{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:UIDR3EPU4NKLYVO3GLNBMTDWXD","short_pith_number":"pith:UIDR3EPU","canonical_record":{"source":{"id":"1702.01991","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2017-02-07T13:02:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f2ff985266660b217fa06d0389b440c364f59a18fa3c16cee0c574b170828e07","abstract_canon_sha256":"c5b4f2fc90a7af82afb8fcd5839651f774fff3e9ac8e6d959bfdc7d26a7bd138"},"schema_version":"1.0"},"canonical_sha256":"a2071d91f4e354bc55db32da164c76b8d902fb6fd44fa3509b1442d96f8f18e3","source":{"kind":"arxiv","id":"1702.01991","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.01991","created_at":"2026-05-18T00:02:13Z"},{"alias_kind":"arxiv_version","alias_value":"1702.01991v3","created_at":"2026-05-18T00:02:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.01991","created_at":"2026-05-18T00:02:13Z"},{"alias_kind":"pith_short_12","alias_value":"UIDR3EPU4NKL","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"UIDR3EPU4NKLYVO3","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"UIDR3EPU","created_at":"2026-05-18T12:31:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:UIDR3EPU4NKLYVO3GLNBMTDWXD","target":"record","payload":{"canonical_record":{"source":{"id":"1702.01991","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2017-02-07T13:02:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f2ff985266660b217fa06d0389b440c364f59a18fa3c16cee0c574b170828e07","abstract_canon_sha256":"c5b4f2fc90a7af82afb8fcd5839651f774fff3e9ac8e6d959bfdc7d26a7bd138"},"schema_version":"1.0"},"canonical_sha256":"a2071d91f4e354bc55db32da164c76b8d902fb6fd44fa3509b1442d96f8f18e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:13.677890Z","signature_b64":"KuGkRC91oIrOGEnHoXK9iF9bjqeGTVCWl0eF+6aCksI357Ws/jsHaG+XOyLtMYzPhc3DZPCaaTK6KiocHgYsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2071d91f4e354bc55db32da164c76b8d902fb6fd44fa3509b1442d96f8f18e3","last_reissued_at":"2026-05-18T00:02:13.677269Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:13.677269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.01991","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:02:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RNcFSuTjWR8wKWBYkaiBTzFLtpryi25ZsfINIM8dRxo3YdfQ3dlD+UTgpIO/qDUFcAEI70Givjgw+YypklG/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T19:53:33.243024Z"},"content_sha256":"d5bdc418a8a3e1b5296c6da59632b8888dab96d0ac3da5fe1860672cfbed1680","schema_version":"1.0","event_id":"sha256:d5bdc418a8a3e1b5296c6da59632b8888dab96d0ac3da5fe1860672cfbed1680"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:UIDR3EPU4NKLYVO3GLNBMTDWXD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Representations of language in a model of visually grounded speech signal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Afra Alishahi, Grzegorz Chrupa{\\l}a, Lieke Gelderloos","submitted_at":"2017-02-07T13:02:09Z","abstract_excerpt":"We present a visually grounded model of speech perception which projects spoken utterances and images to a joint semantic space. We use a multi-layer recurrent highway network to model the temporal nature of spoken speech, and show that it learns to extract both form and meaning-based linguistic knowledge from the input signal. We carry out an in-depth analysis of the representations used by different components of the trained model and show that encoding of semantic aspects tends to become richer as we go up the hierarchy of layers, whereas encoding of form-related aspects of the language inp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.01991","kind":"arxiv","version":3},"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":"2026-05-18T00:02:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h4Sv1XbyCFCDTCbC8fmpJvK8yGdBXF2K/Dd5fTV2P6P7QWjVAEqf9Or7VG3iR7NwaJoMYs4f/b4W6JgjATvYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T19:53:33.243386Z"},"content_sha256":"a273ad4f44bd22bfffd807c978a62c39446b48c4cfd2c767fd0a1a06f4201d62","schema_version":"1.0","event_id":"sha256:a273ad4f44bd22bfffd807c978a62c39446b48c4cfd2c767fd0a1a06f4201d62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UIDR3EPU4NKLYVO3GLNBMTDWXD/bundle.json","state_url":"https://pith.science/pith/UIDR3EPU4NKLYVO3GLNBMTDWXD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UIDR3EPU4NKLYVO3GLNBMTDWXD/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":"2026-06-28T19:53:33Z","links":{"resolver":"https://pith.science/pith/UIDR3EPU4NKLYVO3GLNBMTDWXD","bundle":"https://pith.science/pith/UIDR3EPU4NKLYVO3GLNBMTDWXD/bundle.json","state":"https://pith.science/pith/UIDR3EPU4NKLYVO3GLNBMTDWXD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UIDR3EPU4NKLYVO3GLNBMTDWXD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:UIDR3EPU4NKLYVO3GLNBMTDWXD","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":"c5b4f2fc90a7af82afb8fcd5839651f774fff3e9ac8e6d959bfdc7d26a7bd138","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2017-02-07T13:02:09Z","title_canon_sha256":"f2ff985266660b217fa06d0389b440c364f59a18fa3c16cee0c574b170828e07"},"schema_version":"1.0","source":{"id":"1702.01991","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.01991","created_at":"2026-05-18T00:02:13Z"},{"alias_kind":"arxiv_version","alias_value":"1702.01991v3","created_at":"2026-05-18T00:02:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.01991","created_at":"2026-05-18T00:02:13Z"},{"alias_kind":"pith_short_12","alias_value":"UIDR3EPU4NKL","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"UIDR3EPU4NKLYVO3","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"UIDR3EPU","created_at":"2026-05-18T12:31:46Z"}],"graph_snapshots":[{"event_id":"sha256:a273ad4f44bd22bfffd807c978a62c39446b48c4cfd2c767fd0a1a06f4201d62","target":"graph","created_at":"2026-05-18T00:02:13Z","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":"We present a visually grounded model of speech perception which projects spoken utterances and images to a joint semantic space. We use a multi-layer recurrent highway network to model the temporal nature of spoken speech, and show that it learns to extract both form and meaning-based linguistic knowledge from the input signal. We carry out an in-depth analysis of the representations used by different components of the trained model and show that encoding of semantic aspects tends to become richer as we go up the hierarchy of layers, whereas encoding of form-related aspects of the language inp","authors_text":"Afra Alishahi, Grzegorz Chrupa{\\l}a, Lieke Gelderloos","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2017-02-07T13:02:09Z","title":"Representations of language in a model of visually grounded speech signal"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.01991","kind":"arxiv","version":3},"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:d5bdc418a8a3e1b5296c6da59632b8888dab96d0ac3da5fe1860672cfbed1680","target":"record","created_at":"2026-05-18T00:02:13Z","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":"c5b4f2fc90a7af82afb8fcd5839651f774fff3e9ac8e6d959bfdc7d26a7bd138","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2017-02-07T13:02:09Z","title_canon_sha256":"f2ff985266660b217fa06d0389b440c364f59a18fa3c16cee0c574b170828e07"},"schema_version":"1.0","source":{"id":"1702.01991","kind":"arxiv","version":3}},"canonical_sha256":"a2071d91f4e354bc55db32da164c76b8d902fb6fd44fa3509b1442d96f8f18e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2071d91f4e354bc55db32da164c76b8d902fb6fd44fa3509b1442d96f8f18e3","first_computed_at":"2026-05-18T00:02:13.677269Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:13.677269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KuGkRC91oIrOGEnHoXK9iF9bjqeGTVCWl0eF+6aCksI357Ws/jsHaG+XOyLtMYzPhc3DZPCaaTK6KiocHgYsAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:13.677890Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.01991","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5bdc418a8a3e1b5296c6da59632b8888dab96d0ac3da5fe1860672cfbed1680","sha256:a273ad4f44bd22bfffd807c978a62c39446b48c4cfd2c767fd0a1a06f4201d62"],"state_sha256":"dbfade222103b2465d40b0e625bdb134c1262a7de898a15146ee4e979485362f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fUxsPtNIw2lnXKEba5oEXIdZbYkyeR08ZegNzPa1vZKxiP8sH66fWUiF5vDGXpo+cyKdWKUJ0vhE4oq4BBEHDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T19:53:33.245302Z","bundle_sha256":"fab8775bef452a43644744f819b6d608c82346f5fc815c6f09dbb81fd848fe4b"}}