{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:IUJFID5NBHUU6VNGCRWQTFKO6G","short_pith_number":"pith:IUJFID5N","canonical_record":{"source":{"id":"2104.02605","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-21T05:43:29Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"ea80e642cf9b85f52a40c421cb5f9569c086479ac679486d79c7519335b906c5","abstract_canon_sha256":"734aaf60b424bcd3103ae2c084f2094199a180439a24ad0a69068ae7e4083759"},"schema_version":"1.0"},"canonical_sha256":"4512540fad09e94f55a6146d09954ef18eac93c0d14bcf0ad8ad444e444c7a6b","source":{"kind":"arxiv","id":"2104.02605","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.02605","created_at":"2026-07-05T02:29:50Z"},{"alias_kind":"arxiv_version","alias_value":"2104.02605v1","created_at":"2026-07-05T02:29:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02605","created_at":"2026-07-05T02:29:50Z"},{"alias_kind":"pith_short_12","alias_value":"IUJFID5NBHUU","created_at":"2026-07-05T02:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"IUJFID5NBHUU6VNG","created_at":"2026-07-05T02:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"IUJFID5N","created_at":"2026-07-05T02:29:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:IUJFID5NBHUU6VNGCRWQTFKO6G","target":"record","payload":{"canonical_record":{"source":{"id":"2104.02605","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-21T05:43:29Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"ea80e642cf9b85f52a40c421cb5f9569c086479ac679486d79c7519335b906c5","abstract_canon_sha256":"734aaf60b424bcd3103ae2c084f2094199a180439a24ad0a69068ae7e4083759"},"schema_version":"1.0"},"canonical_sha256":"4512540fad09e94f55a6146d09954ef18eac93c0d14bcf0ad8ad444e444c7a6b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:50.013921Z","signature_b64":"sNOlG0p0M++EVTWOD9K56xNuxqeRBJnPD2xCEUooWKweDBGY+lCTx32V7TVrKG/TsmCAorQ4a0ORNzZbpWqkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4512540fad09e94f55a6146d09954ef18eac93c0d14bcf0ad8ad444e444c7a6b","last_reissued_at":"2026-07-05T02:29:50.013556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:50.013556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.02605","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":"2026-07-05T02:29:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5MeeoudRD/wvi3fBUOZYs5fDrJ0OYbRFoVrFGZxGaFjAgFxfh8L7jy2a2gWhB5hkKx+srlzi3MWzwYGV4eJ8BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T03:10:00.990025Z"},"content_sha256":"403a5f2521076b60e76dcad2209bc3a1f030ebd8ff7f21997d92a2157ceac02e","schema_version":"1.0","event_id":"sha256:403a5f2521076b60e76dcad2209bc3a1f030ebd8ff7f21997d92a2157ceac02e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:IUJFID5NBHUU6VNGCRWQTFKO6G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Unsupervised Sampling Approach for Image-Sentence Matching Using Document-Level Structural Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Haijun Shan, Xuanjing Huang, Zejun Li, Zhihao Fan, Zhongyu Wei","submitted_at":"2021-03-21T05:43:29Z","abstract_excerpt":"In this paper, we focus on the problem of unsupervised image-sentence matching. Existing research explores to utilize document-level structural information to sample positive and negative instances for model training. Although the approach achieves positive results, it introduces a sampling bias and fails to distinguish instances with high semantic similarity. To alleviate the bias, we propose a new sampling strategy to select additional intra-document image-sentence pairs as positive or negative samples. Furthermore, to recognize the complex pattern in intra-document samples, we propose a Tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02605","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.02605/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T02:29:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IA+v7Mx0DZnId2LOBABfdd5APq2jozvz9Qg8MzL4mMvOAjDglPpp8293O0KG1mX4vM9Oy81S5C46wFotDkvGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T03:10:00.990563Z"},"content_sha256":"1c115b754b7f5a8afdb3b34a25ef4b169e58f2871ff781609f2f7a2ff780e571","schema_version":"1.0","event_id":"sha256:1c115b754b7f5a8afdb3b34a25ef4b169e58f2871ff781609f2f7a2ff780e571"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IUJFID5NBHUU6VNGCRWQTFKO6G/bundle.json","state_url":"https://pith