{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:FHPHTGRN5V4UUIGDYP5VM7CSNT","short_pith_number":"pith:FHPHTGRN","canonical_record":{"source":{"id":"1703.06618","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-20T06:56:33Z","cross_cats_sorted":[],"title_canon_sha256":"e5eb93002754d23461f11d5366151dddf0c517175595bd20b3befb3b70262540","abstract_canon_sha256":"864ae917f980ddf4d12f4f3c7dcddaddc85b1001afca51378571e3da453098e8"},"schema_version":"1.0"},"canonical_sha256":"29de799a2ded794a20c3c3fb567c526cdea83c1d4c5391b3d0387848c1d01ab6","source":{"kind":"arxiv","id":"1703.06618","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.06618","created_at":"2026-05-18T00:48:22Z"},{"alias_kind":"arxiv_version","alias_value":"1703.06618v1","created_at":"2026-05-18T00:48:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06618","created_at":"2026-05-18T00:48:22Z"},{"alias_kind":"pith_short_12","alias_value":"FHPHTGRN5V4U","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FHPHTGRN5V4UUIGD","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FHPHTGRN","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:FHPHTGRN5V4UUIGDYP5VM7CSNT","target":"record","payload":{"canonical_record":{"source":{"id":"1703.06618","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-20T06:56:33Z","cross_cats_sorted":[],"title_canon_sha256":"e5eb93002754d23461f11d5366151dddf0c517175595bd20b3befb3b70262540","abstract_canon_sha256":"864ae917f980ddf4d12f4f3c7dcddaddc85b1001afca51378571e3da453098e8"},"schema_version":"1.0"},"canonical_sha256":"29de799a2ded794a20c3c3fb567c526cdea83c1d4c5391b3d0387848c1d01ab6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:22.229168Z","signature_b64":"sDiVy6SlMNWnhqyajhS859dj00o4UXFr7Z3e77WL2NKub0AS/2gY45YrvMvRRu2iRM8TnRkxB/ul049kiZIfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29de799a2ded794a20c3c3fb567c526cdea83c1d4c5391b3d0387848c1d01ab6","last_reissued_at":"2026-05-18T00:48:22.228514Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:22.228514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.06618","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":"2026-05-18T00:48:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r//H2FMQ0X7V2Wbq2qVOqa18TphtjImFpMx4RQfbjV2bEF1hW7Qdk1BGTUx5LafPwqlUyf8IykQuo3YuxVhgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T08:23:46.790155Z"},"content_sha256":"c44635ba303f03970ac7f0873053373dec0be328ac730c6e29dc947b5ead5289","schema_version":"1.0","event_id":"sha256:c44635ba303f03970ac7f0873053373dec0be328ac730c6e29dc947b5ead5289"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:FHPHTGRN5V4UUIGDYP5VM7CSNT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Twitter100k: A Real-world Dataset for Weakly Supervised Cross-Media Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liang Zheng, Yi Yang, Yongfeng Huang, Yuting Hu","submitted_at":"2017-03-20T06:56:33Z","abstract_excerpt":"This paper contributes a new large-scale dataset for weakly supervised cross-media retrieval, named Twitter100k. Current datasets, such as Wikipedia, NUS Wide and Flickr30k, have two major limitations. First, these datasets are lacking in content diversity, i.e., only some pre-defined classes are covered. Second, texts in these datasets are written in well-organized language, leading to inconsistency with realistic applications. To overcome these drawbacks, the proposed Twitter100k dataset is characterized by two aspects: 1) it has 100,000 image-text pairs randomly crawled from Twitter and thu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06618","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":"2026-05-18T00:48:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5k0tQh8KshI/vTNVbQvKKL53nMcZXvV2zxA7+4qCZY2uGvSd3ix3JjEZVGQB1itO9SIDvUkglfDacp14PnoZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T08:23:46.790833Z"},"content_sha256":"928439bafcbb8ef3260b2685e7e0894f3e2bd5acc971af22d363946d3f976536","schema_version":"1.0","event_id":"sha256:928439bafcbb8ef3260b2685e7e0894f3e2bd5acc971af22d363946d3f976536"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FHPHTGRN5V4UUIGDYP5VM7CSNT/bundle.json","state_url":"https://pith