{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:5RY335LZMY6UASZQKP244IUK56","short_pith_number":"pith:5RY335LZ","canonical_record":{"source":{"id":"2101.00542","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-03T02:05:01Z","cross_cats_sorted":[],"title_canon_sha256":"6d727a9345dd67455844fe7987a613c7df3048358ddb23c87dd8373d918a2a9d","abstract_canon_sha256":"ffd044ba6793c25fb16000436d8bd7958d42e489c6bca2efff4502492861d46b"},"schema_version":"1.0"},"canonical_sha256":"ec71bdf579663d404b3053f5ce228aef8bd72395608444659c6bd5feb56c7168","source":{"kind":"arxiv","id":"2101.00542","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.00542","created_at":"2026-07-05T06:09:02Z"},{"alias_kind":"arxiv_version","alias_value":"2101.00542v4","created_at":"2026-07-05T06:09:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00542","created_at":"2026-07-05T06:09:02Z"},{"alias_kind":"pith_short_12","alias_value":"5RY335LZMY6U","created_at":"2026-07-05T06:09:02Z"},{"alias_kind":"pith_short_16","alias_value":"5RY335LZMY6UASZQ","created_at":"2026-07-05T06:09:02Z"},{"alias_kind":"pith_short_8","alias_value":"5RY335LZ","created_at":"2026-07-05T06:09:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:5RY335LZMY6UASZQKP244IUK56","target":"record","payload":{"canonical_record":{"source":{"id":"2101.00542","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-03T02:05:01Z","cross_cats_sorted":[],"title_canon_sha256":"6d727a9345dd67455844fe7987a613c7df3048358ddb23c87dd8373d918a2a9d","abstract_canon_sha256":"ffd044ba6793c25fb16000436d8bd7958d42e489c6bca2efff4502492861d46b"},"schema_version":"1.0"},"canonical_sha256":"ec71bdf579663d404b3053f5ce228aef8bd72395608444659c6bd5feb56c7168","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:02.903599Z","signature_b64":"V159moSNaHlgz5nip6UlF436ns4RH55/uMQqyd3DA6nddQCslAag5WHecDMqFjykKJUX1V3aCM7owbhe1aQxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec71bdf579663d404b3053f5ce228aef8bd72395608444659c6bd5feb56c7168","last_reissued_at":"2026-07-05T06:09:02.903087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:02.903087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.00542","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:09:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MrXobq4n0PzmDCih62vfe+Q1lldOklp8ZDr5+N59M5pbWhNFq7G9RzwWMrstQqiBUh1kkIHeR5pwpZ+awv6vAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:12:29.283435Z"},"content_sha256":"27effb4493109160d597207247331109ed165f292e6d8b085a3cee3dfcd42d46","schema_version":"1.0","event_id":"sha256:27effb4493109160d597207247331109ed165f292e6d8b085a3cee3dfcd42d46"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:5RY335LZMY6UASZQKP244IUK56","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Efficient Transformer Decoder with Compressed Sub-layers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingbo Zhu, Tong Xiao, Yanyang Li, Ye Lin","submitted_at":"2021-01-03T02:05:01Z","abstract_excerpt":"The large attention-based encoder-decoder network (Transformer) has become prevailing recently due to its effectiveness. But the high computation complexity of its decoder raises the inefficiency issue. By examining the mathematic formulation of the decoder, we show that under some mild conditions, the architecture could be simplified by compressing its sub-layers, the basic building block of Transformer, and achieves a higher parallelism. We thereby propose Compressed Attention Network, whose decoder layer consists of only one sub-layer instead of three. Extensive experiments on 14 WMT machin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00542","kind":"arxiv","version":4},"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/2101.00542/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":"2026-07-05T06:09:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GwB7fweQ0RUgoYg4tsizqgWgF/lnuGXOTHrBAD/lxpzryEdr1izKDsPJpvpqRyhAtPzfNpancYSEd851p43WCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:12:29.283923Z"},"content_sha256":"ec0cde4a83a37679ee1a0bd2189669c1c0b8fffee4d7a7cf39b6596fd91357d8","schema_version":"1.0","event_id":"sha256:ec0cde4a83a37679ee1a0bd2189669c1c0b8fffee4d7a7cf39b6596fd91357d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5RY335LZMY6UASZQKP244IUK56/bundle.json","state_url":"https://pith.science/pith