{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:WTTTPLOG3M2CHSMQ4L7DTEW6GY","short_pith_number":"pith:WTTTPLOG","canonical_record":{"source":{"id":"1910.06717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-01T19:21:26Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"c7abcee14d77b9501cf42bc9ead69b7a415884c37e119ec74838b165a2c1c706","abstract_canon_sha256":"c6b05686acc15e4ba39395687ae6bbcf194992228094286953fe7e19fd642160"},"schema_version":"1.0"},"canonical_sha256":"b4e737adc6db3423c990e2fe3992de362e28c75cba5a794726834947a31d9353","source":{"kind":"arxiv","id":"1910.06717","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.06717","created_at":"2026-07-05T00:12:14Z"},{"alias_kind":"arxiv_version","alias_value":"1910.06717v1","created_at":"2026-07-05T00:12:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.06717","created_at":"2026-07-05T00:12:14Z"},{"alias_kind":"pith_short_12","alias_value":"WTTTPLOG3M2C","created_at":"2026-07-05T00:12:14Z"},{"alias_kind":"pith_short_16","alias_value":"WTTTPLOG3M2CHSMQ","created_at":"2026-07-05T00:12:14Z"},{"alias_kind":"pith_short_8","alias_value":"WTTTPLOG","created_at":"2026-07-05T00:12:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:WTTTPLOG3M2CHSMQ4L7DTEW6GY","target":"record","payload":{"canonical_record":{"source":{"id":"1910.06717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-01T19:21:26Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"c7abcee14d77b9501cf42bc9ead69b7a415884c37e119ec74838b165a2c1c706","abstract_canon_sha256":"c6b05686acc15e4ba39395687ae6bbcf194992228094286953fe7e19fd642160"},"schema_version":"1.0"},"canonical_sha256":"b4e737adc6db3423c990e2fe3992de362e28c75cba5a794726834947a31d9353","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:12:14.486306Z","signature_b64":"jSyUdlcaqLCVxbSXeeS4yu4+p6xKbpFJCACoaRNE5WDBmaUxXv/fbP0yrN9qeP2peO+Izu6X5spmUy8SSYRTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4e737adc6db3423c990e2fe3992de362e28c75cba5a794726834947a31d9353","last_reissued_at":"2026-07-05T00:12:14.485931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:12:14.485931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.06717","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:12:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yglT2LXKwjvCbUk91lBdaWRF7plfP81lW1HWykrmCC94QOJNo5WYnA/RToVqng4MneKjduYu+xIKtjnK07VPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T02:50:14.104084Z"},"content_sha256":"f8ba2bedfa20781d502aa71ca11e51b2b0b3fdb0a1c1163b121bee1e877c1abc","schema_version":"1.0","event_id":"sha256:f8ba2bedfa20781d502aa71ca11e51b2b0b3fdb0a1c1163b121bee1e877c1abc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:WTTTPLOG3M2CHSMQ4L7DTEW6GY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Auto-Sizing the Transformer Network: Improving Speed, Efficiency, and Performance for Low-Resource Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"David Chiang, Jeffery Kinnison, Kenton Murray, Toan Q. Nguyen, Walter Scheirer","submitted_at":"2019-10-01T19:21:26Z","abstract_excerpt":"Neural sequence-to-sequence models, particularly the Transformer, are the state of the art in machine translation. Yet these neural networks are very sensitive to architecture and hyperparameter settings. Optimizing these settings by grid or random search is computationally expensive because it requires many training runs. In this paper, we incorporate architecture search into a single training run through auto-sizing, which uses regularization to delete neurons in a network over the course of training. On very low-resource language pairs, we show that auto-sizing can improve BLEU scores by up"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.06717","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/1910.06717/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:12:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W8qVDpwZxAUjzxf9f0aVOOBGPPXGMRP7yziOsRcYWpG2EVPDD7x5C0OQVOfDffuLWQPAib32cChhqaheI1LKDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T02:50:14.104473Z"},"content_sha256":"55a73bbd8218b40e2cafc098fc3bd62dd04164d8ffa42d77f07d77335f8db2a1","schema_version":"1.0","event_id":"sha256:55a73bbd8218b40e2cafc098fc3bd62dd04164d8ffa42d77f07d77335f8db2a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WTTTPLOG3M2CHSMQ4L7DTEW6GY/bundle.json","state_url":"https://pith.science