{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:GYSGDGDWLN6KAR44WHKETROVKW","short_pith_number":"pith:GYSGDGDW","canonical_record":{"source":{"id":"1704.06913","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2017-04-23T11:27:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ed9b0ba8c14d3aa27032ab04049ddccd3b8083ef80b485d16eb46715230a6cf6","abstract_canon_sha256":"f283cce6bd7ac618c931bccb8386be2ca98fa290c44530399580ae2302c82ccc"},"schema_version":"1.0"},"canonical_sha256":"36246198765b7ca0479cb1d449c5d5559577ef0afbd94efaeac86f7df1005afd","source":{"kind":"arxiv","id":"1704.06913","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.06913","created_at":"2026-05-18T00:32:36Z"},{"alias_kind":"arxiv_version","alias_value":"1704.06913v2","created_at":"2026-05-18T00:32:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06913","created_at":"2026-05-18T00:32:36Z"},{"alias_kind":"pith_short_12","alias_value":"GYSGDGDWLN6K","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GYSGDGDWLN6KAR44","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GYSGDGDW","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:GYSGDGDWLN6KAR44WHKETROVKW","target":"record","payload":{"canonical_record":{"source":{"id":"1704.06913","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2017-04-23T11:27:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ed9b0ba8c14d3aa27032ab04049ddccd3b8083ef80b485d16eb46715230a6cf6","abstract_canon_sha256":"f283cce6bd7ac618c931bccb8386be2ca98fa290c44530399580ae2302c82ccc"},"schema_version":"1.0"},"canonical_sha256":"36246198765b7ca0479cb1d449c5d5559577ef0afbd94efaeac86f7df1005afd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:36.255139Z","signature_b64":"APIH8dqPcRTak7R0C5+TMA4iGnbqSqBV+OYP9JYDorx5474hROk75Pd3mRB8lzCcSbrhicfhuXIQzD/0SlgdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36246198765b7ca0479cb1d449c5d5559577ef0afbd94efaeac86f7df1005afd","last_reissued_at":"2026-05-18T00:32:36.254443Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:36.254443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.06913","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":"2026-05-18T00:32:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sEn0M4tDmt3ZfIQ17djZrlOLcJDTGgnv7SPIXo5b4zoG34h8dTKuUwrZ1Z5wfr9O++1sjJ66xjoGD1cWDNrJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T08:57:38.775226Z"},"content_sha256":"5331a635d80ea7f9d92053b27a84053a4768468468d0e83742822dd4e03b5ac6","schema_version":"1.0","event_id":"sha256:5331a635d80ea7f9d92053b27a84053a4768468468d0e83742822dd4e03b5ac6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:GYSGDGDWLN6KAR44WHKETROVKW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning weakly supervised multimodal phoneme embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Emmanuel Dupoux, Ewan Dunbar, Neil Zeghidour, Rahma Chaabouni","submitted_at":"2017-04-23T11:27:53Z","abstract_excerpt":"Recent works have explored deep architectures for learning multimodal speech representation (e.g. audio and images, articulation and audio) in a supervised way. Here we investigate the role of combining different speech modalities, i.e. audio and visual information representing the lips movements, in a weakly supervised way using Siamese networks and lexical same-different side information. In particular, we ask whether one modality can benefit from the other to provide a richer representation for phone recognition in a weakly supervised setting. We introduce mono-task and multi-task methods f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06913","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":""},"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":"2026-05-18T00:32:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4C6vSvq74q72xcNs84JIET3Z5LPb6RFVfp7R9nQcdhPYjFbL1x3iYy0tdLnI1IM09qXGGI0YBE+HofRcqu5GDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T08:57:38.776000Z"},"content_sha256":"982d7e30e1c502aa34a35ebecb74920b1988f60c7de2671c34c001fed92e3c12","schema_version":"1.0","event_id":"sha256:982d7e30e1c502aa34a35ebecb74920b1988f60c7de2671c34c001fed92e3c12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GYSGDGDWLN6KAR44WHKETROVKW/bundle.json","state_url":"https://pith