{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:DSQBL6R762L5MW3RGW6GISQZNP","short_pith_number":"pith:DSQBL6R7","canonical_record":{"source":{"id":"1710.01949","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-05T10:24:46Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"527c32e05da8d274ad55ecc0c2f19d091f450e9363709defbca381d01ee9d1ec","abstract_canon_sha256":"f2bfc32ff533f6a523c068ba20fb49a3a5fab66971948ef797139225107735d0"},"schema_version":"1.0"},"canonical_sha256":"1ca015fa3ff697d65b7135bc644a196be3fcfcf5cddf62fefbd327bf415ca60b","source":{"kind":"arxiv","id":"1710.01949","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.01949","created_at":"2026-05-18T00:01:47Z"},{"alias_kind":"arxiv_version","alias_value":"1710.01949v2","created_at":"2026-05-18T00:01:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.01949","created_at":"2026-05-18T00:01:47Z"},{"alias_kind":"pith_short_12","alias_value":"DSQBL6R762L5","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"DSQBL6R762L5MW3R","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"DSQBL6R7","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:DSQBL6R762L5MW3RGW6GISQZNP","target":"record","payload":{"canonical_record":{"source":{"id":"1710.01949","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-05T10:24:46Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"527c32e05da8d274ad55ecc0c2f19d091f450e9363709defbca381d01ee9d1ec","abstract_canon_sha256":"f2bfc32ff533f6a523c068ba20fb49a3a5fab66971948ef797139225107735d0"},"schema_version":"1.0"},"canonical_sha256":"1ca015fa3ff697d65b7135bc644a196be3fcfcf5cddf62fefbd327bf415ca60b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:47.418916Z","signature_b64":"NsPPdP9DrQ3UPn8Ks9aQ020PLudUs6OCZLGNfBrZ1wLx1EOA4Qi9CGcsHQAEiuO4XH0ToDoD0V/R7rABA4tjCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ca015fa3ff697d65b7135bc644a196be3fcfcf5cddf62fefbd327bf415ca60b","last_reissued_at":"2026-05-18T00:01:47.418166Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:47.418166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.01949","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":"2026-05-18T00:01:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0BQqXzYCRHpcrNKItlSFLGXDcB/V9gA9cCg46u5ibrPKa6U2al5aPkqJ6v9J1tcZsZAT+eGfAD9zR9V5WyfiCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T07:38:21.674719Z"},"content_sha256":"b22eaf1ec77d9c2c02c6d632a0b4fa7c9bc74c792600455402e95539c7709692","schema_version":"1.0","event_id":"sha256:b22eaf1ec77d9c2c02c6d632a0b4fa7c9bc74c792600455402e95539c7709692"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:DSQBL6R762L5MW3RGW6GISQZNP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semantic speech retrieval with a visually grounded model of untranscribed speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.CL","authors_text":"Gregory Shakhnarovich, Herman Kamper, Karen Livescu","submitted_at":"2017-10-05T10:24:46Z","abstract_excerpt":"There is growing interest in models that can learn from unlabelled speech paired with visual context. This setting is relevant for low-resource speech processing, robotics, and human language acquisition research. Here we study how a visually grounded speech model, trained on images of scenes paired with spoken captions, captures aspects of semantics. We use an external image tagger to generate soft text labels from images, which serve as targets for a neural model that maps untranscribed speech to (semantic) keyword labels. We introduce a newly collected data set of human semantic relevance j"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.01949","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":"2026-05-18T00:01:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6RfCbSdt0iBgpwbvHdcEQ9nnDYdbltNT4ext3gYTFqDJC0Ot1wShk3jrqZMq547xCrpiERc83sNGodNMPeKgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T07:38:21.675367Z"},"content_sha256":"fc94995e64ba9f2d403ac3901691beb6ad8d83a7405c3c4dc573fcc96f40cb68","schema_version":"1.0","event_id":"sha256:fc94995e64ba9f2d403ac3901691beb6ad8d83a7405c3c4dc573fcc96f40cb68"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DSQBL6R762L5MW3RGW6GISQZNP/bundle.json","state_url":"https://pith