{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:KXDFJ2B43D523JMMFH3G6UPZX2","short_pith_number":"pith:KXDFJ2B4","canonical_record":{"source":{"id":"2002.06170","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-14T18:41:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"86a32a97af2261aeb52cf2f865cda0fb58dd4b87d0cbd950760691160ced048c","abstract_canon_sha256":"9a9d99afee66acc063a9aa0a116534c629fa4a7d565c21ccebcf4e3313796f88"},"schema_version":"1.0"},"canonical_sha256":"55c654e83cd8fbada58c29f66f51f9be92f62f2a184c99d5d43f3d81a3869eb4","source":{"kind":"arxiv","id":"2002.06170","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.06170","created_at":"2026-07-05T00:40:50Z"},{"alias_kind":"arxiv_version","alias_value":"2002.06170v1","created_at":"2026-07-05T00:40:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06170","created_at":"2026-07-05T00:40:50Z"},{"alias_kind":"pith_short_12","alias_value":"KXDFJ2B43D52","created_at":"2026-07-05T00:40:50Z"},{"alias_kind":"pith_short_16","alias_value":"KXDFJ2B43D523JMM","created_at":"2026-07-05T00:40:50Z"},{"alias_kind":"pith_short_8","alias_value":"KXDFJ2B4","created_at":"2026-07-05T00:40:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:KXDFJ2B43D523JMMFH3G6UPZX2","target":"record","payload":{"canonical_record":{"source":{"id":"2002.06170","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-14T18:41:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"86a32a97af2261aeb52cf2f865cda0fb58dd4b87d0cbd950760691160ced048c","abstract_canon_sha256":"9a9d99afee66acc063a9aa0a116534c629fa4a7d565c21ccebcf4e3313796f88"},"schema_version":"1.0"},"canonical_sha256":"55c654e83cd8fbada58c29f66f51f9be92f62f2a184c99d5d43f3d81a3869eb4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:50.794282Z","signature_b64":"us6+G0P9fiZMUzPmznQroh+2V9JgtubBsWt0U8w1CjluxhaQu164rJf37kyXazo4pB25IsrVaMYfZgRneEZ0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55c654e83cd8fbada58c29f66f51f9be92f62f2a184c99d5d43f3d81a3869eb4","last_reissued_at":"2026-07-05T00:40:50.793786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:50.793786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.06170","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":"2026-07-05T00:40:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mvLRnXlQjxHFUgaNUqH3/iym6xCPwcSaVDl9g8cRavjmYpryLrd+13OS/82I9WBVtJB+fsQUJMHInkQ0wlBfAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T19:06:16.196759Z"},"content_sha256":"e1b7ff863be4954a9a700f655bdb50d002823edb178e7ec7a4f220faf43639b1","schema_version":"1.0","event_id":"sha256:e1b7ff863be4954a9a700f655bdb50d002823edb178e7ec7a4f220faf43639b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:KXDFJ2B43D523JMMFH3G6UPZX2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transformer on a Diet","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander J. Smola, Aston Zhang, Chenguang Wang, Zheng Zhang, Zihao Ye","submitted_at":"2020-02-14T18:41:58Z","abstract_excerpt":"Transformer has been widely used thanks to its ability to capture sequence information in an efficient way. However, recent developments, such as BERT and GPT-2, deliver only heavy architectures with a focus on effectiveness. In this paper, we explore three carefully-designed light Transformer architectures to figure out whether the Transformer with less computations could produce competitive results. Experimental results on language model benchmark datasets hint that such trade-off is promising, and the light Transformer reduces 70% parameters at best, while obtains competitive perplexity com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06170","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/2002.06170/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":"2026-07-05T00:40:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ClOqV1xTovWQO0/JvjhCGC2ptLPmhHfJ1EUB1bFWid/vpFnjMzl+//lyagmLBu1xShnFwlKwA4i4ELs8Yo4ZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T19:06:16.197141Z"},"content_sha256":"2c96b31af1ffe6d5204332eaab9f2a9fc5816e558a9b8091a5546d64295fce89","schema_version":"1.0","event_id":"sha256:2c96b31af1ffe6d5204332eaab9f2a9fc5816e558a9b8091a5546d64295fce89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KXDFJ2B43D523JMMFH3G6UPZX2/bundle.json","state_url":"https://