{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:RWBYATP44PBRJ5U4B7SI5A5FZR","short_pith_number":"pith:RWBYATP4","canonical_record":{"source":{"id":"2011.09044","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-11-18T02:32:42Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"a09d282ed38b434cec362946c4334775d1b2f63bca1aadab329f90f459b4d9f6","abstract_canon_sha256":"426381b2d43475e7b77b79619ed103fcafac313e0be131a042351c4120ab5019"},"schema_version":"1.0"},"canonical_sha256":"8d83804dfce3c314f69c0fe48e83a5cc76863405f7d2bf472738c169454ccd78","source":{"kind":"arxiv","id":"2011.09044","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.09044","created_at":"2026-07-05T02:32:25Z"},{"alias_kind":"arxiv_version","alias_value":"2011.09044v2","created_at":"2026-07-05T02:32:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.09044","created_at":"2026-07-05T02:32:25Z"},{"alias_kind":"pith_short_12","alias_value":"RWBYATP44PBR","created_at":"2026-07-05T02:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"RWBYATP44PBRJ5U4","created_at":"2026-07-05T02:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"RWBYATP4","created_at":"2026-07-05T02:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:RWBYATP44PBRJ5U4B7SI5A5FZR","target":"record","payload":{"canonical_record":{"source":{"id":"2011.09044","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-11-18T02:32:42Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"a09d282ed38b434cec362946c4334775d1b2f63bca1aadab329f90f459b4d9f6","abstract_canon_sha256":"426381b2d43475e7b77b79619ed103fcafac313e0be131a042351c4120ab5019"},"schema_version":"1.0"},"canonical_sha256":"8d83804dfce3c314f69c0fe48e83a5cc76863405f7d2bf472738c169454ccd78","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:25.774657Z","signature_b64":"7XADXNVO6bhkx1t2jxfPuHjEy9BgjBN4aGaUcY2DPiq/td+uBSYshNvH7B/5R4j+wAWT1qJMuWWg78Ov2eTvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d83804dfce3c314f69c0fe48e83a5cc76863405f7d2bf472738c169454ccd78","last_reissued_at":"2026-07-05T02:32:25.774170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:25.774170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.09044","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:32:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"amwyy9TQ2JJsSbF7/s0+/nJeD8Dza1zZDDRPlCHXkzs/HeA75hit/d0Ipx4ISRR3djRxOkcizEaJGDnGoY0mAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T06:53:12.362813Z"},"content_sha256":"4051349d4c026bed321d337a9a3b6e8ed2218deb34fcb30caa07d3ba8d764ac6","schema_version":"1.0","event_id":"sha256:4051349d4c026bed321d337a9a3b6e8ed2218deb34fcb30caa07d3ba8d764ac6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:RWBYATP44PBRJ5U4B7SI5A5FZR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Athanasios Mouchtaris, Bhuvan Agrawal, Markus M\\\"uller, Martin Radfar, Samridhi Choudhary, Siegfried Kunzmann","submitted_at":"2020-11-18T02:32:42Z","abstract_excerpt":"End-to-end (E2E) spoken language understanding (SLU) systems can infer the semantics of a spoken utterance directly from an audio signal. However, training an E2E system remains a challenge, largely due to the scarcity of paired audio-semantics data. In this paper, we treat an E2E system as a multi-modal model, with audio and text functioning as its two modalities, and use a cross-modal latent space (CMLS) architecture, where a shared latent space is learned between the `acoustic' and `text' embeddings. We propose using different multi-modal losses to explicitly guide the acoustic embeddings t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.09044","kind":"arxiv","version":2},"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/2011.09044/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":"2026-07-05T02:32:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gYngML3BJcjKsBtzqADkFFWDGhwXwbJ4bRJNr3hFc4OHfWuhonuEUxPMkMsQB+wsiclVT3DOWzmxvOaHe70HBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T06:53:12.363309Z"},"content_sha256":"0420e97a9ae39d7112fac4314f7a8a32d8b9aa253e9bd8875bcdaafd7c7b01c4","schema_version":"1.0","event_id":"sha256:0420e97a9ae39d7112fac4314f7a8a32d8b9aa253e9bd8875bcdaafd7c7b01c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RWBYATP44PBRJ5U4B7SI5A5FZR/bundle.json","state_url":"https://pith.science/pith/RWBYATP44PBRJ5U4B7