{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:QQ6FTOJFGQMZPTXOINJPXHRMUS","short_pith_number":"pith:QQ6FTOJF","canonical_record":{"source":{"id":"1612.07833","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-22T22:44:17Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e0c9c456b688b883697f59b5dc33c2ee64537327b3a85c715b8900078af772a7","abstract_canon_sha256":"2bb55a885791f72cae961b5893bca825d1975ec23de12a2c8e99df181f45ab0f"},"schema_version":"1.0"},"canonical_sha256":"843c59b925341997ceee4352fb9e2ca4bf36800daa394581c3704ccd0b6df69a","source":{"kind":"arxiv","id":"1612.07833","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.07833","created_at":"2026-05-18T00:54:05Z"},{"alias_kind":"arxiv_version","alias_value":"1612.07833v1","created_at":"2026-05-18T00:54:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.07833","created_at":"2026-05-18T00:54:05Z"},{"alias_kind":"pith_short_12","alias_value":"QQ6FTOJFGQMZ","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"QQ6FTOJFGQMZPTXO","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"QQ6FTOJF","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:QQ6FTOJFGQMZPTXOINJPXHRMUS","target":"record","payload":{"canonical_record":{"source":{"id":"1612.07833","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-22T22:44:17Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e0c9c456b688b883697f59b5dc33c2ee64537327b3a85c715b8900078af772a7","abstract_canon_sha256":"2bb55a885791f72cae961b5893bca825d1975ec23de12a2c8e99df181f45ab0f"},"schema_version":"1.0"},"canonical_sha256":"843c59b925341997ceee4352fb9e2ca4bf36800daa394581c3704ccd0b6df69a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:54:05.603001Z","signature_b64":"oQVcXm5lOQnoJXdCmv+K1TaHTN0S1RXAmLiPLcgqodR18faO9f7KoXnMVJpZKqum05Yz+JPuNS7yF/SB2qd9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"843c59b925341997ceee4352fb9e2ca4bf36800daa394581c3704ccd0b6df69a","last_reissued_at":"2026-05-18T00:54:05.602421Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:54:05.602421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.07833","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":"2026-05-18T00:54:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yiFJ5xg+QCismlt0DJf/XKRbEbpaFp5rzqqL2MC7f0D0uMlHcTtARwksAdKFQFnORRY+oVnkLq7UHvF5FVX6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T08:36:37.225678Z"},"content_sha256":"29f79c000ca1406cf2e62fdc0858d3e2b035d619c9daf3ac308142860990d4bb","schema_version":"1.0","event_id":"sha256:29f79c000ca1406cf2e62fdc0858d3e2b035d619c9daf3ac308142860990d4bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:QQ6FTOJFGQMZPTXOINJPXHRMUS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Image and Text Simultaneously: a Dual Vision-Language Machine Comprehension Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Fei Sha, Nan Ding, Radu Soricut, Sebastian Goodman","submitted_at":"2016-12-22T22:44:17Z","abstract_excerpt":"We introduce a new multi-modal task for computer systems, posed as a combined vision-language comprehension challenge: identifying the most suitable text describing a scene, given several similar options. Accomplishing the task entails demonstrating comprehension beyond just recognizing \"keywords\" (or key-phrases) and their corresponding visual concepts. Instead, it requires an alignment between the representations of the two modalities that achieves a visually-grounded \"understanding\" of various linguistic elements and their dependencies. This new task also admits an easy-to-compute and well-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.07833","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":"2026-05-18T00:54:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a0G+HUZadaIGhuoIrJCuQm/+eRHnXCp24zEoV//cqG1G4PUnOw4MzpLUpQEjjtrGZwMzdII7pUkxGnTjXkqoDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T08:36:37.226034Z"},"content_sha256":"75f3f807d2bd515b39292f5e33ff3d062af5e8069868c3779f026b1f5e7e7325","schema_version":"1.0","event_id":"sha256:75f3f807d2bd515b39292f5e33ff3d062af5e8069868c3779f026b1f5e7e7325"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QQ6FTOJFGQMZPTXOINJPXHRMUS/bundle.json","state_url":"https://pith.science/pith