{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:TJMWSIWPEGLFXBH3MCLMFMHUST","short_pith_number":"pith:TJMWSIWP","canonical_record":{"source":{"id":"1904.06038","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-04-12T05:18:35Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5429dbc1ebffdd0ffaceebea26f93e51d195018249599e250ebeaa29d44c46d5","abstract_canon_sha256":"0203c13798945cfcbafd555bc84a949c6cb7cf203c267f5aa4e0c4cd977b6e10"},"schema_version":"1.0"},"canonical_sha256":"9a596922cf21965b84fb6096c2b0f494e9024c80b3f05ee79de1301629d28f09","source":{"kind":"arxiv","id":"1904.06038","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.06038","created_at":"2026-05-17T23:48:44Z"},{"alias_kind":"arxiv_version","alias_value":"1904.06038v1","created_at":"2026-05-17T23:48:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06038","created_at":"2026-05-17T23:48:44Z"},{"alias_kind":"pith_short_12","alias_value":"TJMWSIWPEGLF","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"TJMWSIWPEGLFXBH3","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"TJMWSIWP","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:TJMWSIWPEGLFXBH3MCLMFMHUST","target":"record","payload":{"canonical_record":{"source":{"id":"1904.06038","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-04-12T05:18:35Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5429dbc1ebffdd0ffaceebea26f93e51d195018249599e250ebeaa29d44c46d5","abstract_canon_sha256":"0203c13798945cfcbafd555bc84a949c6cb7cf203c267f5aa4e0c4cd977b6e10"},"schema_version":"1.0"},"canonical_sha256":"9a596922cf21965b84fb6096c2b0f494e9024c80b3f05ee79de1301629d28f09","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:44.432307Z","signature_b64":"jX/sadntBr9wS1se6E6TwxP2jsSpaa4qnqLZl49YGkxWsk7+ZI8pvH2aVwlpWJ3daFDYrYT6fb0FROfR9A/ZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a596922cf21965b84fb6096c2b0f494e9024c80b3f05ee79de1301629d28f09","last_reissued_at":"2026-05-17T23:48:44.431782Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:44.431782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.06038","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:48:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6fDSLzpnxJyxm47dTj8GOneFHOker46T8BE+rNJ8AOPBtaT7WVPZ2gxUkQn5qgo/er7UPIhWhDE1wO7FkbEtDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T10:19:01.255286Z"},"content_sha256":"bcf71074895f4f8733a3a7fa5e7358a72e6db1c598a82e9dd3fb6f048a08fe30","schema_version":"1.0","event_id":"sha256:bcf71074895f4f8733a3a7fa5e7358a72e6db1c598a82e9dd3fb6f048a08fe30"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:TJMWSIWPEGLFXBH3MCLMFMHUST","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating the Representational Hub of Language and Vision Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Ece Takmaz, Raffaella Bernardi, Raquel Fern\\'andez, Ravi Shekhar","submitted_at":"2019-04-12T05:18:35Z","abstract_excerpt":"The multimodal models used in the emerging field at the intersection of computational linguistics and computer vision implement the bottom-up processing of the `Hub and Spoke' architecture proposed in cognitive science to represent how the brain processes and combines multi-sensory inputs. In particular, the Hub is implemented as a neural network encoder. We investigate the effect on this encoder of various vision-and-language tasks proposed in the literature: visual question answering, visual reference resolution, and visually grounded dialogue. To measure the quality of the representations l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06038","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":""},"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":"2026-05-17T23:48:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bEt0IOCy9LNIAI/2U0UnmGIPx5ABKmf1r8CGawMvj8uCGZHoLpKIFDGyYvNf7u4A0MZ4WU/8rRcMzI4PhFIRCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T10:19:01.255992Z"},"content_sha256":"1faf6da044c889ce1ce59448654c8588ae7745703b36a63ce98cb7c2a35589b4","schema_version":"1.0","event_id":"sha256:1faf6da044c889ce1ce59448654c8588ae7745703b36a63ce98cb7c2a35589b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TJMWSIWPEGLFXBH3MCLMFMHUST/bundle.json","state