{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DNGYJOEF44BAFPCLKU54MWWMQD","short_pith_number":"pith:DNGYJOEF","schema_version":"1.0","canonical_sha256":"1b4d84b885e70202bc4b553bc65acc80d253191ea595e7fd885df78b2e1f2d8c","source":{"kind":"arxiv","id":"2305.14122","version":2},"attestation_state":"computed","paper":{"title":"Transferring Learning Trajectories of Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daiki Chijiwa","submitted_at":"2023-05-23T14:46:32Z","abstract_excerpt":"Training deep neural networks (DNNs) is computationally expensive, which is problematic especially when performing duplicated or similar training runs in model ensemble or fine-tuning pre-trained models, for example. Once we have trained one DNN on some dataset, we have its learning trajectory (i.e., a sequence of intermediate parameters during training) which may potentially contain useful information for learning the dataset. However, there has been no attempt to utilize such information of a given learning trajectory for another training. In this paper, we formulate the problem of \"transfer"},"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":"2305.14122","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T14:46:32Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"055569822dc5980f852698e9801f0c56e2813797bfd6386ce8037ee8e1353328","abstract_canon_sha256":"943a5ae6ae4d7a4793b46ca8a092ea63943edfdd677fb38f4e0eb24056a82191"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:33.946305Z","signature_b64":"4pdmJI/PtfPva5y2njjV16ofhEM0wpFJxZddgQav8JGsmeITWtG/WUW7tS+p51I44DRwWay1VRHO0ehA26XjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b4d84b885e70202bc4b553bc65acc80d253191ea595e7fd885df78b2e1f2d8c","last_reissued_at":"2026-07-05T06:56:33.945842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:33.945842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transferring Learning Trajectories of Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daiki Chijiwa","submitted_at":"2023-05-23T14:46:32Z","abstract_excerpt":"Training deep neural networks (DNNs) is computationally expensive, which is problematic especially when performing duplicated or similar training runs in model ensemble or fine-tuning pre-trained models, for example. Once we have trained one DNN on some dataset, we have its learning trajectory (i.e., a sequence of intermediate parameters during training) which may potentially contain useful information for learning the dataset. However, there has been no attempt to utilize such information of a given learning trajectory for another training. In this paper, we formulate the problem of \"transfer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14122","kind":"arxiv","version":2},"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/2305.14122/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":"2305.14122","created_at":"2026-07-05T06:56:33.945897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14122v2","created_at":"2026-07-05T06:56:33.945897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14122","created_at":"2026-07-05T06:56:33.945897+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNGYJOEF44BA","created_at":"2026-07-05T06:56:33.945897+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNGYJOEF44BAFPCL","created_at":"2026-07-05T06:56:33.945897+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNGYJOEF","created_at":"2026-07-05T06:56:33.945897+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/DNGYJOEF44BAFPCLKU54MWWMQD","json":"https://pith.science/pith/DNGYJOEF44BAFPCLKU54MWWMQD.json","graph_json":"https://pith.science/api/pith-number/DNGYJOEF44BAFPCLKU54MWWMQD/graph.json","events_json":"https://pith.science/api/pith-number/DNGYJOEF44BAFPCLKU54MWWMQD/events.json","paper":"https://pith.science/paper/DNGYJOEF"},"agent_actions":{"view_html":"https://pith.science/pith/DNGYJOEF44BAFPCLKU54MWWMQD","download_json":"https://pith.science/pith/DNGYJOEF44BAFPCLKU54MWWMQD.json","view_paper":"https://pith.science/paper/DNGYJOEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14122&json=true","fetch_graph":"https://pith.science/api/pith-number/DNGYJOEF44BAFPCLKU54MWWMQD/graph.json","fetch_events":"https://pith.science/api/pith-number/DNGYJOEF44BAFPCLKU54MWWMQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNGYJOEF44BAFPCLKU54MWWMQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNGYJOEF44BAFPCLKU54MWWMQD/action/storage_attestation","attest_author":"https://pith.science/pith/DNGYJOEF44BAFPCLKU54MWWMQD/action/author_attestation","sign_citation":"https://pith.science/pith/DNGYJOEF44BAFPCLKU54MWWMQD/action/citation_signature","submit_replication":"https://pith.science/pith/DNGYJOEF44BAFPCLKU54MWWMQD/action/replication_record"}},"created_at":"2026-07-05T06:56:33.945897+00:00","updated_at":"2026-07-05T06:56:33.945897+00:00"}