{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XIK6R5NNSBZQPJUDIQLJOUAP6W","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":"987f6b8423013346e3e685ccd11611f8d3bee8f28de7165ad5e7bb8ac5de41bb","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-23T05:09:40Z","title_canon_sha256":"471802a4a090bc29a0648b15428944202f2ec4d2f445b5d52471f98ce434ba3b"},"schema_version":"1.0","source":{"id":"2606.24147","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24147","created_at":"2026-06-24T01:14:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24147v1","created_at":"2026-06-24T01:14:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24147","created_at":"2026-06-24T01:14:42Z"},{"alias_kind":"pith_short_12","alias_value":"XIK6R5NNSBZQ","created_at":"2026-06-24T01:14:42Z"},{"alias_kind":"pith_short_16","alias_value":"XIK6R5NNSBZQPJUD","created_at":"2026-06-24T01:14:42Z"},{"alias_kind":"pith_short_8","alias_value":"XIK6R5NN","created_at":"2026-06-24T01:14:42Z"}],"graph_snapshots":[{"event_id":"sha256:717eb5fb5391be451f60ceba1a0db5cff7fc5af6bec6a0d879d3a59c105504cb","target":"graph","created_at":"2026-06-24T01:14:42Z","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/2606.24147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligner-Encoders are recently proposed seq2seq end-to-end ASR models that replace decoder attention by predicting the uth token directly from the u-th encoder position, so the encoder must learn the alignment internally without cross-attention or a transducer lattice. In practice, this alignment often forms abruptly in the upper layers, making training sensitive and brittle on long utterances. We propose InterAligner, which adds an intermediate Aligner objective so alignment can form progressively across depth, together with an intermediate CTC loss (InterCTC) to stabilize optimization. On Lib","authors_text":"Jaeyong Lee, Masato Mimura, Takafumi Moriya","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-23T05:09:40Z","title":"Progressive Alignment Objectives for Aligner-Encoder based ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24147","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:d5fac53acc732b90590119c44bf7c56be22cb6eb8a7c84489b8a58b222692e57","target":"record","created_at":"2026-06-24T01:14:42Z","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":"987f6b8423013346e3e685ccd11611f8d3bee8f28de7165ad5e7bb8ac5de41bb","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-23T05:09:40Z","title_canon_sha256":"471802a4a090bc29a0648b15428944202f2ec4d2f445b5d52471f98ce434ba3b"},"schema_version":"1.0","source":{"id":"2606.24147","kind":"arxiv","version":1}},"canonical_sha256":"ba15e8f5ad907307a683441697500ff5a18adc6feb7372680a348dc0025a2bd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba15e8f5ad907307a683441697500ff5a18adc6feb7372680a348dc0025a2bd9","first_computed_at":"2026-06-24T01:14:42.535050Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:42.535050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kdAekv8o9lJFHbgQwfphoJXmoIUi9el0t6ULRnxjDkwnocyEmv/YZk9pMZmGdoKc+oE5DK9VmQHJPTd/6z0xDw==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:42.535882Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24147","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5fac53acc732b90590119c44bf7c56be22cb6eb8a7c84489b8a58b222692e57","sha256:717eb5fb5391be451f60ceba1a0db5cff7fc5af6bec6a0d879d3a59c105504cb"],"state_sha256":"4b0ef5570aaebcda4a4ef41b83c48e3eef62ccbbfdc0412aebdbd2b04523f7e7"}