{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JMSPIM7XGMJ7KDGMNMPZFDDUVN","short_pith_number":"pith:JMSPIM7X","canonical_record":{"source":{"id":"2305.10126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-17T11:12:07Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"b722c445102921118e12745ba7a3c8c8e24509b2adbb04c55eb545d68e957d71","abstract_canon_sha256":"3a949c95fc80108b0157bb0ea1d4c9d559ef5ce18e37dfdb40e37303dfee0dab"},"schema_version":"1.0"},"canonical_sha256":"4b24f433f73313f50ccc6b1f928c74ab7e4fff5ee34adc7c24e22e872148ff9d","source":{"kind":"arxiv","id":"2305.10126","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10126","created_at":"2026-07-05T06:11:09Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10126v1","created_at":"2026-07-05T06:11:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10126","created_at":"2026-07-05T06:11:09Z"},{"alias_kind":"pith_short_12","alias_value":"JMSPIM7XGMJ7","created_at":"2026-07-05T06:11:09Z"},{"alias_kind":"pith_short_16","alias_value":"JMSPIM7XGMJ7KDGM","created_at":"2026-07-05T06:11:09Z"},{"alias_kind":"pith_short_8","alias_value":"JMSPIM7X","created_at":"2026-07-05T06:11:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JMSPIM7XGMJ7KDGMNMPZFDDUVN","target":"record","payload":{"canonical_record":{"source":{"id":"2305.10126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-17T11:12:07Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"b722c445102921118e12745ba7a3c8c8e24509b2adbb04c55eb545d68e957d71","abstract_canon_sha256":"3a949c95fc80108b0157bb0ea1d4c9d559ef5ce18e37dfdb40e37303dfee0dab"},"schema_version":"1.0"},"canonical_sha256":"4b24f433f73313f50ccc6b1f928c74ab7e4fff5ee34adc7c24e22e872148ff9d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:09.898392Z","signature_b64":"an42iuWnChnXc0tu8nMCMwQBGaFKJ/5XA069hSvysayoZqhqWzyraXqfr99mpO01lvFyTxQ+9PoPR6tM6wilDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b24f433f73313f50ccc6b1f928c74ab7e4fff5ee34adc7c24e22e872148ff9d","last_reissued_at":"2026-07-05T06:11:09.898020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:09.898020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.10126","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":"2026-07-05T06:11:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ncxKR/v0i/be1ZtfwYZRjLBhG9RZUh3i4Dcnr9GGoAJpqmqn5Tu6USs3CKA9cBWhotEC516spwuZDer5F9otCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:23:22.382085Z"},"content_sha256":"449909ee1e113c680a3649872d21f89748c97954edcfa87b5c9c717fc450ab66","schema_version":"1.0","event_id":"sha256:449909ee1e113c680a3649872d21f89748c97954edcfa87b5c9c717fc450ab66"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JMSPIM7XGMJ7KDGMNMPZFDDUVN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fusion-S2iGan: An Efficient and Effective Single-Stage Framework for Speech-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Lambert Schomaker, Zhenxing Zhang","submitted_at":"2023-05-17T11:12:07Z","abstract_excerpt":"The goal of a speech-to-image transform is to produce a photo-realistic picture directly from a speech signal. Recently, various studies have focused on this task and have achieved promising performance. However, current speech-to-image approaches are based on a stacked modular framework that suffers from three vital issues: 1) Training separate networks is time-consuming as well as inefficient and the convergence of the final generative model strongly depends on the previous generators; 2) The quality of precursor images is ignored by this architecture; 3) Multiple discriminator networks are "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10126","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/2305.10126/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":"2026-07-05T06:11:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bTOsws6uI/6xnTFlqFnyCf/Ch90m3xOX6lFhXh6lCQ65Pv4HsO24ID7VoMkPvjT0FA36kquYPkmm8LJfM0MhDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:23:22.382759Z"},"content_sha256":"896041c5a1753206d2393ed9a97ffffbaf2eda6bdbf636c11fd3c53d2519fa1d","schema_version":"1.0","event_id":"sha256:896041c5a1753206d2393ed9a97ffffbaf2eda6bdbf636c11fd3c53d2519fa1d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JMSPIM7XGMJ7KDGMNMPZFDDUVN/bundle.json","state_url":"https://pith