.science/pith/GYSGDGDWLN6KAR44WHKETROVKW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GYSGDGDWLN6KAR44WHKETROVKW/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":"2026-05-25T08:57:38Z","links":{"resolver":"https://pith.science/pith/GYSGDGDWLN6KAR44WHKETROVKW","bundle":"https://pith.science/pith/GYSGDGDWLN6KAR44WHKETROVKW/bundle.json","state":"https://pith.science/pith/GYSGDGDWLN6KAR44WHKETROVKW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GYSGDGDWLN6KAR44WHKETROVKW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:GYSGDGDWLN6KAR44WHKETROVKW","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":"f283cce6bd7ac618c931bccb8386be2ca98fa290c44530399580ae2302c82ccc","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2017-04-23T11:27:53Z","title_canon_sha256":"ed9b0ba8c14d3aa27032ab04049ddccd3b8083ef80b485d16eb46715230a6cf6"},"schema_version":"1.0","source":{"id":"1704.06913","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.06913","created_at":"2026-05-18T00:32:36Z"},{"alias_kind":"arxiv_version","alias_value":"1704.06913v2","created_at":"2026-05-18T00:32:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06913","created_at":"2026-05-18T00:32:36Z"},{"alias_kind":"pith_short_12","alias_value":"GYSGDGDWLN6K","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GYSGDGDWLN6KAR44","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GYSGDGDW","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:982d7e30e1c502aa34a35ebecb74920b1988f60c7de2671c34c001fed92e3c12","target":"graph","created_at":"2026-05-18T00:32:36Z","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"},"paper":{"abstract_excerpt":"Recent works have explored deep architectures for learning multimodal speech representation (e.g. audio and images, articulation and audio) in a supervised way. Here we investigate the role of combining different speech modalities, i.e. audio and visual information representing the lips movements, in a weakly supervised way using Siamese networks and lexical same-different side information. In particular, we ask whether one modality can benefit from the other to provide a richer representation for phone recognition in a weakly supervised setting. We introduce mono-task and multi-task methods f","authors_text":"Emmanuel Dupoux, Ewan Dunbar, Neil Zeghidour, Rahma Chaabouni","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2017-04-23T11:27:53Z","title":"Learning weakly supervised multimodal phoneme embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06913","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":"sha256:5331a635d80ea7f9d92053b27a84053a4768468468d0e83742822dd4e03b5ac6","target":"record","created_at":"2026-05-18T00:32:36Z","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":"f283cce6bd7ac618c931bccb8386be2ca98fa290c44530399580ae2302c82ccc","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2017-04-23T11:27:53Z","title_canon_sha256":"ed9b0ba8c14d3aa27032ab04049ddccd3b8083ef80b485d16eb46715230a6cf6"},"schema_version":"1.0","source":{"id":"1704.06913","kind":"arxiv","version":2}},"canonical_sha256":"36246198765b7ca0479cb1d449c5d5559577ef0afbd94efaeac86f7df1005afd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36246198765b7ca0479cb1d449c5d5559577ef0afbd94efaeac86f7df1005afd","first_computed_at":"2026-05-18T00:32:36.254443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:32:36.254443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"APIH8dqPcRTak7R0C5+TMA4iGnbqSqBV+OYP9JYDorx5474hROk75Pd3mRB8lzCcSbrhicfhuXIQzD/0SlgdBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:32:36.255139Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.06913","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5331a635d80ea7f9d92053b27a84053a4768468468d0e83742822dd4e03b5ac6","sha256:982d7e30e1c502aa34a35ebecb74920b1988f60c7de2671c34c001fed92e3c12"],"state_sha256":"70329e1d0253d845b2c85b510076b70e51ca4c42f09b1ed65a58a05424f3f2cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/+g0/svHKKwAdqXQh6ubBP93VsZjC8rkL/YZjxjTT/LWHbQj2lG2dqg23d0GsPA9HGtohMmfh5rPMtkaoYbhBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T08:57:38.779665Z","bundle_sha256":"2518fc2725f85651efffa53642c739ee78ab495b8de670cc037364c58f87ffce"}}