{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:NH77URPNOSJEHY5UGRKJFIE6BM","short_pith_number":"pith:NH77URPN","canonical_record":{"source":{"id":"2205.02444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-05T05:14:01Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d14e480d0e567c48a41e603d8d994a60c188751d1424828becda8dc0bbc159e8","abstract_canon_sha256":"4348fe886309b8671eacae20cd224f7612d5c7e500ed69902f1da90336e8db7e"},"schema_version":"1.0"},"canonical_sha256":"69fffa45ed749243e3b4345492a09e0b28c3cfa36f2a08e128ece17ded4d011a","source":{"kind":"arxiv","id":"2205.02444","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.02444","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"arxiv_version","alias_value":"2205.02444v1","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02444","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"pith_short_12","alias_value":"NH77URPNOSJE","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"pith_short_16","alias_value":"NH77URPNOSJEHY5U","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"pith_short_8","alias_value":"NH77URPN","created_at":"2026-07-05T04:20:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:NH77URPNOSJEHY5UGRKJFIE6BM","target":"record","payload":{"canonical_record":{"source":{"id":"2205.02444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-05T05:14:01Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d14e480d0e567c48a41e603d8d994a60c188751d1424828becda8dc0bbc159e8","abstract_canon_sha256":"4348fe886309b8671eacae20cd224f7612d5c7e500ed69902f1da90336e8db7e"},"schema_version":"1.0"},"canonical_sha256":"69fffa45ed749243e3b4345492a09e0b28c3cfa36f2a08e128ece17ded4d011a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:37.139735Z","signature_b64":"lPGqGVgNaSzUln04NAPhTOjHJp4tGwdlp3vIVsAacqH3t8afDhE75TpoYiGrm/5p/6pe7mLd83p3p4sm3heoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69fffa45ed749243e3b4345492a09e0b28c3cfa36f2a08e128ece17ded4d011a","last_reissued_at":"2026-07-05T04:20:37.139276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:37.139276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.02444","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":"2026-07-05T04:20:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ll53atg6aix6QsHONj/AGDyYkVu0vdyp34o88lnlnVtiDImW8ZaTz0G2SkHZyMqtsAY/fXGkBA5ZejiKeC4Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:12:50.441678Z"},"content_sha256":"25c7310c90fccbacc26555fc4220231d29078d2c2e09da4581ff5df40197cbdb","schema_version":"1.0","event_id":"sha256:25c7310c90fccbacc26555fc4220231d29078d2c2e09da4581ff5df40197cbdb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:NH77URPNOSJEHY5UGRKJFIE6BM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-modal Contrastive Learning for Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Lei Li, Mingxuan Wang, Rong Ye","submitted_at":"2022-05-05T05:14:01Z","abstract_excerpt":"How can we learn unified representations for spoken utterances and their written text? Learning similar representations for semantically similar speech and text is important for speech translation. To this end, we propose ConST, a cross-modal contrastive learning method for end-to-end speech-to-text translation. We evaluate ConST and a variety of previous baselines on a popular benchmark MuST-C. Experiments show that the proposed ConST consistently outperforms the previous methods on, and achieves an average BLEU of 29.4. The analysis further verifies that ConST indeed closes the representatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02444","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/2205.02444/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":"2026-07-05T04:20:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xb39K1Y6bh2sjhxqE0iXiFXMBcTHy/qSsT5ZhYYusJTZ10e3WFBoSVk/p+cCy9NHvdYluK7BWYQBApJAqHyBBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:12:50.442051Z"},"content_sha256":"c3aae3baf617e1e24d7f8b22c75a1d35b8acff34594b03d1ae79f5578484fdfc","schema_version":"1.0","event_id":"sha256:c3aae3baf617e1e24d7f8b22c75a1d35b8acff34594b03d1ae79f5578484fdfc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NH77URPNOSJEHY5UGRKJFIE6BM/bundle.json","state_url":"https://pith.science/pith/NH77URPNOSJEHY5UGRKJFIE6BM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NH77URPNOSJEHY5UGRKJFIE6BM/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":"2026-07-07T04:12:50Z","links":{"resolver":"https://pith.science/pith/NH77URPNOSJEHY5UGRKJFIE6BM","bundle":"https://pith.science/pith/NH77URPNOSJEHY5UGRKJFIE6BM/bundle.json","state":"https://pith.science/pith/NH77URPNOSJEHY5UGRKJFIE6BM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NH77URPNOSJEHY5UGRKJFIE6BM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NH77URPNOSJEHY5UGRKJFIE6BM","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":"4348fe886309b8671eacae20cd224f7612d5c7e500ed69902f1da90336e8db7e","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-05T05:14:01Z","title_canon_sha256":"d14e480d0e567c48a41e603d8d994a60c188751d1424828becda8dc0bbc159e8"},"schema_version":"1.0","source":{"id":"2205.02444","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.02444","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"arxiv_version","alias_value":"2205.02444v1","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02444","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"pith_short_12","alias_value":"NH77URPNOSJE","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"pith_short_16","alias_value":"NH77URPNOSJEHY5U","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"pith_short_8","alias_value":"NH77URPN","created_at":"2026-07-05T04:20:37Z"}],"graph_snapshots":[{"event_id":"sha256:c3aae3baf617e1e24d7f8b22c75a1d35b8acff34594b03d1ae79f5578484fdfc","target":"graph","created_at":"2026-07-05T04:20:37Z","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/2205.02444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How can we learn unified representations for spoken utterances and their written text? Learning similar representations for semantically similar speech and text is important for speech translation. To this end, we propose ConST, a cross-modal contrastive learning method for end-to-end speech-to-text translation. We evaluate ConST and a variety of previous baselines on a popular benchmark MuST-C. Experiments show that the proposed ConST consistently outperforms the previous methods on, and achieves an average BLEU of 29.4. The analysis further verifies that ConST indeed closes the representatio","authors_text":"Lei Li, Mingxuan Wang, Rong Ye","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-05T05:14:01Z","title":"Cross-modal Contrastive Learning for Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02444","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":"sha256:25c7310c90fccbacc26555fc4220231d29078d2c2e09da4581ff5df40197cbdb","target":"record","created_at":"2026-07-05T04:20:37Z","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":"4348fe886309b8671eacae20cd224f7612d5c7e500ed69902f1da90336e8db7e","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-05T05:14:01Z","title_canon_sha256":"d14e480d0e567c48a41e603d8d994a60c188751d1424828becda8dc0bbc159e8"},"schema_version":"1.0","source":{"id":"2205.02444","kind":"arxiv","version":1}},"canonical_sha256":"69fffa45ed749243e3b4345492a09e0b28c3cfa36f2a08e128ece17ded4d011a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69fffa45ed749243e3b4345492a09e0b28c3cfa36f2a08e128ece17ded4d011a","first_computed_at":"2026-07-05T04:20:37.139276Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:20:37.139276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lPGqGVgNaSzUln04NAPhTOjHJp4tGwdlp3vIVsAacqH3t8afDhE75TpoYiGrm/5p/6pe7mLd83p3p4sm3heoCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:20:37.139735Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.02444","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25c7310c90fccbacc26555fc4220231d29078d2c2e09da4581ff5df40197cbdb","sha256:c3aae3baf617e1e24d7f8b22c75a1d35b8acff34594b03d1ae79f5578484fdfc"],"state_sha256":"4d4dd5bfd2587b6c4286d0985c1e49159659b6a39ea7138190a1ae128fc09ff6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xo7EIj4Oh7EY+Iz9zL7KJ5EjJjEYrbKSu6Fay8L99tQ5ZLfYX8y5TimdP4otaxi8WYY67JhGOxHq+AvjMklBBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:12:50.443995Z","bundle_sha256":"e6e4f529e7dab239411661f21c5765f0bd65175c8aa897854d847333dcd221b0"}}