{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:54IYG2P7FJA7W4ENZ253NOJPRX","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":"4b8e7972a3919ffd07698a7dbfb62f2105b5071ab83eccbaa649ff30aa066365","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-06T22:09:52Z","title_canon_sha256":"a437dcdb048e2ae3606642ff8a3c76ac29ac0d96507f83b4aeb066deda420a83"},"schema_version":"1.0","source":{"id":"2502.05232","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05232","created_at":"2026-07-05T10:11:34Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05232v1","created_at":"2026-07-05T10:11:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05232","created_at":"2026-07-05T10:11:34Z"},{"alias_kind":"pith_short_12","alias_value":"54IYG2P7FJA7","created_at":"2026-07-05T10:11:34Z"},{"alias_kind":"pith_short_16","alias_value":"54IYG2P7FJA7W4EN","created_at":"2026-07-05T10:11:34Z"},{"alias_kind":"pith_short_8","alias_value":"54IYG2P7","created_at":"2026-07-05T10:11:34Z"}],"graph_snapshots":[{"event_id":"sha256:84a237fe387791dadbc31858f918ba6d4cfc8a06b846f65843210adb1d48701a","target":"graph","created_at":"2026-07-05T10:11:34Z","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/2502.05232/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern systems for automatic speech recognition, including the RNN-Transducer and Attention-based Encoder-Decoder (AED), are designed so that the encoder is not required to alter the time-position of information from the audio sequence into the embedding; alignment to the final text output is processed during decoding. We discover that the transformer-based encoder adopted in recent years is actually capable of performing the alignment internally during the forward pass, prior to decoding. This new phenomenon enables a simpler and more efficient model, the \"Aligner-Encoder\". To train it, we di","authors_text":"Adam Stooke, Khe Chai Sim, Pedro Moreno Mengibar, Rohit Prabhavalkar","cross_cats":["cs.AI","cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-06T22:09:52Z","title":"Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05232","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":"sha256:52456bd2c31846ae223b32cda7276b9f4aef0756af373dee79f9ced4e94dc467","target":"record","created_at":"2026-07-05T10:11:34Z","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":"4b8e7972a3919ffd07698a7dbfb62f2105b5071ab83eccbaa649ff30aa066365","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-06T22:09:52Z","title_canon_sha256":"a437dcdb048e2ae3606642ff8a3c76ac29ac0d96507f83b4aeb066deda420a83"},"schema_version":"1.0","source":{"id":"2502.05232","kind":"arxiv","version":1}},"canonical_sha256":"ef118369ff2a41fb708dcebbb6b92f8dcaf8d16261744b2cbee715ee67f61d19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef118369ff2a41fb708dcebbb6b92f8dcaf8d16261744b2cbee715ee67f61d19","first_computed_at":"2026-07-05T10:11:34.544902Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:34.544902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v3+oo2cN1rgw3SuYlxgP6RWSaq0a/a2Rm3wzkdLCClvtiZZTjaitZ593yRuepjiwhYSbJBNHctUvtxGp7H3xDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:34.545381Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.05232","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52456bd2c31846ae223b32cda7276b9f4aef0756af373dee79f9ced4e94dc467","sha256:84a237fe387791dadbc31858f918ba6d4cfc8a06b846f65843210adb1d48701a"],"state_sha256":"6d120a08457ecefa35126d9e08657216a869dcfd3e0842d98533c7c5173974bd"}