/pith/WTTTPLOG3M2CHSMQ4L7DTEW6GY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WTTTPLOG3M2CHSMQ4L7DTEW6GY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-17T02:50:14Z","links":{"resolver":"https://pith.science/pith/WTTTPLOG3M2CHSMQ4L7DTEW6GY","bundle":"https://pith.science/pith/WTTTPLOG3M2CHSMQ4L7DTEW6GY/bundle.json","state":"https://pith.science/pith/WTTTPLOG3M2CHSMQ4L7DTEW6GY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WTTTPLOG3M2CHSMQ4L7DTEW6GY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WTTTPLOG3M2CHSMQ4L7DTEW6GY","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":"c6b05686acc15e4ba39395687ae6bbcf194992228094286953fe7e19fd642160","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-01T19:21:26Z","title_canon_sha256":"c7abcee14d77b9501cf42bc9ead69b7a415884c37e119ec74838b165a2c1c706"},"schema_version":"1.0","source":{"id":"1910.06717","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.06717","created_at":"2026-07-05T00:12:14Z"},{"alias_kind":"arxiv_version","alias_value":"1910.06717v1","created_at":"2026-07-05T00:12:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.06717","created_at":"2026-07-05T00:12:14Z"},{"alias_kind":"pith_short_12","alias_value":"WTTTPLOG3M2C","created_at":"2026-07-05T00:12:14Z"},{"alias_kind":"pith_short_16","alias_value":"WTTTPLOG3M2CHSMQ","created_at":"2026-07-05T00:12:14Z"},{"alias_kind":"pith_short_8","alias_value":"WTTTPLOG","created_at":"2026-07-05T00:12:14Z"}],"graph_snapshots":[{"event_id":"sha256:55a73bbd8218b40e2cafc098fc3bd62dd04164d8ffa42d77f07d77335f8db2a1","target":"graph","created_at":"2026-07-05T00:12:14Z","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/1910.06717/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural sequence-to-sequence models, particularly the Transformer, are the state of the art in machine translation. Yet these neural networks are very sensitive to architecture and hyperparameter settings. Optimizing these settings by grid or random search is computationally expensive because it requires many training runs. In this paper, we incorporate architecture search into a single training run through auto-sizing, which uses regularization to delete neurons in a network over the course of training. On very low-resource language pairs, we show that auto-sizing can improve BLEU scores by up","authors_text":"David Chiang, Jeffery Kinnison, Kenton Murray, Toan Q. Nguyen, Walter Scheirer","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-01T19:21:26Z","title":"Auto-Sizing the Transformer Network: Improving Speed, Efficiency, and Performance for Low-Resource Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.06717","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:f8ba2bedfa20781d502aa71ca11e51b2b0b3fdb0a1c1163b121bee1e877c1abc","target":"record","created_at":"2026-07-05T00:12:14Z","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":"c6b05686acc15e4ba39395687ae6bbcf194992228094286953fe7e19fd642160","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-01T19:21:26Z","title_canon_sha256":"c7abcee14d77b9501cf42bc9ead69b7a415884c37e119ec74838b165a2c1c706"},"schema_version":"1.0","source":{"id":"1910.06717","kind":"arxiv","version":1}},"canonical_sha256":"b4e737adc6db3423c990e2fe3992de362e28c75cba5a794726834947a31d9353","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4e737adc6db3423c990e2fe3992de362e28c75cba5a794726834947a31d9353","first_computed_at":"2026-07-05T00:12:14.485931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:12:14.485931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jSyUdlcaqLCVxbSXeeS4yu4+p6xKbpFJCACoaRNE5WDBmaUxXv/fbP0yrN9qeP2peO+Izu6X5spmUy8SSYRTAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:12:14.486306Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.06717","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8ba2bedfa20781d502aa71ca11e51b2b0b3fdb0a1c1163b121bee1e877c1abc","sha256:55a73bbd8218b40e2cafc098fc3bd62dd04164d8ffa42d77f07d77335f8db2a1"],"state_sha256":"eb49ca3967933a270179806dbd3e142ac0be02f3cc2b88ab883463bdd2d28926"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KCAqfUbWy1xXTSoQu/TD7Oo5FiOMVyRhBqti81zNZVL759i6poTN6Z+dgge5h290hauhsoPGzblj2UQo8kDZBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T02:50:14.106507Z","bundle_sha256":"81c45c14000de78118e8452f565410ae7dbf96aa36d9c01a1b2b50a9e44c90cf"}}