{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:CF5PXRLVBXPBRYIRA5X5MSFEEQ","short_pith_number":"pith:CF5PXRLV","canonical_record":{"source":{"id":"1507.05670","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-20T22:43:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"977d7b6b99e51066985f8ae4becfdb595602a4e08c1c9d3bddb1eeca2567e9af","abstract_canon_sha256":"244be3818d2257cf1ebfbc3246e36dab694d1c71c25082c1fc0b561414de3715"},"schema_version":"1.0"},"canonical_sha256":"117afbc5750dde18e111076fd648a424215bf88e8ff659c86cbf1a1e2775ed3a","source":{"kind":"arxiv","id":"1507.05670","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.05670","created_at":"2026-05-18T01:27:23Z"},{"alias_kind":"arxiv_version","alias_value":"1507.05670v2","created_at":"2026-05-18T01:27:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.05670","created_at":"2026-05-18T01:27:23Z"},{"alias_kind":"pith_short_12","alias_value":"CF5PXRLVBXPB","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"CF5PXRLVBXPBRYIR","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"CF5PXRLV","created_at":"2026-05-18T12:29:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:CF5PXRLVBXPBRYIRA5X5MSFEEQ","target":"record","payload":{"canonical_record":{"source":{"id":"1507.05670","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-20T22:43:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"977d7b6b99e51066985f8ae4becfdb595602a4e08c1c9d3bddb1eeca2567e9af","abstract_canon_sha256":"244be3818d2257cf1ebfbc3246e36dab694d1c71c25082c1fc0b561414de3715"},"schema_version":"1.0"},"canonical_sha256":"117afbc5750dde18e111076fd648a424215bf88e8ff659c86cbf1a1e2775ed3a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:27:23.049559Z","signature_b64":"2WCXIFvQuK69K8Cy+tQUd1ZQs5yEZ3EsCSn8W0PMmXNd+kW8y15CAJ3k9CV1pCBA3uFtG3j280/A8zNsF5OqDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"117afbc5750dde18e111076fd648a424215bf88e8ff659c86cbf1a1e2775ed3a","last_reissued_at":"2026-05-18T01:27:23.048975Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:27:23.048975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1507.05670","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":"2026-05-18T01:27:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ywJ4mRmzdHDaP9VrABbTe31ZtBh2OoR59oW0GvcK6GKWF17WL08mOfPsAsE+I4pDM8or6koeK8BUVLw7BP51Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T00:01:08.019441Z"},"content_sha256":"8758a5122e2c8620809c419b310050ba2c35b4b14d862ab1ef85e86c86677327","schema_version":"1.0","event_id":"sha256:8758a5122e2c8620809c419b310050ba2c35b4b14d862ab1ef85e86c86677327"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:CF5PXRLVBXPBRYIRA5X5MSFEEQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Building a Large-scale Multimodal Knowledge Base System for Answering Visual Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ce Zhang, Christopher R\\'e, Li Fei-Fei, Yuke Zhu","submitted_at":"2015-07-20T22:43:51Z","abstract_excerpt":"The complexity of the visual world creates significant challenges for comprehensive visual understanding. In spite of recent successes in visual recognition, today's vision systems would still struggle to deal with visual queries that require a deeper reasoning. We propose a knowledge base (KB) framework to handle an assortment of visual queries, without the need to train new classifiers for new tasks. Building such a large-scale multimodal KB presents a major challenge of scalability. We cast a large-scale MRF into a KB representation, incorporating visual, textual and structured data, as wel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.05670","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":"2026-05-18T01:27:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p82zBneZTNBtqWR3BlfR0viitrG0iGRUVRQjRK6HhARn3fUvFRsRDSEKBQm1VvHUqG2rtUlVUVJ363Efh1wDCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T00:01:08.020152Z"},"content_sha256":"12e4fc27c0d5514d4707e380dcd5a10ea3f4f049ee5280ee9aeec1f1eb07e2ec","schema_version":"1.0","event_id":"sha256:12e4fc27c0d5514d4707e380dcd5a10ea3f4f049ee5280ee9aeec1f1eb07e2ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CF5PXRLVBXPBRYIRA5X5MSFEEQ/bundle.json","state_url":"https://pith