case scenarios, namely fashion MNIST and gene express"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10483","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/2503.10483/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":"2503.10483","created_at":"2026-07-05T10:30:46.281481+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10483v1","created_at":"2026-07-05T10:30:46.281481+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10483","created_at":"2026-07-05T10:30:46.281481+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7E5BT2FWOGJ","created_at":"2026-07-05T10:30:46.281481+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7E5BT2FWOGJIHBO","created_at":"2026-07-05T10:30:46.281481+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7E5BT2F","created_at":"2026-07-05T10:30:46.281481+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08350","citing_title":"Grokking and epoch-wise double descent in quantum neural networks","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2607.00365","citing_title":"When AI meets quantum information: A comprehensive review","ref_index":214,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z7E5BT2FWOGJIHBOPXPNONLRGD","json":"https://pith.science/pith/Z7E5BT2FWOGJIHBOPXPNONLRGD.json","graph_json":"https://pith.science/api/pith-number/Z7E5BT2FWOGJIHBOPXPNONLRGD/graph.json","events_json":"https://pith.science/api/pith-number/Z7E5BT2FWOGJIHBOPXPNONLRGD/events.json","paper":"https://pith.science/paper/Z7E5BT2F"},"agent_actions":{"view_html":"https://pith.science/pith/Z7E5BT2FWOGJIHBOPXPNONLRGD","download_json":"https://pith.science/pith/Z7E5BT2FWOGJIHBOPXPNONLRGD.json","view_paper":"https://pith.science/paper/Z7E5BT2F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10483&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7E5BT2FWOGJIHBOPXPNONLRGD/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7E5BT2FWOGJIHBOPXPNONLRGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7E5BT2FWOGJIHBOPXPNONLRGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7E5BT2FWOGJIHBOPXPNONLRGD/action/storage_attestation","attest_author":"https://pith.science/pith/Z7E5BT2FWOGJIHBOPXPNONLRGD/action/author_attestation","sign_citation":"https://pith.science/pith/Z7E5BT2FWOGJIHBOPXPNONLRGD/action/citation_signature","submit_replication":"https://pith.science/pith/Z7E5BT2FWOGJIHBOPXPNONLRGD/action/replication_record"}},"created_at":"2026-07-05T10:30:46.281481+00:00","updated_at":"2026-07-05T10:30:46.281481+00:00"}