{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:KPTLHDFPDQ3K34X6XS66WHPXKD","short_pith_number":"pith:KPTLHDFP","canonical_record":{"source":{"id":"2005.09940","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-20T09:53:06Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"c9ed8585de5eaea5d7e6fb52c3dc7ac045cb262dd7bf47092c1376b6f28d806c","abstract_canon_sha256":"eb282b02fcb899d96d96c4246381f82003ab42096a0486c4e7931ce9fc0fbe0f"},"schema_version":"1.0"},"canonical_sha256":"53e6b38caf1c36adf2febcbdeb1df750ee46ed1c528e06f3a276dde34a81ea69","source":{"kind":"arxiv","id":"2005.09940","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.09940","created_at":"2026-07-05T01:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2005.09940v1","created_at":"2026-07-05T01:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.09940","created_at":"2026-07-05T01:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"KPTLHDFPDQ3K","created_at":"2026-07-05T01:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"KPTLHDFPDQ3K34X6","created_at":"2026-07-05T01:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"KPTLHDFP","created_at":"2026-07-05T01:04:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:KPTLHDFPDQ3K34X6XS66WHPXKD","target":"record","payload":{"canonical_record":{"source":{"id":"2005.09940","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-20T09:53:06Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"c9ed8585de5eaea5d7e6fb52c3dc7ac045cb262dd7bf47092c1376b6f28d806c","abstract_canon_sha256":"eb282b02fcb899d96d96c4246381f82003ab42096a0486c4e7931ce9fc0fbe0f"},"schema_version":"1.0"},"canonical_sha256":"53e6b38caf1c36adf2febcbdeb1df750ee46ed1c528e06f3a276dde34a81ea69","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:04:35.459757Z","signature_b64":"8xJ7nhmWfC72yST/c/6xM5tlX3bTUcZYkexlFxZDgnTzl/bbmfywKtJl3h6G2tsPT4VSUFpxPVdH0P9UhmdoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53e6b38caf1c36adf2febcbdeb1df750ee46ed1c528e06f3a276dde34a81ea69","last_reissued_at":"2026-07-05T01:04:35.459265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:04:35.459265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.09940","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":"2026-07-05T01:04:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U0uhylQbLYYukGXzKNaGgkYS7rR7dRTdk9j2qUePH4VjTyJOzBKKV4WXiumXFE1f410iUcPjjebCIXj4rwVLBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T12:34:16.390880Z"},"content_sha256":"4801fe9c8b0afe08365dd2c490238f1940cd4f82e8985ce41be7cb373882b51e","schema_version":"1.0","event_id":"sha256:4801fe9c8b0afe08365dd2c490238f1940cd4f82e8985ce41be7cb373882b51e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:KPTLHDFPDQ3K34X6XS66WHPXKD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Relative Positional Encoding for Speech Recognition and Direct Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alexander Waibel, Elizabeth Salesky, Jan Niehues, Ngoc-Quan Pham, Sebastian Stueker, Thai-Son Nguyen, Thanh-Le Ha, Tuan-Nam Nguyen","submitted_at":"2020-05-20T09:53:06Z","abstract_excerpt":"Transformer models are powerful sequence-to-sequence architectures that are capable of directly mapping speech inputs to transcriptions or translations. However, the mechanism for modeling positions in this model was tailored for text modeling, and thus is less ideal for acoustic inputs. In this work, we adapt the relative position encoding scheme to the Speech Transformer, where the key addition is relative distance between input states in the self-attention network. As a result, the network can better adapt to the variable distributions present in speech data. Our experiments show that our r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.09940","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/2005.09940/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":"2026-07-05T01:04:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tdg05KXrWfYrFp6HP/DLxdu8LTs1hO+Tm8YIhHPb6qmUC2R2khARJiaTzy/bx8HdgLFtkJBdWfPcz35ntIblCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T12:34:16.391286Z"},"content_sha256":"aa7f889a6b3b178f47dc1e9d23de0404fe5bc7fd1551e220e4cb3ef59657f4d6","schema_version":"1.0","event_id":"sha256:aa7f889a6b3b178f47dc1e9d23de0404fe5bc7fd1551e220e4cb3ef59657f4d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KPTLHDFPDQ3K34X6XS66WHPXKD/bundle.json","state_url":"https