{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:H2YXMKLLEURNS6LWTVVGKJBUCG","short_pith_number":"pith:H2YXMKLL","canonical_record":{"source":{"id":"2312.10952","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-18T06:08:51Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"1c32385a3164ea992dda2cd29e689908660696e5356c99404f8889e5fd8f706c","abstract_canon_sha256":"19743567d63987fa29558f6b53d325a80b2f091e609160decfe91da7e2320443"},"schema_version":"1.0"},"canonical_sha256":"3eb176296b2522d979769d6a65243411b292d6f4bf58c5750eaa3b63f5c6a183","source":{"kind":"arxiv","id":"2312.10952","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:H2YXMKLLEURNS6LWTVVGKJBUCG","target":"record","payload":{"canonical_record":{"source":{"id":"2312.10952","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-18T06:08:51Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"1c32385a3164ea992dda2cd29e689908660696e5356c99404f8889e5fd8f706c","abstract_canon_sha256":"19743567d63987fa29558f6b53d325a80b2f091e609160decfe91da7e2320443"},"schema_version":"1.0"},"canonical_sha256":"3eb176296b2522d979769d6a65243411b292d6f4bf58c5750eaa3b63f5c6a183","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:14.907177Z","signature_b64":"vm4n2tDYD6M/m/StPRpa7ddAqvDo4LXaMMBcd96rfagAwExYYvEwA0hRgTMXnPE/qzfVnnBRjaU//8VJ6jFoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3eb176296b2522d979769d6a65243411b292d6f4bf58c5750eaa3b63f5c6a183","last_reissued_at":"2026-07-05T07:25:14.906762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:14.906762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.10952","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":"2026-07-05T07:25:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ywxNZbC8InODbJ2AgbYMTd+uJOP90LOyvsUwpUP77ggAA0l61UfoAQRkDAF9SbFDkH6yfI0ICmu/+D2i/Yf2Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T05:26:50.300063Z"},"content_sha256":"7f127263d21e0d8d21d0faf844276851b8130e5f155bface638f432a96a02744","schema_version":"1.0","event_id":"sha256:7f127263d21e0d8d21d0faf844276851b8130e5f155bface638f432a96a02744"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:H2YXMKLLEURNS6LWTVVGKJBUCG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Soft Alignment of Modality Space for End-to-end Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bei Li, Chen Xu, Chunliang Zhang, Jingbo Zhu, Kaiqi Kou, Tong Xiao, Yuhao Zhang","submitted_at":"2023-12-18T06:08:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10952","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/2312.10952/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":"2026-07-05T07:25:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gTQgtAvUtSEhfBd3grVJ9Lh7Q47q7tQCwU4tzZ6VTkCGt3YHDRqj0eejyzR60jfO/za40hcMA6D2OBG+vnU5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T05:26:50.300573Z"},"content_sha256":"688451a643ee2766aef5224fe3873f856c07ffd27c392dc4a2a69c48fa074676","schema_version":"1.0","event_id":"sha256:688451a643ee2766aef5224fe3873f856c07ffd27c392dc4a2a69c48fa074676"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H2YXMKLLEURNS6LWTVVGKJBUCG/bundle.json","state_url":"https://pith.science/pith/H2YXMKLLEURNS6LWTVVGKJBUCG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H2YXMKLLEURNS6LWTVVGKJBUCG/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":"2026-08-12T05:26:50Z","links":{"resolver":"https://pith.science/pith/H2YXMKLLEURNS6LWTVVGKJBUCG","bundle":"https://pith.science/pith/H2YXMKLLEURNS6LWTVVGKJBUCG/bundle.json","state":"https://pith.science/pith/H2YXMKLLEURNS6LWTVVGKJBUCG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H2YXMKLLEURNS6LWTVVGKJBUCG/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zGX6DfeaF3Q6YKjWu2vMGVOQMWvTZcgIrjeUzE1yqpwHvfj/Dazy8zIMQhygomNqYXkGgIj3ewO55NH1fAZcAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T05:26:50.304206Z","bundle_sha256":"a12b6c847220fdfaf9c28e9939f48655a6fa6ee75a9412c20e7e41aea274ad19"}}