{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:S4ISCFO7BQD257ZHDIJ2HHTVVB","short_pith_number":"pith:S4ISCFO7","schema_version":"1.0","canonical_sha256":"97112115df0c07aeff271a13a39e75a874dbb0d2c46917c52f6a21a37e7b8aa3","source":{"kind":"arxiv","id":"2010.15288","version":1},"attestation_state":"computed","paper":{"title":"Speech-Image Semantic Alignment Does Not Depend on Any Prior Classification Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.IT","cs.MM","math.IT"],"primary_cat":"cs.LG","authors_text":"Masood S. Mortazavi","submitted_at":"2020-10-29T00:14:33Z","abstract_excerpt":"Semantically-aligned $(speech, image)$ datasets can be used to explore \"visually-grounded speech\". In a majority of existing investigations, features of an image signal are extracted using neural networks \"pre-trained\" on other tasks (e.g., classification on ImageNet). In still others, pre-trained networks are used to extract audio features prior to semantic embedding. Without \"transfer learning\" through pre-trained initialization or pre-trained feature extraction, previous results have tended to show low rates of recall in $speech \\rightarrow image$ and $image \\rightarrow speech$ queries.\n  C"},"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":"2010.15288","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-29T00:14:33Z","cross_cats_sorted":["cs.CV","cs.IT","cs.MM","math.IT"],"title_canon_sha256":"85bc1195cc719c6306ffe8dbd8fff794b1e93c3081a46aa87c5abc282497a0b9","abstract_canon_sha256":"839f2037cfb3ed1c5e07e28fdf3018620281a66204c69cb59ee59cd9ee2a321f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:47:35.540165Z","signature_b64":"Vb3vBgzz0QLWlv/7VDK8d+p0/uiO2XMeLdwg1X9PdIpRzdirTFYRtr71HFiQSTwEp14piFpk8LakAuWV7BTfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97112115df0c07aeff271a13a39e75a874dbb0d2c46917c52f6a21a37e7b8aa3","last_reissued_at":"2026-07-05T01:47:35.539734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:47:35.539734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speech-Image Semantic Alignment Does Not Depend on Any Prior Classification Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.IT","cs.MM","math.IT"],"primary_cat":"cs.LG","authors_text":"Masood S. Mortazavi","submitted_at":"2020-10-29T00:14:33Z","abstract_excerpt":"Semantically-aligned $(speech, image)$ datasets can be used to explore \"visually-grounded speech\". In a majority of existing investigations, features of an image signal are extracted using neural networks \"pre-trained\" on other tasks (e.g., classification on ImageNet). In still others, pre-trained networks are used to extract audio features prior to semantic embedding. Without \"transfer learning\" through pre-trained initialization or pre-trained feature extraction, previous results have tended to show low rates of recall in $speech \\rightarrow image$ and $image \\rightarrow speech$ queries.\n  C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.15288","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/2010.15288/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":"2010.15288","created_at":"2026-07-05T01:47:35.539794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.15288v1","created_at":"2026-07-05T01:47:35.539794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.15288","created_at":"2026-07-05T01:47:35.539794+00:00"},{"alias_kind":"pith_short_12","alias_value":"S4ISCFO7BQD2","created_at":"2026-07-05T01:47:35.539794+00:00"},{"alias_kind":"pith_short_16","alias_value":"S4ISCFO7BQD257ZH","created_at":"2026-07-05T01:47:35.539794+00:00"},{"alias_kind":"pith_short_8","alias_value":"S4ISCFO7","created_at":"2026-07-05T01:47:35.539794+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/S4ISCFO7BQD257ZHDIJ2HHTVVB","json":"https://pith.science/pith/S4ISCFO7BQD257ZHDIJ2HHTVVB.json","graph_json":"https://pith.science/api/pith-number/S4ISCFO7BQD257ZHDIJ2HHTVVB/graph.json","events_json":"https://pith.science/api/pith-number/S4ISCFO7BQD257ZHDIJ2HHTVVB/events.json","paper":"https://pith.science/paper/S4ISCFO7"},"agent_actions":{"view_html":"https://pith.science/pith/S4ISCFO7BQD257ZHDIJ2HHTVVB","download_json":"https://pith.science/pith/S4ISCFO7BQD257ZHDIJ2HHTVVB.json","view_paper":"https://pith.science/paper/S4ISCFO7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.15288&json=true","fetch_graph":"https://pith.science/api/pith-number/S4ISCFO7BQD257ZHDIJ2HHTVVB/graph.json","fetch_events":"https://pith.science/api/pith-number/S4ISCFO7BQD257ZHDIJ2HHTVVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S4ISCFO7BQD257ZHDIJ2HHTVVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S4ISCFO7BQD257ZHDIJ2HHTVVB/action/storage_attestation","attest_author":"https://pith.science/pith/S4ISCFO7BQD257ZHDIJ2HHTVVB/action/author_attestation","sign_citation":"https://pith.science/pith/S4ISCFO7BQD257ZHDIJ2HHTVVB/action/citation_signature","submit_replication":"https://pith.science/pith/S4ISCFO7BQD257ZHDIJ2HHTVVB/action/replication_record"}},"created_at":"2026-07-05T01:47:35.539794+00:00","updated_at":"2026-07-05T01:47:35.539794+00:00"}