://pith.science/pith/KPTLHDFPDQ3K34X6XS66WHPXKD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KPTLHDFPDQ3K34X6XS66WHPXKD/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":"2026-07-12T12:34:16Z","links":{"resolver":"https://pith.science/pith/KPTLHDFPDQ3K34X6XS66WHPXKD","bundle":"https://pith.science/pith/KPTLHDFPDQ3K34X6XS66WHPXKD/bundle.json","state":"https://pith.science/pith/KPTLHDFPDQ3K34X6XS66WHPXKD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KPTLHDFPDQ3K34X6XS66WHPXKD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KPTLHDFPDQ3K34X6XS66WHPXKD","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":"eb282b02fcb899d96d96c4246381f82003ab42096a0486c4e7931ce9fc0fbe0f","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-20T09:53:06Z","title_canon_sha256":"c9ed8585de5eaea5d7e6fb52c3dc7ac045cb262dd7bf47092c1376b6f28d806c"},"schema_version":"1.0","source":{"id":"2005.09940","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.09940","created_at":"2026-07-05T01:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2005.09940v1","created_at":"2026-07-05T01:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.09940","created_at":"2026-07-05T01:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"KPTLHDFPDQ3K","created_at":"2026-07-05T01:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"KPTLHDFPDQ3K34X6","created_at":"2026-07-05T01:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"KPTLHDFP","created_at":"2026-07-05T01:04:35Z"}],"graph_snapshots":[{"event_id":"sha256:aa7f889a6b3b178f47dc1e9d23de0404fe5bc7fd1551e220e4cb3ef59657f4d6","target":"graph","created_at":"2026-07-05T01:04:35Z","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/2005.09940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer models are powerful sequence-to-sequence architectures that are capable of directly mapping speech inputs to transcriptions or translations. However, the mechanism for modeling positions in this model was tailored for text modeling, and thus is less ideal for acoustic inputs. In this work, we adapt the relative position encoding scheme to the Speech Transformer, where the key addition is relative distance between input states in the self-attention network. As a result, the network can better adapt to the variable distributions present in speech data. Our experiments show that our r","authors_text":"Alexander Waibel, Elizabeth Salesky, Jan Niehues, Ngoc-Quan Pham, Sebastian Stueker, Thai-Son Nguyen, Thanh-Le Ha, Tuan-Nam Nguyen","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-20T09:53:06Z","title":"Relative Positional Encoding for Speech Recognition and Direct Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.09940","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":"sha256:4801fe9c8b0afe08365dd2c490238f1940cd4f82e8985ce41be7cb373882b51e","target":"record","created_at":"2026-07-05T01:04:35Z","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":"eb282b02fcb899d96d96c4246381f82003ab42096a0486c4e7931ce9fc0fbe0f","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-20T09:53:06Z","title_canon_sha256":"c9ed8585de5eaea5d7e6fb52c3dc7ac045cb262dd7bf47092c1376b6f28d806c"},"schema_version":"1.0","source":{"id":"2005.09940","kind":"arxiv","version":1}},"canonical_sha256":"53e6b38caf1c36adf2febcbdeb1df750ee46ed1c528e06f3a276dde34a81ea69","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53e6b38caf1c36adf2febcbdeb1df750ee46ed1c528e06f3a276dde34a81ea69","first_computed_at":"2026-07-05T01:04:35.459265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:04:35.459265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8xJ7nhmWfC72yST/c/6xM5tlX3bTUcZYkexlFxZDgnTzl/bbmfywKtJl3h6G2tsPT4VSUFpxPVdH0P9UhmdoDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:04:35.459757Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.09940","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4801fe9c8b0afe08365dd2c490238f1940cd4f82e8985ce41be7cb373882b51e","sha256:aa7f889a6b3b178f47dc1e9d23de0404fe5bc7fd1551e220e4cb3ef59657f4d6"],"state_sha256":"75e83944f76992c0c383ed6eee34d916669d979efd057d74a4813c4e6e7e7dd6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oxGXXCYhQ/5hpAG8z4N9EAkiKEr6aAD4Qdsjr7QAuZ88Z6RAkAy8jfnCv5UGvlEis3oP0a3PJ276tbrtqQ/NDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T12:34:16.395332Z","bundle_sha256":"1ef2dd036df0147601443cf4a56aae9a9dbbe9d03d8ed0ea5cf7bf7526837411"}}