.science/pith/CF5PXRLVBXPBRYIRA5X5MSFEEQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CF5PXRLVBXPBRYIRA5X5MSFEEQ/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":"2026-05-19T00:01:08Z","links":{"resolver":"https://pith.science/pith/CF5PXRLVBXPBRYIRA5X5MSFEEQ","bundle":"https://pith.science/pith/CF5PXRLVBXPBRYIRA5X5MSFEEQ/bundle.json","state":"https://pith.science/pith/CF5PXRLVBXPBRYIRA5X5MSFEEQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CF5PXRLVBXPBRYIRA5X5MSFEEQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:CF5PXRLVBXPBRYIRA5X5MSFEEQ","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":"244be3818d2257cf1ebfbc3246e36dab694d1c71c25082c1fc0b561414de3715","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-20T22:43:51Z","title_canon_sha256":"977d7b6b99e51066985f8ae4becfdb595602a4e08c1c9d3bddb1eeca2567e9af"},"schema_version":"1.0","source":{"id":"1507.05670","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.05670","created_at":"2026-05-18T01:27:23Z"},{"alias_kind":"arxiv_version","alias_value":"1507.05670v2","created_at":"2026-05-18T01:27:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.05670","created_at":"2026-05-18T01:27:23Z"},{"alias_kind":"pith_short_12","alias_value":"CF5PXRLVBXPB","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"CF5PXRLVBXPBRYIR","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"CF5PXRLV","created_at":"2026-05-18T12:29:14Z"}],"graph_snapshots":[{"event_id":"sha256:12e4fc27c0d5514d4707e380dcd5a10ea3f4f049ee5280ee9aeec1f1eb07e2ec","target":"graph","created_at":"2026-05-18T01:27:23Z","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 complexity of the visual world creates significant challenges for comprehensive visual understanding. In spite of recent successes in visual recognition, today's vision systems would still struggle to deal with visual queries that require a deeper reasoning. We propose a knowledge base (KB) framework to handle an assortment of visual queries, without the need to train new classifiers for new tasks. Building such a large-scale multimodal KB presents a major challenge of scalability. We cast a large-scale MRF into a KB representation, incorporating visual, textual and structured data, as wel","authors_text":"Ce Zhang, Christopher R\\'e, Li Fei-Fei, Yuke Zhu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-20T22:43:51Z","title":"Building a Large-scale Multimodal Knowledge Base System for Answering Visual Queries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.05670","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":"sha256:8758a5122e2c8620809c419b310050ba2c35b4b14d862ab1ef85e86c86677327","target":"record","created_at":"2026-05-18T01:27:23Z","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":"244be3818d2257cf1ebfbc3246e36dab694d1c71c25082c1fc0b561414de3715","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-20T22:43:51Z","title_canon_sha256":"977d7b6b99e51066985f8ae4becfdb595602a4e08c1c9d3bddb1eeca2567e9af"},"schema_version":"1.0","source":{"id":"1507.05670","kind":"arxiv","version":2}},"canonical_sha256":"117afbc5750dde18e111076fd648a424215bf88e8ff659c86cbf1a1e2775ed3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"117afbc5750dde18e111076fd648a424215bf88e8ff659c86cbf1a1e2775ed3a","first_computed_at":"2026-05-18T01:27:23.048975Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:27:23.048975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2WCXIFvQuK69K8Cy+tQUd1ZQs5yEZ3EsCSn8W0PMmXNd+kW8y15CAJ3k9CV1pCBA3uFtG3j280/A8zNsF5OqDw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:27:23.049559Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.05670","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8758a5122e2c8620809c419b310050ba2c35b4b14d862ab1ef85e86c86677327","sha256:12e4fc27c0d5514d4707e380dcd5a10ea3f4f049ee5280ee9aeec1f1eb07e2ec"],"state_sha256":"f6a90ecd98e3895870cbe129a7714fcd7c80caae08fc65d44e3da06224db6ce1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MNOMrGikXdXIp5rONmKvF9sXjBQPHTpHVyWglSeA1DcfsZxY6+MtUcENDsB70R1fJzLFNSaB4JpTlOKeTChCDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T00:01:08.022281Z","bundle_sha256":"6ca973466bbc80390a53bc142eecfa10e962dbf5deb300588947e32925b3fba8"}}