.science/pith/IUJFID5NBHUU6VNGCRWQTFKO6G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IUJFID5NBHUU6VNGCRWQTFKO6G/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":"2026-08-19T03:10:00Z","links":{"resolver":"https://pith.science/pith/IUJFID5NBHUU6VNGCRWQTFKO6G","bundle":"https://pith.science/pith/IUJFID5NBHUU6VNGCRWQTFKO6G/bundle.json","state":"https://pith.science/pith/IUJFID5NBHUU6VNGCRWQTFKO6G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IUJFID5NBHUU6VNGCRWQTFKO6G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IUJFID5NBHUU6VNGCRWQTFKO6G","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":"734aaf60b424bcd3103ae2c084f2094199a180439a24ad0a69068ae7e4083759","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-21T05:43:29Z","title_canon_sha256":"ea80e642cf9b85f52a40c421cb5f9569c086479ac679486d79c7519335b906c5"},"schema_version":"1.0","source":{"id":"2104.02605","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.02605","created_at":"2026-07-05T02:29:50Z"},{"alias_kind":"arxiv_version","alias_value":"2104.02605v1","created_at":"2026-07-05T02:29:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02605","created_at":"2026-07-05T02:29:50Z"},{"alias_kind":"pith_short_12","alias_value":"IUJFID5NBHUU","created_at":"2026-07-05T02:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"IUJFID5NBHUU6VNG","created_at":"2026-07-05T02:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"IUJFID5N","created_at":"2026-07-05T02:29:50Z"}],"graph_snapshots":[{"event_id":"sha256:1c115b754b7f5a8afdb3b34a25ef4b169e58f2871ff781609f2f7a2ff780e571","target":"graph","created_at":"2026-07-05T02:29:50Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2104.02605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we focus on the problem of unsupervised image-sentence matching. Existing research explores to utilize document-level structural information to sample positive and negative instances for model training. Although the approach achieves positive results, it introduces a sampling bias and fails to distinguish instances with high semantic similarity. To alleviate the bias, we propose a new sampling strategy to select additional intra-document image-sentence pairs as positive or negative samples. Furthermore, to recognize the complex pattern in intra-document samples, we propose a Tra","authors_text":"Haijun Shan, Xuanjing Huang, Zejun Li, Zhihao Fan, Zhongyu Wei","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-21T05:43:29Z","title":"An Unsupervised Sampling Approach for Image-Sentence Matching Using Document-Level Structural Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02605","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":"sha256:403a5f2521076b60e76dcad2209bc3a1f030ebd8ff7f21997d92a2157ceac02e","target":"record","created_at":"2026-07-05T02:29:50Z","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":"734aaf60b424bcd3103ae2c084f2094199a180439a24ad0a69068ae7e4083759","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-21T05:43:29Z","title_canon_sha256":"ea80e642cf9b85f52a40c421cb5f9569c086479ac679486d79c7519335b906c5"},"schema_version":"1.0","source":{"id":"2104.02605","kind":"arxiv","version":1}},"canonical_sha256":"4512540fad09e94f55a6146d09954ef18eac93c0d14bcf0ad8ad444e444c7a6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4512540fad09e94f55a6146d09954ef18eac93c0d14bcf0ad8ad444e444c7a6b","first_computed_at":"2026-07-05T02:29:50.013556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:29:50.013556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sNOlG0p0M++EVTWOD9K56xNuxqeRBJnPD2xCEUooWKweDBGY+lCTx32V7TVrKG/TsmCAorQ4a0ORNzZbpWqkCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:29:50.013921Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.02605","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:403a5f2521076b60e76dcad2209bc3a1f030ebd8ff7f21997d92a2157ceac02e","sha256:1c115b754b7f5a8afdb3b34a25ef4b169e58f2871ff781609f2f7a2ff780e571"],"state_sha256":"42909431dffc05b30d4b80aad102ef1f1b0647be2207af35b92502f7bb0c58ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UFzMbsOHcXPaImdb0bhzkJLDx2sgNrOgHIvhuFuEa++tkPSKVaWOMUr+1xV7u4fVXVL934SBtyTQdxrjdO8mDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T03:10:00.994571Z","bundle_sha256":"a47418ca682179bece9bc9039886e231aee2ca872828514d2a4239c20b64cd0e"}}