_url":"https://pith.science/pith/TJMWSIWPEGLFXBH3MCLMFMHUST/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TJMWSIWPEGLFXBH3MCLMFMHUST/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":"2026-06-07T10:19:01Z","links":{"resolver":"https://pith.science/pith/TJMWSIWPEGLFXBH3MCLMFMHUST","bundle":"https://pith.science/pith/TJMWSIWPEGLFXBH3MCLMFMHUST/bundle.json","state":"https://pith.science/pith/TJMWSIWPEGLFXBH3MCLMFMHUST/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TJMWSIWPEGLFXBH3MCLMFMHUST/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TJMWSIWPEGLFXBH3MCLMFMHUST","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":"0203c13798945cfcbafd555bc84a949c6cb7cf203c267f5aa4e0c4cd977b6e10","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-04-12T05:18:35Z","title_canon_sha256":"5429dbc1ebffdd0ffaceebea26f93e51d195018249599e250ebeaa29d44c46d5"},"schema_version":"1.0","source":{"id":"1904.06038","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.06038","created_at":"2026-05-17T23:48:44Z"},{"alias_kind":"arxiv_version","alias_value":"1904.06038v1","created_at":"2026-05-17T23:48:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06038","created_at":"2026-05-17T23:48:44Z"},{"alias_kind":"pith_short_12","alias_value":"TJMWSIWPEGLF","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"TJMWSIWPEGLFXBH3","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"TJMWSIWP","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:1faf6da044c889ce1ce59448654c8588ae7745703b36a63ce98cb7c2a35589b4","target":"graph","created_at":"2026-05-17T23:48:44Z","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":"The multimodal models used in the emerging field at the intersection of computational linguistics and computer vision implement the bottom-up processing of the `Hub and Spoke' architecture proposed in cognitive science to represent how the brain processes and combines multi-sensory inputs. In particular, the Hub is implemented as a neural network encoder. We investigate the effect on this encoder of various vision-and-language tasks proposed in the literature: visual question answering, visual reference resolution, and visually grounded dialogue. To measure the quality of the representations l","authors_text":"Ece Takmaz, Raffaella Bernardi, Raquel Fern\\'andez, Ravi Shekhar","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-04-12T05:18:35Z","title":"Evaluating the Representational Hub of Language and Vision Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06038","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:bcf71074895f4f8733a3a7fa5e7358a72e6db1c598a82e9dd3fb6f048a08fe30","target":"record","created_at":"2026-05-17T23:48:44Z","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":"0203c13798945cfcbafd555bc84a949c6cb7cf203c267f5aa4e0c4cd977b6e10","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-04-12T05:18:35Z","title_canon_sha256":"5429dbc1ebffdd0ffaceebea26f93e51d195018249599e250ebeaa29d44c46d5"},"schema_version":"1.0","source":{"id":"1904.06038","kind":"arxiv","version":1}},"canonical_sha256":"9a596922cf21965b84fb6096c2b0f494e9024c80b3f05ee79de1301629d28f09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a596922cf21965b84fb6096c2b0f494e9024c80b3f05ee79de1301629d28f09","first_computed_at":"2026-05-17T23:48:44.431782Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:44.431782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jX/sadntBr9wS1se6E6TwxP2jsSpaa4qnqLZl49YGkxWsk7+ZI8pvH2aVwlpWJ3daFDYrYT6fb0FROfR9A/ZBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:44.432307Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.06038","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcf71074895f4f8733a3a7fa5e7358a72e6db1c598a82e9dd3fb6f048a08fe30","sha256:1faf6da044c889ce1ce59448654c8588ae7745703b36a63ce98cb7c2a35589b4"],"state_sha256":"2ba844254a76ff7f0628811904cfa90a71f847442d30ba2180c1511ece87ddb1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8F5L0vwyXIEN7VLxr6qOerVyquGpdmei2a06SEoxOSt/v0MZsBlfSYgwLAeOSqPOKECXCCsEQ4moE3+4JLIOBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T10:19:01.259705Z","bundle_sha256":"5dfd1f6b975ceb192b85434eb9902de2d5e3e91e1b7abafd6923b64435d24044"}}