{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HATZ44FDX2TSQY6B6ZAXBQ4MMO","short_pith_number":"pith:HATZ44FD","schema_version":"1.0","canonical_sha256":"38279e70a3bea72863c1f64170c38c63ba3a96b2bcc345fc1e04d4e221c54a34","source":{"kind":"arxiv","id":"2105.05482","version":1},"attestation_state":"computed","paper":{"title":"On the reproducibility of fully convolutional neural networks for modeling time-space evolving physical systems","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["physics.flu-dyn"],"primary_cat":"cs.LG","authors_text":"Antonio Alguacil, Micha\\\"el Bauerheim, Wagner Gon\\c{c}alves Pinto","submitted_at":"2021-05-12T07:39:30Z","abstract_excerpt":"Reproducibility of a deep-learning fully convolutional neural network is evaluated by training several times the same network on identical conditions (database, hyperparameters, hardware) with non-deterministic Graphics Processings Unit (GPU) operations. The propagation of two-dimensional acoustic waves, typical of time-space evolving physical systems, is studied on both recursive and non-recursive tasks. Significant changes in models properties (weights, featured fields) are observed. When tested on various propagation benchmarks, these models systematically returned estimations with a high 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":"2105.05482","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-12T07:39:30Z","cross_cats_sorted":["physics.flu-dyn"],"title_canon_sha256":"333b23f3471b50665e36830c5c4090005df9a83fefe51291f36a0972888aed6d","abstract_canon_sha256":"fe4499900bf43ba86ddb40ab1747e3d9678f85ccbb0946aeffd8e29cd6a76134"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:37.481311Z","signature_b64":"LnNj/rp7tE5J53GBalDXLmVH3FFGKte95LCoTzXcW9X+hhVYGSYbDfGdfW29Y2QYT62qwzNMP6I9FMR1oriUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38279e70a3bea72863c1f64170c38c63ba3a96b2bcc345fc1e04d4e221c54a34","last_reissued_at":"2026-07-05T02:44:37.480864Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:37.480864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the reproducibility of fully convolutional neural networks for modeling time-space evolving physical systems","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["physics.flu-dyn"],"primary_cat":"cs.LG","authors_text":"Antonio Alguacil, Micha\\\"el Bauerheim, Wagner Gon\\c{c}alves Pinto","submitted_at":"2021-05-12T07:39:30Z","abstract_excerpt":"Reproducibility of a deep-learning fully convolutional neural network is evaluated by training several times the same network on identical conditions (database, hyperparameters, hardware) with non-deterministic Graphics Processings Unit (GPU) operations. The propagation of two-dimensional acoustic waves, typical of time-space evolving physical systems, is studied on both recursive and non-recursive tasks. Significant changes in models properties (weights, featured fields) are observed. When tested on various propagation benchmarks, these models systematically returned estimations with a high l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05482","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/2105.05482/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":"2105.05482","created_at":"2026-07-05T02:44:37.480920+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.05482v1","created_at":"2026-07-05T02:44:37.480920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05482","created_at":"2026-07-05T02:44:37.480920+00:00"},{"alias_kind":"pith_short_12","alias_value":"HATZ44FDX2TS","created_at":"2026-07-05T02:44:37.480920+00:00"},{"alias_kind":"pith_short_16","alias_value":"HATZ44FDX2TSQY6B","created_at":"2026-07-05T02:44:37.480920+00:00"},{"alias_kind":"pith_short_8","alias_value":"HATZ44FD","created_at":"2026-07-05T02:44:37.480920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03887","citing_title":"Omega-S: A Functional Resilience Index for LLM Fine-Tuning","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HATZ44FDX2TSQY6B6ZAXBQ4MMO","json":"https://pith.science/pith/HATZ44FDX2TSQY6B6ZAXBQ4MMO.json","graph_json":"https://pith.science/api/pith-number/HATZ44FDX2TSQY6B6ZAXBQ4MMO/graph.json","events_json":"https://pith.science/api/pith-number/HATZ44FDX2TSQY6B6ZAXBQ4MMO/events.json","paper":"https://pith.science/paper/HATZ44FD"},"agent_actions":{"view_html":"https://pith.science/pith/HATZ44FDX2TSQY6B6ZAXBQ4MMO","download_json":"https://pith.science/pith/HATZ44FDX2TSQY6B6ZAXBQ4MMO.json","view_paper":"https://pith.science/paper/HATZ44FD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.05482&json=true","fetch_graph":"https://pith.science/api/pith-number/HATZ44FDX2TSQY6B6ZAXBQ4MMO/graph.json","fetch_events":"https://pith.science/api/pith-number/HATZ44FDX2TSQY6B6ZAXBQ4MMO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HATZ44FDX2TSQY6B6ZAXBQ4MMO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HATZ44FDX2TSQY6B6ZAXBQ4MMO/action/storage_attestation","attest_author":"https://pith.science/pith/HATZ44FDX2TSQY6B6ZAXBQ4MMO/action/author_attestation","sign_citation":"https://pith.science/pith/HATZ44FDX2TSQY6B6ZAXBQ4MMO/action/citation_signature","submit_replication":"https://pith.science/pith/HATZ44FDX2TSQY6B6ZAXBQ4MMO/action/replication_record"}},"created_at":"2026-07-05T02:44:37.480920+00:00","updated_at":"2026-07-05T02:44:37.480920+00:00"}