{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ADYV7GFH7PFXLTNNTPRSLP34JK","short_pith_number":"pith:ADYV7GFH","canonical_record":{"source":{"id":"2411.18294","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-27T12:32:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"70b9ccd14faee842544c114f41a6d2de4b7d47bfe468adc5b88fcb8bc0fd46d9","abstract_canon_sha256":"63a0bae02efd38efe56c8e1fcc91be7f490853912554540885e3c9594cb4a9ac"},"schema_version":"1.0"},"canonical_sha256":"00f15f98a7fbcb75cdad9be325bf7c4ab140653c2c5422af78668dabe830e3b8","source":{"kind":"arxiv","id":"2411.18294","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18294","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18294v1","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18294","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"pith_short_12","alias_value":"ADYV7GFH7PFX","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"pith_short_16","alias_value":"ADYV7GFH7PFXLTNN","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"pith_short_8","alias_value":"ADYV7GFH","created_at":"2026-07-05T09:41:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ADYV7GFH7PFXLTNNTPRSLP34JK","target":"record","payload":{"canonical_record":{"source":{"id":"2411.18294","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-27T12:32:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"70b9ccd14faee842544c114f41a6d2de4b7d47bfe468adc5b88fcb8bc0fd46d9","abstract_canon_sha256":"63a0bae02efd38efe56c8e1fcc91be7f490853912554540885e3c9594cb4a9ac"},"schema_version":"1.0"},"canonical_sha256":"00f15f98a7fbcb75cdad9be325bf7c4ab140653c2c5422af78668dabe830e3b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:14.500896Z","signature_b64":"U9ZsClSyVeB6xTkovMglbAiVzZWlDO1Entxe6uWhcGvY8EfUsAkrDVBBSVmoV4rXlmos9KUvao9Bzfn5aLmMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00f15f98a7fbcb75cdad9be325bf7c4ab140653c2c5422af78668dabe830e3b8","last_reissued_at":"2026-07-05T09:41:14.500441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:14.500441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.18294","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":"2026-07-05T09:41:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aKPTO19zMLDePeTu+fo3adiDZh/hj/CqnRaimK5/JpLhFp5aUmJ0LsTnX0EGUdOL6rqguJonF41uKh1e+lr4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:01:46.863721Z"},"content_sha256":"dfe81cb315c59f4c205d0f7379fbb61ca81df23700526109d7dd6b6e4c7587b5","schema_version":"1.0","event_id":"sha256:dfe81cb315c59f4c205d0f7379fbb61ca81df23700526109d7dd6b6e4c7587b5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ADYV7GFH7PFXLTNNTPRSLP34JK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aligning Pre-trained Models for Spoken Language Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander Polok, Jan \\v{C}ernock\\'y, Santosh Kesiraju, \\v{S}imon Sedl\\'a\\v{c}ek","submitted_at":"2024-11-27T12:32:41Z","abstract_excerpt":"This paper investigates a novel approach to end-to-end speech translation (ST) based on aligning frozen pre-trained automatic speech recognition (ASR) and machine translation (MT) models via a small connector module (Q-Former, our Subsampler-Transformer Encoder). This connector bridges the gap between the speech and text modalities, transforming ASR encoder embeddings into the latent representation space of the MT encoder while being the only part of the system optimized during training. Experiments are conducted on the How2 English-Portuguese dataset as we investigate the alignment approach i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18294","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/2411.18294/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":"2026-07-05T09:41:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VdFNxurH22hOt/Bb9l5bSguPECkZfPnhkZZCo2Spsaxw2jR9EGUV2QRhBeYD4Fkfm4PXlGwcd1w6B0pguI0IAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:01:46.864118Z"},"content_sha256":"dd31a9be2267f7fc48772cedcc756a6f5c32fa81a51af83d11d3ba9285be3af4","schema_version":"1.0","event_id":"sha256:dd31a9be2267f7fc48772cedcc756a6f5c32fa81a51af83d11d3ba9285be3af4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ADYV7GFH7PFXLTNNTPRSLP34JK/bundle.json","state_url":"https