.science/pith/DSQBL6R762L5MW3RGW6GISQZNP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DSQBL6R762L5MW3RGW6GISQZNP/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":"2026-06-01T07:38:21Z","links":{"resolver":"https://pith.science/pith/DSQBL6R762L5MW3RGW6GISQZNP","bundle":"https://pith.science/pith/DSQBL6R762L5MW3RGW6GISQZNP/bundle.json","state":"https://pith.science/pith/DSQBL6R762L5MW3RGW6GISQZNP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DSQBL6R762L5MW3RGW6GISQZNP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:DSQBL6R762L5MW3RGW6GISQZNP","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":"f2bfc32ff533f6a523c068ba20fb49a3a5fab66971948ef797139225107735d0","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-05T10:24:46Z","title_canon_sha256":"527c32e05da8d274ad55ecc0c2f19d091f450e9363709defbca381d01ee9d1ec"},"schema_version":"1.0","source":{"id":"1710.01949","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.01949","created_at":"2026-05-18T00:01:47Z"},{"alias_kind":"arxiv_version","alias_value":"1710.01949v2","created_at":"2026-05-18T00:01:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.01949","created_at":"2026-05-18T00:01:47Z"},{"alias_kind":"pith_short_12","alias_value":"DSQBL6R762L5","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"DSQBL6R762L5MW3R","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"DSQBL6R7","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:fc94995e64ba9f2d403ac3901691beb6ad8d83a7405c3c4dc573fcc96f40cb68","target":"graph","created_at":"2026-05-18T00:01:47Z","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":"There is growing interest in models that can learn from unlabelled speech paired with visual context. This setting is relevant for low-resource speech processing, robotics, and human language acquisition research. Here we study how a visually grounded speech model, trained on images of scenes paired with spoken captions, captures aspects of semantics. We use an external image tagger to generate soft text labels from images, which serve as targets for a neural model that maps untranscribed speech to (semantic) keyword labels. We introduce a newly collected data set of human semantic relevance j","authors_text":"Gregory Shakhnarovich, Herman Kamper, Karen Livescu","cross_cats":["cs.CV","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-05T10:24:46Z","title":"Semantic speech retrieval with a visually grounded model of untranscribed speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.01949","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:b22eaf1ec77d9c2c02c6d632a0b4fa7c9bc74c792600455402e95539c7709692","target":"record","created_at":"2026-05-18T00:01:47Z","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":"f2bfc32ff533f6a523c068ba20fb49a3a5fab66971948ef797139225107735d0","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-05T10:24:46Z","title_canon_sha256":"527c32e05da8d274ad55ecc0c2f19d091f450e9363709defbca381d01ee9d1ec"},"schema_version":"1.0","source":{"id":"1710.01949","kind":"arxiv","version":2}},"canonical_sha256":"1ca015fa3ff697d65b7135bc644a196be3fcfcf5cddf62fefbd327bf415ca60b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ca015fa3ff697d65b7135bc644a196be3fcfcf5cddf62fefbd327bf415ca60b","first_computed_at":"2026-05-18T00:01:47.418166Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:47.418166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NsPPdP9DrQ3UPn8Ks9aQ020PLudUs6OCZLGNfBrZ1wLx1EOA4Qi9CGcsHQAEiuO4XH0ToDoD0V/R7rABA4tjCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:47.418916Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.01949","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b22eaf1ec77d9c2c02c6d632a0b4fa7c9bc74c792600455402e95539c7709692","sha256:fc94995e64ba9f2d403ac3901691beb6ad8d83a7405c3c4dc573fcc96f40cb68"],"state_sha256":"14f90866b5a5e1e56d8c87f0c75c2e33c39f7ba5498c97066b79420cbbfe6a7f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lcxWz6X8Cv2/EHykyYyv35iSm6U+/avI37rhB1pMMjyiwVKixAfMujio8BCiBqbTDca4s/h0yNYD+7ttfsmZBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T07:38:21.678197Z","bundle_sha256":"1da17dbd6b5b8aac7e5dcf37a6da4bc9b919f9a6e26cc3a99761a0af3842d2f0"}}