{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z6ZOFF6LQAKFLB57A2IQW62WY6","short_pith_number":"pith:Z6ZOFF6L","schema_version":"1.0","canonical_sha256":"cfb2e297cb80145587bf06910b7b56c7a54b286bc80e8fb4f12727c3cdf82283","source":{"kind":"arxiv","id":"2507.01075","version":1},"attestation_state":"computed","paper":{"title":"Provenance Tracking in Large-Scale Machine Learning Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Gabriele Padovani, Sandro Fiore, Valentine Anantharaj","submitted_at":"2025-07-01T14:10:02Z","abstract_excerpt":"As the demand for large scale AI models continues to grow, the optimization of their training to balance computational efficiency, execution time, accuracy and energy consumption represents a critical multidimensional challenge. Achieving this balance requires not only innovative algorithmic techniques and hardware architectures but also comprehensive tools for monitoring, analyzing, and understanding the underlying processes involved in model training and deployment. Provenance data information about the origins, context, and transformations of data and processes has become a key component in"},"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":"2507.01075","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T14:10:02Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"75ed70939fb363362c9de0f3d0eb878983c87c79b9a1d16d451afbdbe4f9cd89","abstract_canon_sha256":"863690c0135fb1ff8e43bfdef10221ff3741c228d3a304c65c82afb7f84c5a10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:24.777586Z","signature_b64":"z4OP3hrwXT1N4/+VslcOuXj1tQKH2KpX6MJmatJL4gUGdiHUDOPPRfA0hSE08mb3yWyHjwQnNQcyuABoGIWVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfb2e297cb80145587bf06910b7b56c7a54b286bc80e8fb4f12727c3cdf82283","last_reissued_at":"2026-07-05T11:30:24.777081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:24.777081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provenance Tracking in Large-Scale Machine Learning Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Gabriele Padovani, Sandro Fiore, Valentine Anantharaj","submitted_at":"2025-07-01T14:10:02Z","abstract_excerpt":"As the demand for large scale AI models continues to grow, the optimization of their training to balance computational efficiency, execution time, accuracy and energy consumption represents a critical multidimensional challenge. Achieving this balance requires not only innovative algorithmic techniques and hardware architectures but also comprehensive tools for monitoring, analyzing, and understanding the underlying processes involved in model training and deployment. Provenance data information about the origins, context, and transformations of data and processes has become a key component in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01075","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/2507.01075/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":"2507.01075","created_at":"2026-07-05T11:30:24.777147+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01075v1","created_at":"2026-07-05T11:30:24.777147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01075","created_at":"2026-07-05T11:30:24.777147+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6ZOFF6LQAKF","created_at":"2026-07-05T11:30:24.777147+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6ZOFF6LQAKFLB57","created_at":"2026-07-05T11:30:24.777147+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6ZOFF6L","created_at":"2026-07-05T11:30:24.777147+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.10937","citing_title":"Provenance Tracking in AI Compilers through the Lens of Coalgebra","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z6ZOFF6LQAKFLB57A2IQW62WY6","json":"https://pith.science/pith/Z6ZOFF6LQAKFLB57A2IQW62WY6.json","graph_json":"https://pith.science/api/pith-number/Z6ZOFF6LQAKFLB57A2IQW62WY6/graph.json","events_json":"https://pith.science/api/pith-number/Z6ZOFF6LQAKFLB57A2IQW62WY6/events.json","paper":"https://pith.science/paper/Z6ZOFF6L"},"agent_actions":{"view_html":"https://pith.science/pith/Z6ZOFF6LQAKFLB57A2IQW62WY6","download_json":"https://pith.science/pith/Z6ZOFF6LQAKFLB57A2IQW62WY6.json","view_paper":"https://pith.science/paper/Z6ZOFF6L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01075&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6ZOFF6LQAKFLB57A2IQW62WY6/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6ZOFF6LQAKFLB57A2IQW62WY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6ZOFF6LQAKFLB57A2IQW62WY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6ZOFF6LQAKFLB57A2IQW62WY6/action/storage_attestation","attest_author":"https://pith.science/pith/Z6ZOFF6LQAKFLB57A2IQW62WY6/action/author_attestation","sign_citation":"https://pith.science/pith/Z6ZOFF6LQAKFLB57A2IQW62WY6/action/citation_signature","submit_replication":"https://pith.science/pith/Z6ZOFF6LQAKFLB57A2IQW62WY6/action/replication_record"}},"created_at":"2026-07-05T11:30:24.777147+00:00","updated_at":"2026-07-05T11:30:24.777147+00:00"}