{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FEGUURDYEV2LZMW6UIXYHFDXIR","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":"9019202902466df6c3c42a10dfd67f4986540a7080082aac3bf33f65e091b194","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-16T06:15:20Z","title_canon_sha256":"83481e6271e65f34cd7c0dd3a83e5c8f957afb57c425006e663d22d4a31805ab"},"schema_version":"1.0","source":{"id":"2109.07740","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.07740","created_at":"2026-07-05T03:15:00Z"},{"alias_kind":"arxiv_version","alias_value":"2109.07740v1","created_at":"2026-07-05T03:15:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.07740","created_at":"2026-07-05T03:15:00Z"},{"alias_kind":"pith_short_12","alias_value":"FEGUURDYEV2L","created_at":"2026-07-05T03:15:00Z"},{"alias_kind":"pith_short_16","alias_value":"FEGUURDYEV2LZMW6","created_at":"2026-07-05T03:15:00Z"},{"alias_kind":"pith_short_8","alias_value":"FEGUURDY","created_at":"2026-07-05T03:15:00Z"}],"graph_snapshots":[{"event_id":"sha256:95cb0f45ad5e625631c88f04e1dfe3634096680a7800077e375eb77be8b6317e","target":"graph","created_at":"2026-07-05T03:15:00Z","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/2109.07740/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present an empirical study of scaling properties of encoder-decoder Transformer models used in neural machine translation (NMT). We show that cross-entropy loss as a function of model size follows a certain scaling law. Specifically (i) We propose a formula which describes the scaling behavior of cross-entropy loss as a bivariate function of encoder and decoder size, and show that it gives accurate predictions under a variety of scaling approaches and languages; we show that the total number of parameters alone is not sufficient for such purposes. (ii) We observe different power law exponen","authors_text":"Ankur Bapna, Behrooz Ghorbani, Ciprian Chelba, Colin Cherry, Markus Freitag, Maxim Krikun, Orhan Firat, Xavier Garcia","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-16T06:15:20Z","title":"Scaling Laws for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.07740","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:b2d1dab50659b81b6ed319a357f1c680eb7b2d404674a8d1ae71697a25d59f70","target":"record","created_at":"2026-07-05T03:15:00Z","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":"9019202902466df6c3c42a10dfd67f4986540a7080082aac3bf33f65e091b194","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-16T06:15:20Z","title_canon_sha256":"83481e6271e65f34cd7c0dd3a83e5c8f957afb57c425006e663d22d4a31805ab"},"schema_version":"1.0","source":{"id":"2109.07740","kind":"arxiv","version":1}},"canonical_sha256":"290d4a44782574bcb2dea22f839477446c8ff11df062a6d76d39ccb6585aa780","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"290d4a44782574bcb2dea22f839477446c8ff11df062a6d76d39ccb6585aa780","first_computed_at":"2026-07-05T03:15:00.520492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:00.520492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+hgmZyFCXt87JQx5BT98XoYW6G/Pw5ApCq8yNeSKzo7FR4EUvGv6pFmE+WI6TJgYYHWpnDorZhxMCRQft9kcCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:00.520924Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.07740","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2d1dab50659b81b6ed319a357f1c680eb7b2d404674a8d1ae71697a25d59f70","sha256:95cb0f45ad5e625631c88f04e1dfe3634096680a7800077e375eb77be8b6317e"],"state_sha256":"1520292c6a639209a51e9a116413bc5434d76e63675e986538dc2ee28816ac72"}