{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TW7PL5QL4KQROQNYBLQMXVQFEN","short_pith_number":"pith:TW7PL5QL","schema_version":"1.0","canonical_sha256":"9dbef5f60be2a11741b80ae0cbd60523461763fbf30a5044149fc3934abea5db","source":{"kind":"arxiv","id":"2109.08186","version":4},"attestation_state":"computed","paper":{"title":"Fast-Slow Transformer for Visually Grounding Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"eess.AS","authors_text":"David Harwath, Puyuan Peng","submitted_at":"2021-09-16T18:45:45Z","abstract_excerpt":"We present Fast-Slow Transformer for Visually Grounding Speech, or FaST-VGS. FaST-VGS is a Transformer-based model for learning the associations between raw speech waveforms and visual images. The model unifies dual-encoder and cross-attention architectures into a single model, reaping the superior retrieval speed of the former along with the accuracy of the latter. FaST-VGS achieves state-of-the-art speech-image retrieval accuracy on benchmark datasets, and its learned representations exhibit strong performance on the ZeroSpeech 2021 phonetic and semantic tasks."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2109.08186","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-09-16T18:45:45Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"2a6e3aec440201542dc7eb89a5968f468fd8eed148b5fd919387f64eebc8052e","abstract_canon_sha256":"1bcf3519289db239558982e5f28472664109bfc509fe72696a241e7193bd7a44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:31.970441Z","signature_b64":"YXlcyzhmG2nu6QfxIDYeeu3+LXMOgRQn5KMTBxRwFIk6/s2emWt0ncHxQwwa/elXypjHkPCkQIEPNOjAR/5cAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dbef5f60be2a11741b80ae0cbd60523461763fbf30a5044149fc3934abea5db","last_reissued_at":"2026-07-05T04:01:31.970049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:31.970049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast-Slow Transformer for Visually Grounding Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"eess.AS","authors_text":"David Harwath, Puyuan Peng","submitted_at":"2021-09-16T18:45:45Z","abstract_excerpt":"We present Fast-Slow Transformer for Visually Grounding Speech, or FaST-VGS. FaST-VGS is a Transformer-based model for learning the associations between raw speech waveforms and visual images. The model unifies dual-encoder and cross-attention architectures into a single model, reaping the superior retrieval speed of the former along with the accuracy of the latter. FaST-VGS achieves state-of-the-art speech-image retrieval accuracy on benchmark datasets, and its learned representations exhibit strong performance on the ZeroSpeech 2021 phonetic and semantic tasks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.08186","kind":"arxiv","version":4},"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/2109.08186/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2109.08186","created_at":"2026-07-05T04:01:31.970107+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.08186v4","created_at":"2026-07-05T04:01:31.970107+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.08186","created_at":"2026-07-05T04:01:31.970107+00:00"},{"alias_kind":"pith_short_12","alias_value":"TW7PL5QL4KQR","created_at":"2026-07-05T04:01:31.970107+00:00"},{"alias_kind":"pith_short_16","alias_value":"TW7PL5QL4KQROQNY","created_at":"2026-07-05T04:01:31.970107+00:00"},{"alias_kind":"pith_short_8","alias_value":"TW7PL5QL","created_at":"2026-07-05T04:01:31.970107+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TW7PL5QL4KQROQNYBLQMXVQFEN","json":"https://pith.science/pith/TW7PL5QL4KQROQNYBLQMXVQFEN.json","graph_json":"https://pith.science/api/pith-number/TW7PL5QL4KQROQNYBLQMXVQFEN/graph.json","events_json":"https://pith.science/api/pith-number/TW7PL5QL4KQROQNYBLQMXVQFEN/events.json","paper":"https://pith.science/paper/TW7PL5QL"},"agent_actions":{"view_html":"https://pith.science/pith/TW7PL5QL4KQROQNYBLQMXVQFEN","download_json":"https://pith.science/pith/TW7PL5QL4KQROQNYBLQMXVQFEN.json","view_paper":"https://pith.science/paper/TW7PL5QL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.08186&json=true","fetch_graph":"https://pith.science/api/pith-number/TW7PL5QL4KQROQNYBLQMXVQFEN/graph.json","fetch_events":"https://pith.science/api/pith-number/TW7PL5QL4KQROQNYBLQMXVQFEN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TW7PL5QL4KQROQNYBLQMXVQFEN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TW7PL5QL4KQROQNYBLQMXVQFEN/action/storage_attestation","attest_author":"https://pith.science/pith/TW7PL5QL4KQROQNYBLQMXVQFEN/action/author_attestation","sign_citation":"https://pith.science/pith/TW7PL5QL4KQROQNYBLQMXVQFEN/action/citation_signature","submit_replication":"https://pith.science/pith/TW7PL5QL4KQROQNYBLQMXVQFEN/action/replication_record"}},"created_at":"2026-07-05T04:01:31.970107+00:00","updated_at":"2026-07-05T04:01:31.970107+00:00"}