://pith.science/pith/ADYV7GFH7PFXLTNNTPRSLP34JK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ADYV7GFH7PFXLTNNTPRSLP34JK/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":"2026-08-04T09:01:46Z","links":{"resolver":"https://pith.science/pith/ADYV7GFH7PFXLTNNTPRSLP34JK","bundle":"https://pith.science/pith/ADYV7GFH7PFXLTNNTPRSLP34JK/bundle.json","state":"https://pith.science/pith/ADYV7GFH7PFXLTNNTPRSLP34JK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ADYV7GFH7PFXLTNNTPRSLP34JK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ADYV7GFH7PFXLTNNTPRSLP34JK","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":"63a0bae02efd38efe56c8e1fcc91be7f490853912554540885e3c9594cb4a9ac","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-27T12:32:41Z","title_canon_sha256":"70b9ccd14faee842544c114f41a6d2de4b7d47bfe468adc5b88fcb8bc0fd46d9"},"schema_version":"1.0","source":{"id":"2411.18294","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18294","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18294v1","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18294","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"pith_short_12","alias_value":"ADYV7GFH7PFX","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"pith_short_16","alias_value":"ADYV7GFH7PFXLTNN","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"pith_short_8","alias_value":"ADYV7GFH","created_at":"2026-07-05T09:41:14Z"}],"graph_snapshots":[{"event_id":"sha256:dd31a9be2267f7fc48772cedcc756a6f5c32fa81a51af83d11d3ba9285be3af4","target":"graph","created_at":"2026-07-05T09:41:14Z","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/2411.18294/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates a novel approach to end-to-end speech translation (ST) based on aligning frozen pre-trained automatic speech recognition (ASR) and machine translation (MT) models via a small connector module (Q-Former, our Subsampler-Transformer Encoder). This connector bridges the gap between the speech and text modalities, transforming ASR encoder embeddings into the latent representation space of the MT encoder while being the only part of the system optimized during training. Experiments are conducted on the How2 English-Portuguese dataset as we investigate the alignment approach i","authors_text":"Alexander Polok, Jan \\v{C}ernock\\'y, Santosh Kesiraju, \\v{S}imon Sedl\\'a\\v{c}ek","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-27T12:32:41Z","title":"Aligning Pre-trained Models for Spoken Language Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18294","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:dfe81cb315c59f4c205d0f7379fbb61ca81df23700526109d7dd6b6e4c7587b5","target":"record","created_at":"2026-07-05T09:41:14Z","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":"63a0bae02efd38efe56c8e1fcc91be7f490853912554540885e3c9594cb4a9ac","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-27T12:32:41Z","title_canon_sha256":"70b9ccd14faee842544c114f41a6d2de4b7d47bfe468adc5b88fcb8bc0fd46d9"},"schema_version":"1.0","source":{"id":"2411.18294","kind":"arxiv","version":1}},"canonical_sha256":"00f15f98a7fbcb75cdad9be325bf7c4ab140653c2c5422af78668dabe830e3b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00f15f98a7fbcb75cdad9be325bf7c4ab140653c2c5422af78668dabe830e3b8","first_computed_at":"2026-07-05T09:41:14.500441Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:14.500441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U9ZsClSyVeB6xTkovMglbAiVzZWlDO1Entxe6uWhcGvY8EfUsAkrDVBBSVmoV4rXlmos9KUvao9Bzfn5aLmMBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:14.500896Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.18294","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfe81cb315c59f4c205d0f7379fbb61ca81df23700526109d7dd6b6e4c7587b5","sha256:dd31a9be2267f7fc48772cedcc756a6f5c32fa81a51af83d11d3ba9285be3af4"],"state_sha256":"e5c0bf86789146d7962dfb15169b63eb5053a9161eb267433ce19c3a95844d7b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FEfKE2icOGJQX5+gtdUb/QIE4BbEgfgeN5bWKYHD2gmjjj5ckWFfn5/dxLFSMqULIWkvSIpdI0fqmEsgMTfTCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:01:46.866925Z","bundle_sha256":"041dd62c550e442714ce416547e0fd4252605c810c974d07dbfd74a134c7365b"}}