{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:S4ISCFO7BQD257ZHDIJ2HHTVVB","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":"839f2037cfb3ed1c5e07e28fdf3018620281a66204c69cb59ee59cd9ee2a321f","cross_cats_sorted":["cs.CV","cs.IT","cs.MM","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-29T00:14:33Z","title_canon_sha256":"85bc1195cc719c6306ffe8dbd8fff794b1e93c3081a46aa87c5abc282497a0b9"},"schema_version":"1.0","source":{"id":"2010.15288","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.15288","created_at":"2026-07-05T01:47:35Z"},{"alias_kind":"arxiv_version","alias_value":"2010.15288v1","created_at":"2026-07-05T01:47:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.15288","created_at":"2026-07-05T01:47:35Z"},{"alias_kind":"pith_short_12","alias_value":"S4ISCFO7BQD2","created_at":"2026-07-05T01:47:35Z"},{"alias_kind":"pith_short_16","alias_value":"S4ISCFO7BQD257ZH","created_at":"2026-07-05T01:47:35Z"},{"alias_kind":"pith_short_8","alias_value":"S4ISCFO7","created_at":"2026-07-05T01:47:35Z"}],"graph_snapshots":[{"event_id":"sha256:34d9bc0d6da802bea6d255971f671fd83386adec842e4ca9bbe4d9fdd5a59736","target":"graph","created_at":"2026-07-05T01:47:35Z","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/2010.15288/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Masood S. Mortazavi","cross_cats":["cs.CV","cs.IT","cs.MM","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-29T00:14:33Z","title":"Speech-Image Semantic Alignment Does Not Depend on Any Prior Classification Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.15288","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":"sha256:40cdfad9533a5749fac0fd097d59913a1ef5698fdd92f5e78945126642c52aca","target":"record","created_at":"2026-07-05T01:47:35Z","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":"839f2037cfb3ed1c5e07e28fdf3018620281a66204c69cb59ee59cd9ee2a321f","cross_cats_sorted":["cs.CV","cs.IT","cs.MM","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-29T00:14:33Z","title_canon_sha256":"85bc1195cc719c6306ffe8dbd8fff794b1e93c3081a46aa87c5abc282497a0b9"},"schema_version":"1.0","source":{"id":"2010.15288","kind":"arxiv","version":1}},"canonical_sha256":"97112115df0c07aeff271a13a39e75a874dbb0d2c46917c52f6a21a37e7b8aa3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97112115df0c07aeff271a13a39e75a874dbb0d2c46917c52f6a21a37e7b8aa3","first_computed_at":"2026-07-05T01:47:35.539734Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:47:35.539734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vb3vBgzz0QLWlv/7VDK8d+p0/uiO2XMeLdwg1X9PdIpRzdirTFYRtr71HFiQSTwEp14piFpk8LakAuWV7BTfAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:47:35.540165Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.15288","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40cdfad9533a5749fac0fd097d59913a1ef5698fdd92f5e78945126642c52aca","sha256:34d9bc0d6da802bea6d255971f671fd83386adec842e4ca9bbe4d9fdd5a59736"],"state_sha256":"000a9af02652eeaa1d704cb5525afad2db70012fb559d52c83c3454524749dc2"}