{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H2YXMKLLEURNS6LWTVVGKJBUCG","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":"19743567d63987fa29558f6b53d325a80b2f091e609160decfe91da7e2320443","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-18T06:08:51Z","title_canon_sha256":"1c32385a3164ea992dda2cd29e689908660696e5356c99404f8889e5fd8f706c"},"schema_version":"1.0","source":{"id":"2312.10952","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.10952","created_at":"2026-07-05T07:25:14Z"},{"alias_kind":"arxiv_version","alias_value":"2312.10952v1","created_at":"2026-07-05T07:25:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10952","created_at":"2026-07-05T07:25:14Z"},{"alias_kind":"pith_short_12","alias_value":"H2YXMKLLEURN","created_at":"2026-07-05T07:25:14Z"},{"alias_kind":"pith_short_16","alias_value":"H2YXMKLLEURNS6LW","created_at":"2026-07-05T07:25:14Z"},{"alias_kind":"pith_short_8","alias_value":"H2YXMKLL","created_at":"2026-07-05T07:25:14Z"}],"graph_snapshots":[{"event_id":"sha256:688451a643ee2766aef5224fe3873f856c07ffd27c392dc4a2a69c48fa074676","target":"graph","created_at":"2026-07-05T07:25:14Z","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/2312.10952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end Speech Translation (ST) aims to convert speech into target text within a unified model. The inherent differences between speech and text modalities often impede effective cross-modal and cross-lingual transfer. Existing methods typically employ hard alignment (H-Align) of individual speech and text segments, which can degrade textual representations. To address this, we introduce Soft Alignment (S-Align), using adversarial training to align the representation spaces of both modalities. S-Align creates a modality-invariant space while preserving individual modality quality. Experimen","authors_text":"Bei Li, Chen Xu, Chunliang Zhang, Jingbo Zhu, Kaiqi Kou, Tong Xiao, Yuhao Zhang","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-18T06:08:51Z","title":"Soft Alignment of Modality Space for End-to-end Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10952","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":"sha256:7f127263d21e0d8d21d0faf844276851b8130e5f155bface638f432a96a02744","target":"record","created_at":"2026-07-05T07:25:14Z","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":"19743567d63987fa29558f6b53d325a80b2f091e609160decfe91da7e2320443","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-18T06:08:51Z","title_canon_sha256":"1c32385a3164ea992dda2cd29e689908660696e5356c99404f8889e5fd8f706c"},"schema_version":"1.0","source":{"id":"2312.10952","kind":"arxiv","version":1}},"canonical_sha256":"3eb176296b2522d979769d6a65243411b292d6f4bf58c5750eaa3b63f5c6a183","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3eb176296b2522d979769d6a65243411b292d6f4bf58c5750eaa3b63f5c6a183","first_computed_at":"2026-07-05T07:25:14.906762Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:25:14.906762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vm4n2tDYD6M/m/StPRpa7ddAqvDo4LXaMMBcd96rfagAwExYYvEwA0hRgTMXnPE/qzfVnnBRjaU//8VJ6jFoCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:25:14.907177Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.10952","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f127263d21e0d8d21d0faf844276851b8130e5f155bface638f432a96a02744","sha256:688451a643ee2766aef5224fe3873f856c07ffd27c392dc4a2a69c48fa074676"],"state_sha256":"1b21f748f3d813023fe6656234b0a0e138e47ac8d7768eecbcf7834cee0c4ce8"}