/5RY335LZMY6UASZQKP244IUK56/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5RY335LZMY6UASZQKP244IUK56/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":"2026-08-03T17:12:29Z","links":{"resolver":"https://pith.science/pith/5RY335LZMY6UASZQKP244IUK56","bundle":"https://pith.science/pith/5RY335LZMY6UASZQKP244IUK56/bundle.json","state":"https://pith.science/pith/5RY335LZMY6UASZQKP244IUK56/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5RY335LZMY6UASZQKP244IUK56/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5RY335LZMY6UASZQKP244IUK56","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":"ffd044ba6793c25fb16000436d8bd7958d42e489c6bca2efff4502492861d46b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-03T02:05:01Z","title_canon_sha256":"6d727a9345dd67455844fe7987a613c7df3048358ddb23c87dd8373d918a2a9d"},"schema_version":"1.0","source":{"id":"2101.00542","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.00542","created_at":"2026-07-05T06:09:02Z"},{"alias_kind":"arxiv_version","alias_value":"2101.00542v4","created_at":"2026-07-05T06:09:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00542","created_at":"2026-07-05T06:09:02Z"},{"alias_kind":"pith_short_12","alias_value":"5RY335LZMY6U","created_at":"2026-07-05T06:09:02Z"},{"alias_kind":"pith_short_16","alias_value":"5RY335LZMY6UASZQ","created_at":"2026-07-05T06:09:02Z"},{"alias_kind":"pith_short_8","alias_value":"5RY335LZ","created_at":"2026-07-05T06:09:02Z"}],"graph_snapshots":[{"event_id":"sha256:ec0cde4a83a37679ee1a0bd2189669c1c0b8fffee4d7a7cf39b6596fd91357d8","target":"graph","created_at":"2026-07-05T06:09:02Z","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/2101.00542/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The large attention-based encoder-decoder network (Transformer) has become prevailing recently due to its effectiveness. But the high computation complexity of its decoder raises the inefficiency issue. By examining the mathematic formulation of the decoder, we show that under some mild conditions, the architecture could be simplified by compressing its sub-layers, the basic building block of Transformer, and achieves a higher parallelism. We thereby propose Compressed Attention Network, whose decoder layer consists of only one sub-layer instead of three. Extensive experiments on 14 WMT machin","authors_text":"Jingbo Zhu, Tong Xiao, Yanyang Li, Ye Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-03T02:05:01Z","title":"An Efficient Transformer Decoder with Compressed Sub-layers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00542","kind":"arxiv","version":4},"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":"sha256:27effb4493109160d597207247331109ed165f292e6d8b085a3cee3dfcd42d46","target":"record","created_at":"2026-07-05T06:09:02Z","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":"ffd044ba6793c25fb16000436d8bd7958d42e489c6bca2efff4502492861d46b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-03T02:05:01Z","title_canon_sha256":"6d727a9345dd67455844fe7987a613c7df3048358ddb23c87dd8373d918a2a9d"},"schema_version":"1.0","source":{"id":"2101.00542","kind":"arxiv","version":4}},"canonical_sha256":"ec71bdf579663d404b3053f5ce228aef8bd72395608444659c6bd5feb56c7168","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec71bdf579663d404b3053f5ce228aef8bd72395608444659c6bd5feb56c7168","first_computed_at":"2026-07-05T06:09:02.903087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:09:02.903087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V159moSNaHlgz5nip6UlF436ns4RH55/uMQqyd3DA6nddQCslAag5WHecDMqFjykKJUX1V3aCM7owbhe1aQxBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:09:02.903599Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.00542","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27effb4493109160d597207247331109ed165f292e6d8b085a3cee3dfcd42d46","sha256:ec0cde4a83a37679ee1a0bd2189669c1c0b8fffee4d7a7cf39b6596fd91357d8"],"state_sha256":"682033251031923befefe0073c0cc4abaaff4afe4c52fdb74982bfc29c106250"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w/bJttI5HdVorefWL5W0BWAwWHrBP4V/7b8xu9szOlfK53cN2q5OXnWWMRQm9JNYEAPi1nTXLhsyTuZ1YxwIDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:12:29.288752Z","bundle_sha256":"d097f113931adaf40b305fa6c3f22beea53462ec806ae1f761bc55f65bc9cbbb"}}