.science/pith/JMSPIM7XGMJ7KDGMNMPZFDDUVN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JMSPIM7XGMJ7KDGMNMPZFDDUVN/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":"2026-07-07T07:23:22Z","links":{"resolver":"https://pith.science/pith/JMSPIM7XGMJ7KDGMNMPZFDDUVN","bundle":"https://pith.science/pith/JMSPIM7XGMJ7KDGMNMPZFDDUVN/bundle.json","state":"https://pith.science/pith/JMSPIM7XGMJ7KDGMNMPZFDDUVN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JMSPIM7XGMJ7KDGMNMPZFDDUVN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JMSPIM7XGMJ7KDGMNMPZFDDUVN","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":"3a949c95fc80108b0157bb0ea1d4c9d559ef5ce18e37dfdb40e37303dfee0dab","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-17T11:12:07Z","title_canon_sha256":"b722c445102921118e12745ba7a3c8c8e24509b2adbb04c55eb545d68e957d71"},"schema_version":"1.0","source":{"id":"2305.10126","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10126","created_at":"2026-07-05T06:11:09Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10126v1","created_at":"2026-07-05T06:11:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10126","created_at":"2026-07-05T06:11:09Z"},{"alias_kind":"pith_short_12","alias_value":"JMSPIM7XGMJ7","created_at":"2026-07-05T06:11:09Z"},{"alias_kind":"pith_short_16","alias_value":"JMSPIM7XGMJ7KDGM","created_at":"2026-07-05T06:11:09Z"},{"alias_kind":"pith_short_8","alias_value":"JMSPIM7X","created_at":"2026-07-05T06:11:09Z"}],"graph_snapshots":[{"event_id":"sha256:896041c5a1753206d2393ed9a97ffffbaf2eda6bdbf636c11fd3c53d2519fa1d","target":"graph","created_at":"2026-07-05T06:11:09Z","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/2305.10126/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of a speech-to-image transform is to produce a photo-realistic picture directly from a speech signal. Recently, various studies have focused on this task and have achieved promising performance. However, current speech-to-image approaches are based on a stacked modular framework that suffers from three vital issues: 1) Training separate networks is time-consuming as well as inefficient and the convergence of the final generative model strongly depends on the previous generators; 2) The quality of precursor images is ignored by this architecture; 3) Multiple discriminator networks are ","authors_text":"Lambert Schomaker, Zhenxing Zhang","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-17T11:12:07Z","title":"Fusion-S2iGan: An Efficient and Effective Single-Stage Framework for Speech-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10126","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":"sha256:449909ee1e113c680a3649872d21f89748c97954edcfa87b5c9c717fc450ab66","target":"record","created_at":"2026-07-05T06:11:09Z","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":"3a949c95fc80108b0157bb0ea1d4c9d559ef5ce18e37dfdb40e37303dfee0dab","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-17T11:12:07Z","title_canon_sha256":"b722c445102921118e12745ba7a3c8c8e24509b2adbb04c55eb545d68e957d71"},"schema_version":"1.0","source":{"id":"2305.10126","kind":"arxiv","version":1}},"canonical_sha256":"4b24f433f73313f50ccc6b1f928c74ab7e4fff5ee34adc7c24e22e872148ff9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b24f433f73313f50ccc6b1f928c74ab7e4fff5ee34adc7c24e22e872148ff9d","first_computed_at":"2026-07-05T06:11:09.898020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:09.898020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"an42iuWnChnXc0tu8nMCMwQBGaFKJ/5XA069hSvysayoZqhqWzyraXqfr99mpO01lvFyTxQ+9PoPR6tM6wilDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:09.898392Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.10126","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:449909ee1e113c680a3649872d21f89748c97954edcfa87b5c9c717fc450ab66","sha256:896041c5a1753206d2393ed9a97ffffbaf2eda6bdbf636c11fd3c53d2519fa1d"],"state_sha256":"336bb3128c15ded97398a59c03c6d8a8f70dbc53a1252314afb3f057b07fb757"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XQHRvJwGI3LdJHV263kOQLJ/2FcAUc6nFkrCY/0zR670FFZSI5ecArU4YoIYQ5OxXU9RuDstJ5RzrO5mLZI0BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:23:22.386213Z","bundle_sha256":"2111a935b88201717dc1edf5e46168e587db74b89b9024ef236886a31a338bdf"}}