SI5A5FZR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RWBYATP44PBRJ5U4B7SI5A5FZR/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":"2026-08-01T06:53:12Z","links":{"resolver":"https://pith.science/pith/RWBYATP44PBRJ5U4B7SI5A5FZR","bundle":"https://pith.science/pith/RWBYATP44PBRJ5U4B7SI5A5FZR/bundle.json","state":"https://pith.science/pith/RWBYATP44PBRJ5U4B7SI5A5FZR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RWBYATP44PBRJ5U4B7SI5A5FZR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RWBYATP44PBRJ5U4B7SI5A5FZR","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":"426381b2d43475e7b77b79619ed103fcafac313e0be131a042351c4120ab5019","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-11-18T02:32:42Z","title_canon_sha256":"a09d282ed38b434cec362946c4334775d1b2f63bca1aadab329f90f459b4d9f6"},"schema_version":"1.0","source":{"id":"2011.09044","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.09044","created_at":"2026-07-05T02:32:25Z"},{"alias_kind":"arxiv_version","alias_value":"2011.09044v2","created_at":"2026-07-05T02:32:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.09044","created_at":"2026-07-05T02:32:25Z"},{"alias_kind":"pith_short_12","alias_value":"RWBYATP44PBR","created_at":"2026-07-05T02:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"RWBYATP44PBRJ5U4","created_at":"2026-07-05T02:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"RWBYATP4","created_at":"2026-07-05T02:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:0420e97a9ae39d7112fac4314f7a8a32d8b9aa253e9bd8875bcdaafd7c7b01c4","target":"graph","created_at":"2026-07-05T02:32:25Z","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/2011.09044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end (E2E) spoken language understanding (SLU) systems can infer the semantics of a spoken utterance directly from an audio signal. However, training an E2E system remains a challenge, largely due to the scarcity of paired audio-semantics data. In this paper, we treat an E2E system as a multi-modal model, with audio and text functioning as its two modalities, and use a cross-modal latent space (CMLS) architecture, where a shared latent space is learned between the `acoustic' and `text' embeddings. We propose using different multi-modal losses to explicitly guide the acoustic embeddings t","authors_text":"Athanasios Mouchtaris, Bhuvan Agrawal, Markus M\\\"uller, Martin Radfar, Samridhi Choudhary, Siegfried Kunzmann","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-11-18T02:32:42Z","title":"Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.09044","kind":"arxiv","version":2},"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":"sha256:4051349d4c026bed321d337a9a3b6e8ed2218deb34fcb30caa07d3ba8d764ac6","target":"record","created_at":"2026-07-05T02:32:25Z","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":"426381b2d43475e7b77b79619ed103fcafac313e0be131a042351c4120ab5019","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-11-18T02:32:42Z","title_canon_sha256":"a09d282ed38b434cec362946c4334775d1b2f63bca1aadab329f90f459b4d9f6"},"schema_version":"1.0","source":{"id":"2011.09044","kind":"arxiv","version":2}},"canonical_sha256":"8d83804dfce3c314f69c0fe48e83a5cc76863405f7d2bf472738c169454ccd78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d83804dfce3c314f69c0fe48e83a5cc76863405f7d2bf472738c169454ccd78","first_computed_at":"2026-07-05T02:32:25.774170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:25.774170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7XADXNVO6bhkx1t2jxfPuHjEy9BgjBN4aGaUcY2DPiq/td+uBSYshNvH7B/5R4j+wAWT1qJMuWWg78Ov2eTvDw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:25.774657Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.09044","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4051349d4c026bed321d337a9a3b6e8ed2218deb34fcb30caa07d3ba8d764ac6","sha256:0420e97a9ae39d7112fac4314f7a8a32d8b9aa253e9bd8875bcdaafd7c7b01c4"],"state_sha256":"6568ae3db769df92b7fd4cb1db4aef1de099c1839c091d71797a76b493e493f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rny52w4mqWGZLimkSptVkCWMOm/uB2z9xiqrCZIOOToKrFPlxN15bmQzE1AAXvGJaNWvbow9kuHu7oJHBv5pDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T06:53:12.366754Z","bundle_sha256":"7569a27347976843c62b15984517d777959cb81fad77fab1c6f4bdbc0a6566a5"}}