pith.science/pith/KXDFJ2B43D523JMMFH3G6UPZX2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KXDFJ2B43D523JMMFH3G6UPZX2/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":"2026-07-18T19:06:16Z","links":{"resolver":"https://pith.science/pith/KXDFJ2B43D523JMMFH3G6UPZX2","bundle":"https://pith.science/pith/KXDFJ2B43D523JMMFH3G6UPZX2/bundle.json","state":"https://pith.science/pith/KXDFJ2B43D523JMMFH3G6UPZX2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KXDFJ2B43D523JMMFH3G6UPZX2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KXDFJ2B43D523JMMFH3G6UPZX2","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":"9a9d99afee66acc063a9aa0a116534c629fa4a7d565c21ccebcf4e3313796f88","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-14T18:41:58Z","title_canon_sha256":"86a32a97af2261aeb52cf2f865cda0fb58dd4b87d0cbd950760691160ced048c"},"schema_version":"1.0","source":{"id":"2002.06170","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.06170","created_at":"2026-07-05T00:40:50Z"},{"alias_kind":"arxiv_version","alias_value":"2002.06170v1","created_at":"2026-07-05T00:40:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06170","created_at":"2026-07-05T00:40:50Z"},{"alias_kind":"pith_short_12","alias_value":"KXDFJ2B43D52","created_at":"2026-07-05T00:40:50Z"},{"alias_kind":"pith_short_16","alias_value":"KXDFJ2B43D523JMM","created_at":"2026-07-05T00:40:50Z"},{"alias_kind":"pith_short_8","alias_value":"KXDFJ2B4","created_at":"2026-07-05T00:40:50Z"}],"graph_snapshots":[{"event_id":"sha256:2c96b31af1ffe6d5204332eaab9f2a9fc5816e558a9b8091a5546d64295fce89","target":"graph","created_at":"2026-07-05T00:40:50Z","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/2002.06170/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer has been widely used thanks to its ability to capture sequence information in an efficient way. However, recent developments, such as BERT and GPT-2, deliver only heavy architectures with a focus on effectiveness. In this paper, we explore three carefully-designed light Transformer architectures to figure out whether the Transformer with less computations could produce competitive results. Experimental results on language model benchmark datasets hint that such trade-off is promising, and the light Transformer reduces 70% parameters at best, while obtains competitive perplexity com","authors_text":"Alexander J. Smola, Aston Zhang, Chenguang Wang, Zheng Zhang, Zihao Ye","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-14T18:41:58Z","title":"Transformer on a Diet"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06170","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:e1b7ff863be4954a9a700f655bdb50d002823edb178e7ec7a4f220faf43639b1","target":"record","created_at":"2026-07-05T00:40:50Z","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":"9a9d99afee66acc063a9aa0a116534c629fa4a7d565c21ccebcf4e3313796f88","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-14T18:41:58Z","title_canon_sha256":"86a32a97af2261aeb52cf2f865cda0fb58dd4b87d0cbd950760691160ced048c"},"schema_version":"1.0","source":{"id":"2002.06170","kind":"arxiv","version":1}},"canonical_sha256":"55c654e83cd8fbada58c29f66f51f9be92f62f2a184c99d5d43f3d81a3869eb4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55c654e83cd8fbada58c29f66f51f9be92f62f2a184c99d5d43f3d81a3869eb4","first_computed_at":"2026-07-05T00:40:50.793786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:40:50.793786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"us6+G0P9fiZMUzPmznQroh+2V9JgtubBsWt0U8w1CjluxhaQu164rJf37kyXazo4pB25IsrVaMYfZgRneEZ0DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:40:50.794282Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.06170","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1b7ff863be4954a9a700f655bdb50d002823edb178e7ec7a4f220faf43639b1","sha256:2c96b31af1ffe6d5204332eaab9f2a9fc5816e558a9b8091a5546d64295fce89"],"state_sha256":"4aa23de4c72a1625dd4f79b9d58bc9d201d2bc6846444d24cfe632f7da868cc2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nUCOllQwGCaMZa20tqfPfoTD8oZi+FriSaXhR5DtTVdCpSvI99aIRz2zvR5/tjnspBXXJXvwliHJte+KamujBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T19:06:16.199687Z","bundle_sha256":"faec371c1d170a57237ad75481789b80bdd5d3cec476ab76c3813ac2e5e30bc3"}}