/QQ6FTOJFGQMZPTXOINJPXHRMUS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QQ6FTOJFGQMZPTXOINJPXHRMUS/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":"2026-06-04T08:36:37Z","links":{"resolver":"https://pith.science/pith/QQ6FTOJFGQMZPTXOINJPXHRMUS","bundle":"https://pith.science/pith/QQ6FTOJFGQMZPTXOINJPXHRMUS/bundle.json","state":"https://pith.science/pith/QQ6FTOJFGQMZPTXOINJPXHRMUS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QQ6FTOJFGQMZPTXOINJPXHRMUS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:QQ6FTOJFGQMZPTXOINJPXHRMUS","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":"2bb55a885791f72cae961b5893bca825d1975ec23de12a2c8e99df181f45ab0f","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-22T22:44:17Z","title_canon_sha256":"e0c9c456b688b883697f59b5dc33c2ee64537327b3a85c715b8900078af772a7"},"schema_version":"1.0","source":{"id":"1612.07833","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.07833","created_at":"2026-05-18T00:54:05Z"},{"alias_kind":"arxiv_version","alias_value":"1612.07833v1","created_at":"2026-05-18T00:54:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.07833","created_at":"2026-05-18T00:54:05Z"},{"alias_kind":"pith_short_12","alias_value":"QQ6FTOJFGQMZ","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"QQ6FTOJFGQMZPTXO","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"QQ6FTOJF","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:75f3f807d2bd515b39292f5e33ff3d062af5e8069868c3779f026b1f5e7e7325","target":"graph","created_at":"2026-05-18T00:54:05Z","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 introduce a new multi-modal task for computer systems, posed as a combined vision-language comprehension challenge: identifying the most suitable text describing a scene, given several similar options. Accomplishing the task entails demonstrating comprehension beyond just recognizing \"keywords\" (or key-phrases) and their corresponding visual concepts. Instead, it requires an alignment between the representations of the two modalities that achieves a visually-grounded \"understanding\" of various linguistic elements and their dependencies. This new task also admits an easy-to-compute and well-","authors_text":"Fei Sha, Nan Ding, Radu Soricut, Sebastian Goodman","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-22T22:44:17Z","title":"Understanding Image and Text Simultaneously: a Dual Vision-Language Machine Comprehension Task"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.07833","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":"sha256:29f79c000ca1406cf2e62fdc0858d3e2b035d619c9daf3ac308142860990d4bb","target":"record","created_at":"2026-05-18T00:54:05Z","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":"2bb55a885791f72cae961b5893bca825d1975ec23de12a2c8e99df181f45ab0f","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-22T22:44:17Z","title_canon_sha256":"e0c9c456b688b883697f59b5dc33c2ee64537327b3a85c715b8900078af772a7"},"schema_version":"1.0","source":{"id":"1612.07833","kind":"arxiv","version":1}},"canonical_sha256":"843c59b925341997ceee4352fb9e2ca4bf36800daa394581c3704ccd0b6df69a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"843c59b925341997ceee4352fb9e2ca4bf36800daa394581c3704ccd0b6df69a","first_computed_at":"2026-05-18T00:54:05.602421Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:54:05.602421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oQVcXm5lOQnoJXdCmv+K1TaHTN0S1RXAmLiPLcgqodR18faO9f7KoXnMVJpZKqum05Yz+JPuNS7yF/SB2qd9AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:54:05.603001Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.07833","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29f79c000ca1406cf2e62fdc0858d3e2b035d619c9daf3ac308142860990d4bb","sha256:75f3f807d2bd515b39292f5e33ff3d062af5e8069868c3779f026b1f5e7e7325"],"state_sha256":"46fd9d3080dca70aea1b02487b81972cec07ea899cf4a7c3a258c8c7b708980a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KLeL5ksAxkiid5hmVDqq4AGrRH9tOBE7Q4Zq/ps7zsFufFn6jXpOdWRt8V9IE9/GzsUQ+74Q5iGwoeVnK/2ACQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T08:36:37.228137Z","bundle_sha256":"6eaa19220e7751b8cef560c4a5631f8c6c2dc0f5142bb8e07da45393f3c9f712"}}