.science/pith/FHPHTGRN5V4UUIGDYP5VM7CSNT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FHPHTGRN5V4UUIGDYP5VM7CSNT/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":"2026-06-11T08:23:46Z","links":{"resolver":"https://pith.science/pith/FHPHTGRN5V4UUIGDYP5VM7CSNT","bundle":"https://pith.science/pith/FHPHTGRN5V4UUIGDYP5VM7CSNT/bundle.json","state":"https://pith.science/pith/FHPHTGRN5V4UUIGDYP5VM7CSNT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FHPHTGRN5V4UUIGDYP5VM7CSNT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:FHPHTGRN5V4UUIGDYP5VM7CSNT","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":"864ae917f980ddf4d12f4f3c7dcddaddc85b1001afca51378571e3da453098e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-20T06:56:33Z","title_canon_sha256":"e5eb93002754d23461f11d5366151dddf0c517175595bd20b3befb3b70262540"},"schema_version":"1.0","source":{"id":"1703.06618","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.06618","created_at":"2026-05-18T00:48:22Z"},{"alias_kind":"arxiv_version","alias_value":"1703.06618v1","created_at":"2026-05-18T00:48:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06618","created_at":"2026-05-18T00:48:22Z"},{"alias_kind":"pith_short_12","alias_value":"FHPHTGRN5V4U","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FHPHTGRN5V4UUIGD","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FHPHTGRN","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:928439bafcbb8ef3260b2685e7e0894f3e2bd5acc971af22d363946d3f976536","target":"graph","created_at":"2026-05-18T00:48:22Z","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":"This paper contributes a new large-scale dataset for weakly supervised cross-media retrieval, named Twitter100k. Current datasets, such as Wikipedia, NUS Wide and Flickr30k, have two major limitations. First, these datasets are lacking in content diversity, i.e., only some pre-defined classes are covered. Second, texts in these datasets are written in well-organized language, leading to inconsistency with realistic applications. To overcome these drawbacks, the proposed Twitter100k dataset is characterized by two aspects: 1) it has 100,000 image-text pairs randomly crawled from Twitter and thu","authors_text":"Liang Zheng, Yi Yang, Yongfeng Huang, Yuting Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-20T06:56:33Z","title":"Twitter100k: A Real-world Dataset for Weakly Supervised Cross-Media Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06618","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:c44635ba303f03970ac7f0873053373dec0be328ac730c6e29dc947b5ead5289","target":"record","created_at":"2026-05-18T00:48:22Z","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":"864ae917f980ddf4d12f4f3c7dcddaddc85b1001afca51378571e3da453098e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-20T06:56:33Z","title_canon_sha256":"e5eb93002754d23461f11d5366151dddf0c517175595bd20b3befb3b70262540"},"schema_version":"1.0","source":{"id":"1703.06618","kind":"arxiv","version":1}},"canonical_sha256":"29de799a2ded794a20c3c3fb567c526cdea83c1d4c5391b3d0387848c1d01ab6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29de799a2ded794a20c3c3fb567c526cdea83c1d4c5391b3d0387848c1d01ab6","first_computed_at":"2026-05-18T00:48:22.228514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:22.228514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sDiVy6SlMNWnhqyajhS859dj00o4UXFr7Z3e77WL2NKub0AS/2gY45YrvMvRRu2iRM8TnRkxB/ul049kiZIfDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:22.229168Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.06618","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c44635ba303f03970ac7f0873053373dec0be328ac730c6e29dc947b5ead5289","sha256:928439bafcbb8ef3260b2685e7e0894f3e2bd5acc971af22d363946d3f976536"],"state_sha256":"6007a04071d2bef7f7dee4af7c2bacb9ea81b9d98a219a3994adf2a710fa2fa3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UVgakCl9GeE6S7BS6SPYb6xnLMBx8WBBg08SFIOinMevahjMptho+xlU3tRlIaIgCigVtZe9ppRYsE3yvDlOCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T08:23:46.794851Z","bundle_sha256":"32f6d0930b10a02a7a76c53ced59711c67ccdb2ba53cf33a6858a4663daef286"}}