{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VVRWI3E32RBFHCYX4JUKL4S7K5","short_pith_number":"pith:VVRWI3E3","schema_version":"1.0","canonical_sha256":"ad63646c9bd442538b17e268a5f25f576c8a5de36ec8f05d40767da168a16854","source":{"kind":"arxiv","id":"2007.08617","version":1},"attestation_state":"computed","paper":{"title":"Preserving Semantic Neighborhoods for Robust Cross-modal Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Adriana Kovashka, Christopher Thomas","submitted_at":"2020-07-16T20:32:54Z","abstract_excerpt":"The abundance of multimodal data (e.g. social media posts) has inspired interest in cross-modal retrieval methods. Popular approaches rely on a variety of metric learning losses, which prescribe what the proximity of image and text should be, in the learned space. However, most prior methods have focused on the case where image and text convey redundant information; in contrast, real-world image-text pairs convey complementary information with little overlap. Further, images in news articles and media portray topics in a visually diverse fashion; thus, we need to take special care to ensure a "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2007.08617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-16T20:32:54Z","cross_cats_sorted":["cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"472700ae9dade3764c07f26164cc60d7a21af5d79644300875758f6ef3afd24b","abstract_canon_sha256":"cf954302a030644f6a1d87df9f7a46622044ba91523396ea0c0e0c0cae21fc2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:37:35.086669Z","signature_b64":"2W0OhoT/rxbCXNcXUlsDB8tQewkr6StE3JTwsYpAi7uERT1XgZ2fT4rEtC9EKFciTJeHYW+3OOlpC5LdopO0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad63646c9bd442538b17e268a5f25f576c8a5de36ec8f05d40767da168a16854","last_reissued_at":"2026-07-05T01:37:35.086259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:37:35.086259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preserving Semantic Neighborhoods for Robust Cross-modal Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Adriana Kovashka, Christopher Thomas","submitted_at":"2020-07-16T20:32:54Z","abstract_excerpt":"The abundance of multimodal data (e.g. social media posts) has inspired interest in cross-modal retrieval methods. Popular approaches rely on a variety of metric learning losses, which prescribe what the proximity of image and text should be, in the learned space. However, most prior methods have focused on the case where image and text convey redundant information; in contrast, real-world image-text pairs convey complementary information with little overlap. Further, images in news articles and media portray topics in a visually diverse fashion; thus, we need to take special care to ensure a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.08617","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/2007.08617/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2007.08617","created_at":"2026-07-05T01:37:35.086325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.08617v1","created_at":"2026-07-05T01:37:35.086325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.08617","created_at":"2026-07-05T01:37:35.086325+00:00"},{"alias_kind":"pith_short_12","alias_value":"VVRWI3E32RBF","created_at":"2026-07-05T01:37:35.086325+00:00"},{"alias_kind":"pith_short_16","alias_value":"VVRWI3E32RBFHCYX","created_at":"2026-07-05T01:37:35.086325+00:00"},{"alias_kind":"pith_short_8","alias_value":"VVRWI3E3","created_at":"2026-07-05T01:37:35.086325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17372","citing_title":"Multimodal Political Bias Identification and Neutralization","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VVRWI3E32RBFHCYX4JUKL4S7K5","json":"https://pith.science/pith/VVRWI3E32RBFHCYX4JUKL4S7K5.json","graph_json":"https://pith.science/api/pith-number/VVRWI3E32RBFHCYX4JUKL4S7K5/graph.json","events_json":"https://pith.science/api/pith-number/VVRWI3E32RBFHCYX4JUKL4S7K5/events.json","paper":"https://pith.science/paper/VVRWI3E3"},"agent_actions":{"view_html":"https://pith.science/pith/VVRWI3E32RBFHCYX4JUKL4S7K5","download_json":"https://pith.science/pith/VVRWI3E32RBFHCYX4JUKL4S7K5.json","view_paper":"https://pith.science/paper/VVRWI3E3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.08617&json=true","fetch_graph":"https://pith.science/api/pith-number/VVRWI3E32RBFHCYX4JUKL4S7K5/graph.json","fetch_events":"https://pith.science/api/pith-number/VVRWI3E32RBFHCYX4JUKL4S7K5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VVRWI3E32RBFHCYX4JUKL4S7K5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VVRWI3E32RBFHCYX4JUKL4S7K5/action/storage_attestation","attest_author":"https://pith.science/pith/VVRWI3E32RBFHCYX4JUKL4S7K5/action/author_attestation","sign_citation":"https://pith.science/pith/VVRWI3E32RBFHCYX4JUKL4S7K5/action/citation_signature","submit_replication":"https://pith.science/pith/VVRWI3E32RBFHCYX4JUKL4S7K5/action/replication_record"}},"created_at":"2026-07-05T01:37:35.086325+00:00","updated_at":"2026-07-05T01:37:35.086325+00:00"}