{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:64XXGIGJGNDD5GSW4RQFAKNLK3","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":"413e88a60dc24366f1f39289692a0259f38e1537af3a05b916a923c4eec55933","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T16:17:01Z","title_canon_sha256":"1287545e0148847c79fbf7351fbfa0af04ac74f01559b582773e85917a183049"},"schema_version":"1.0","source":{"id":"2410.22179","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22179","created_at":"2026-07-05T10:29:25Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22179v2","created_at":"2026-07-05T10:29:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22179","created_at":"2026-07-05T10:29:25Z"},{"alias_kind":"pith_short_12","alias_value":"64XXGIGJGNDD","created_at":"2026-07-05T10:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"64XXGIGJGNDD5GSW","created_at":"2026-07-05T10:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"64XXGIGJ","created_at":"2026-07-05T10:29:25Z"}],"graph_snapshots":[{"event_id":"sha256:79bfab52e7cca2876f49c05e211a19e3bc0487c9e93d778e4ad67b753e622709","target":"graph","created_at":"2026-07-05T10:29:25Z","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/2410.22179/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive (AR) Transformer-based sequence models are known to have difficulty generalizing to sequences longer than those seen during training. When applied to text-to-speech (TTS), these models tend to drop or repeat words or produce erratic output, especially for longer utterances. In this paper, we introduce enhancements aimed at AR Transformer-based encoder-decoder TTS systems that address these robustness and length generalization issues. Our approach uses an alignment mechanism to provide cross-attention operations with relative location information. The associated alignment positio","authors_text":"Daisy Stanton, David Kao, Eric Battenberg, Julian Salazar, Matt Shannon, RJ Skerry-Ryan, Soroosh Mariooryad","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T16:17:01Z","title":"Robust and Unbounded Length Generalization in Autoregressive Transformer-Based Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22179","kind":"arxiv","version":2},"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":"sha256:74495e5da9bec4dfc9aeed43a172590d08014aea4eec9ed2082b7b18f712fbc2","target":"record","created_at":"2026-07-05T10:29:25Z","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":"413e88a60dc24366f1f39289692a0259f38e1537af3a05b916a923c4eec55933","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T16:17:01Z","title_canon_sha256":"1287545e0148847c79fbf7351fbfa0af04ac74f01559b582773e85917a183049"},"schema_version":"1.0","source":{"id":"2410.22179","kind":"arxiv","version":2}},"canonical_sha256":"f72f7320c933463e9a56e4605029ab56c4a44d84ddc63c5a07f4279608b0ae6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f72f7320c933463e9a56e4605029ab56c4a44d84ddc63c5a07f4279608b0ae6f","first_computed_at":"2026-07-05T10:29:25.735366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:25.735366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pgkHNCSzdFt5TWtQotEXCKfBmy91vCL6RRlgYKlUgHjIrVIG4GUCn94bArZgU3HRQhXLWqr0HnTYD+KTrHqDBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:25.736002Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.22179","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74495e5da9bec4dfc9aeed43a172590d08014aea4eec9ed2082b7b18f712fbc2","sha256:79bfab52e7cca2876f49c05e211a19e3bc0487c9e93d778e4ad67b753e622709"],"state_sha256":"7ad2129db86f6fd10a3b8addd0c1da396d956d21ccf13f167506ad4a2b1ff80d"}