{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BARCMXR4IT4GP3TRYSXA2DA3XT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f906d9d5dd21cc08caf914f3e7de5fbd75c7493dfcd448d6d6e4da5b2eb376f6","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-07T03:04:34Z","title_canon_sha256":"69b4e33d0f7f082a0117ece273f883114e86d3453fe02e33c1be0195a2ca9c59"},"schema_version":"1.0","source":{"id":"2404.07999","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07999","created_at":"2026-07-05T08:07:01Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07999v1","created_at":"2026-07-05T08:07:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07999","created_at":"2026-07-05T08:07:01Z"},{"alias_kind":"pith_short_12","alias_value":"BARCMXR4IT4G","created_at":"2026-07-05T08:07:01Z"},{"alias_kind":"pith_short_16","alias_value":"BARCMXR4IT4GP3TR","created_at":"2026-07-05T08:07:01Z"},{"alias_kind":"pith_short_8","alias_value":"BARCMXR4","created_at":"2026-07-05T08:07:01Z"}],"graph_snapshots":[{"event_id":"sha256:83588b327050ef24a14dca0ffd8c89472d112357123d402773b426643aa4fdc3","target":"graph","created_at":"2026-07-05T08:07:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.07999/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The fast growing capabilities of large-scale deep learning models, such as Bert, GPT and ViT, are revolutionizing the landscape of NLP, CV and many other domains. Training such models, however, poses an unprecedented demand for computing power, which incurs exponentially increasing energy cost and carbon dioxide emissions. It is thus critical to develop efficient training solutions to reduce the training costs. Motivated by a set of key observations of inter- and intra-layer similarities among feature maps and attentions that can be identified from typical training processes, we propose a mult","authors_text":"Han Zhang, Longwei Zou, Yangdong Deng","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-07T03:04:34Z","title":"A Multi-Level Framework for Accelerating Training Transformer Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07999","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2630e5a185f6f32c57f1aea6dcb041e0202414218375fa7c55c3a3aeaa1d9434","target":"record","created_at":"2026-07-05T08:07:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f906d9d5dd21cc08caf914f3e7de5fbd75c7493dfcd448d6d6e4da5b2eb376f6","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-07T03:04:34Z","title_canon_sha256":"69b4e33d0f7f082a0117ece273f883114e86d3453fe02e33c1be0195a2ca9c59"},"schema_version":"1.0","source":{"id":"2404.07999","kind":"arxiv","version":1}},"canonical_sha256":"0822265e3c44f867ee71c4ae0d0c1bbce8210050ffbb6e1cc656e0820c2b0bd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0822265e3c44f867ee71c4ae0d0c1bbce8210050ffbb6e1cc656e0820c2b0bd2","first_computed_at":"2026-07-05T08:07:01.064291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:07:01.064291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K7TuvPvJlLQLDjhdObT5gefqRGFgX5Q7vFW6/VlqGO89PnuuhLWQTr7RXnkOJ1/KAQieXqotN8NrhYy3DAZ/DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:07:01.064782Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.07999","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2630e5a185f6f32c57f1aea6dcb041e0202414218375fa7c55c3a3aeaa1d9434","sha256:83588b327050ef24a14dca0ffd8c89472d112357123d402773b426643aa4fdc3"],"state_sha256":"6e099d1dd102c785ca10de9ba84f35237eb169fb0a3b21f488b6f7a9293642f5"}