{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MAIW76IXPOLQOW2UQ522IIK2ZQ","short_pith_number":"pith:MAIW76IX","schema_version":"1.0","canonical_sha256":"60116ff9177b97075b548775a4215acc091d4d7335aaa36cb43f008444b6b7e0","source":{"kind":"arxiv","id":"2507.01078","version":1},"attestation_state":"computed","paper":{"title":"yProv4ML: Effortless Provenance Tracking for 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":"2025-07-01T14:59:52Z","abstract_excerpt":"The rapid growth of interest in large language models (LLMs) reflects their potential for flexibility and generalization, and attracted the attention of a diverse range of researchers. However, the advent of these techniques has also brought to light the lack of transparency and rigor with which development is pursued. In particular, the inability to determine the number of epochs and other hyperparameters in advance presents challenges in identifying the best model. To address this challenge, machine learning frameworks such as MLFlow can automate the collection of this type of information. H"},"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":"2507.01078","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T14:59:52Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"ed70db04feae1789fc397f3d6339ac06c2ea471fb58748d99649fc75f11dcad0","abstract_canon_sha256":"02531322aca2ddf620a06d68677225b95f7de27127d9ecb2c1ea29553bc11fab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:24.832748Z","signature_b64":"JQDBDacC9W2+9qTX9dGOc4xOpDphvKvRx7+XoLg5NO9kGPMYWz1fAygc/VqCblIsu75FGFbUJoFG74lyqS/1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60116ff9177b97075b548775a4215acc091d4d7335aaa36cb43f008444b6b7e0","last_reissued_at":"2026-07-05T11:30:24.832254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:24.832254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"yProv4ML: Effortless Provenance Tracking for 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":"2025-07-01T14:59:52Z","abstract_excerpt":"The rapid growth of interest in large language models (LLMs) reflects their potential for flexibility and generalization, and attracted the attention of a diverse range of researchers. However, the advent of these techniques has also brought to light the lack of transparency and rigor with which development is pursued. In particular, the inability to determine the number of epochs and other hyperparameters in advance presents challenges in identifying the best model. To address this challenge, machine learning frameworks such as MLFlow can automate the collection of this type of information. H"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01078","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/2507.01078/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":"2507.01078","created_at":"2026-07-05T11:30:24.832313+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01078v1","created_at":"2026-07-05T11:30:24.832313+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01078","created_at":"2026-07-05T11:30:24.832313+00:00"},{"alias_kind":"pith_short_12","alias_value":"MAIW76IXPOLQ","created_at":"2026-07-05T11:30:24.832313+00:00"},{"alias_kind":"pith_short_16","alias_value":"MAIW76IXPOLQOW2U","created_at":"2026-07-05T11:30:24.832313+00:00"},{"alias_kind":"pith_short_8","alias_value":"MAIW76IX","created_at":"2026-07-05T11:30:24.832313+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/MAIW76IXPOLQOW2UQ522IIK2ZQ","json":"https://pith.science/pith/MAIW76IXPOLQOW2UQ522IIK2ZQ.json","graph_json":"https://pith.science/api/pith-number/MAIW76IXPOLQOW2UQ522IIK2ZQ/graph.json","events_json":"https://pith.science/api/pith-number/MAIW76IXPOLQOW2UQ522IIK2ZQ/events.json","paper":"https://pith.science/paper/MAIW76IX"},"agent_actions":{"view_html":"https://pith.science/pith/MAIW76IXPOLQOW2UQ522IIK2ZQ","download_json":"https://pith.science/pith/MAIW76IXPOLQOW2UQ522IIK2ZQ.json","view_paper":"https://pith.science/paper/MAIW76IX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01078&json=true","fetch_graph":"https://pith.science/api/pith-number/MAIW76IXPOLQOW2UQ522IIK2ZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/MAIW76IXPOLQOW2UQ522IIK2ZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MAIW76IXPOLQOW2UQ522IIK2ZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MAIW76IXPOLQOW2UQ522IIK2ZQ/action/storage_attestation","attest_author":"https://pith.science/pith/MAIW76IXPOLQOW2UQ522IIK2ZQ/action/author_attestation","sign_citation":"https://pith.science/pith/MAIW76IXPOLQOW2UQ522IIK2ZQ/action/citation_signature","submit_replication":"https://pith.science/pith/MAIW76IXPOLQOW2UQ522IIK2ZQ/action/replication_record"}},"created_at":"2026-07-05T11:30:24.832313+00:00","updated_at":"2026-07-05T11:30:24.832313+00:00"}