{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:V4NX6F676TLCS4SCBCGRJNC6RF","short_pith_number":"pith:V4NX6F67","canonical_record":{"source":{"id":"1808.07793","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2018-08-23T15:07:52Z","cross_cats_sorted":["cs.CV","cs.IR"],"title_canon_sha256":"77643385dc77675ddeb9ee549e6b20864858070bc1fb44933c03fef16aad0cb2","abstract_canon_sha256":"8992287b00fbc96b29a612c830fcc7dce002daaaf38e8939b2916fef088417d2"},"schema_version":"1.0"},"canonical_sha256":"af1b7f17dff4d6297242088d14b45e89741102d4a813c16154a62cd2636d108e","source":{"kind":"arxiv","id":"1808.07793","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.07793","created_at":"2026-05-18T00:07:24Z"},{"alias_kind":"arxiv_version","alias_value":"1808.07793v1","created_at":"2026-05-18T00:07:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07793","created_at":"2026-05-18T00:07:24Z"},{"alias_kind":"pith_short_12","alias_value":"V4NX6F676TLC","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"V4NX6F676TLCS4SC","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"V4NX6F67","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:V4NX6F676TLCS4SCBCGRJNC6RF","target":"record","payload":{"canonical_record":{"source":{"id":"1808.07793","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2018-08-23T15:07:52Z","cross_cats_sorted":["cs.CV","cs.IR"],"title_canon_sha256":"77643385dc77675ddeb9ee549e6b20864858070bc1fb44933c03fef16aad0cb2","abstract_canon_sha256":"8992287b00fbc96b29a612c830fcc7dce002daaaf38e8939b2916fef088417d2"},"schema_version":"1.0"},"canonical_sha256":"af1b7f17dff4d6297242088d14b45e89741102d4a813c16154a62cd2636d108e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:24.290644Z","signature_b64":"xYgcDBt5XMALEjOpIoE6qyvkCtEsn0KmJS1jQccexIBAbzIH0ieHjGxH7DH2kMwwHtoMtqxlWyVQSeaJHxTRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af1b7f17dff4d6297242088d14b45e89741102d4a813c16154a62cd2636d108e","last_reissued_at":"2026-05-18T00:07:24.290190Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:24.290190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.07793","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":"2026-05-18T00:07:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kqwAjj1XPGj1Ucpsslrv5XqJ46giUiPc+vhrW7ejD7g9AuZ7xpc+dJkyukYkjGXJ5qMDNPjINS6GjDCT0FBpDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T16:50:53.668068Z"},"content_sha256":"afe10e37068809e6aae856b39bb7395ca3ed82c3524ec767f9d7d3f776eccb76","schema_version":"1.0","event_id":"sha256:afe10e37068809e6aae856b39bb7395ca3ed82c3524ec767f9d7d3f776eccb76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:V4NX6F676TLCS4SCBCGRJNC6RF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.IR"],"primary_cat":"cs.MM","authors_text":"Amit K. Roy-Chowdhury, Evangelos E. Papalexakis, Niluthpol Chowdhury Mithun, Rameswar Panda","submitted_at":"2018-08-23T15:07:52Z","abstract_excerpt":"Cross-modal retrieval between visual data and natural language description remains a long-standing challenge in multimedia. While recent image-text retrieval methods offer great promise by learning deep representations aligned across modalities, most of these methods are plagued by the issue of training with small-scale datasets covering a limited number of images with ground-truth sentences. Moreover, it is extremely expensive to create a larger dataset by annotating millions of images with sentences and may lead to a biased model. Inspired by the recent success of webly supervised learning i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07793","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":"2026-05-18T00:07:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wb/MOJtGva4wv1K0XoRlmgLyNFiKVjTqcGvdkaI9yYJUFsNI+tFlNAk2vKpNgLqC10dG3mfYrEyu+iam2gF5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T16:50:53.668430Z"},"content_sha256":"7487c9490ba256643c6ccbd3e2e6e1c0b433e22e487b4bf11277c2bc9579888b","schema_version":"1.0","event_id":"sha256:7487c9490ba256643c6ccbd3e2e6e1c0b433e22e487b4bf11277c2bc9579888b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V4NX6F676TLCS4SCBCGRJNC6RF/bundle.json","state_url":"https://pith.science/pith/V4NX6F676TLCS4SCBCGRJNC6RF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V4NX6F676TLCS4SCBCGRJNC6RF/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":"2026-06-03T16:50:53Z","links":{"resolver":"https://pith.science/pith/V4NX6F676TLCS4SCBCGRJNC6RF","bundle":"https://pith.science/pith/V4NX6F676TLCS4SCBCGRJNC6RF/bundle.json","state":"https://pith.science/pith/V4NX6F676TLCS4SCBCGRJNC6RF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V4NX6F676TLCS4SCBCGRJNC6RF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:V4NX6F676TLCS4SCBCGRJNC6RF","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":"8992287b00fbc96b29a612c830fcc7dce002daaaf38e8939b2916fef088417d2","cross_cats_sorted":["cs.CV","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2018-08-23T15:07:52Z","title_canon_sha256":"77643385dc77675ddeb9ee549e6b20864858070bc1fb44933c03fef16aad0cb2"},"schema_version":"1.0","source":{"id":"1808.07793","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.07793","created_at":"2026-05-18T00:07:24Z"},{"alias_kind":"arxiv_version","alias_value":"1808.07793v1","created_at":"2026-05-18T00:07:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07793","created_at":"2026-05-18T00:07:24Z"},{"alias_kind":"pith_short_12","alias_value":"V4NX6F676TLC","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"V4NX6F676TLCS4SC","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"V4NX6F67","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:7487c9490ba256643c6ccbd3e2e6e1c0b433e22e487b4bf11277c2bc9579888b","target":"graph","created_at":"2026-05-18T00:07:24Z","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":"Cross-modal retrieval between visual data and natural language description remains a long-standing challenge in multimedia. While recent image-text retrieval methods offer great promise by learning deep representations aligned across modalities, most of these methods are plagued by the issue of training with small-scale datasets covering a limited number of images with ground-truth sentences. Moreover, it is extremely expensive to create a larger dataset by annotating millions of images with sentences and may lead to a biased model. Inspired by the recent success of webly supervised learning i","authors_text":"Amit K. Roy-Chowdhury, Evangelos E. Papalexakis, Niluthpol Chowdhury Mithun, Rameswar Panda","cross_cats":["cs.CV","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2018-08-23T15:07:52Z","title":"Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07793","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:afe10e37068809e6aae856b39bb7395ca3ed82c3524ec767f9d7d3f776eccb76","target":"record","created_at":"2026-05-18T00:07:24Z","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":"8992287b00fbc96b29a612c830fcc7dce002daaaf38e8939b2916fef088417d2","cross_cats_sorted":["cs.CV","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2018-08-23T15:07:52Z","title_canon_sha256":"77643385dc77675ddeb9ee549e6b20864858070bc1fb44933c03fef16aad0cb2"},"schema_version":"1.0","source":{"id":"1808.07793","kind":"arxiv","version":1}},"canonical_sha256":"af1b7f17dff4d6297242088d14b45e89741102d4a813c16154a62cd2636d108e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af1b7f17dff4d6297242088d14b45e89741102d4a813c16154a62cd2636d108e","first_computed_at":"2026-05-18T00:07:24.290190Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:24.290190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xYgcDBt5XMALEjOpIoE6qyvkCtEsn0KmJS1jQccexIBAbzIH0ieHjGxH7DH2kMwwHtoMtqxlWyVQSeaJHxTRDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:24.290644Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.07793","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afe10e37068809e6aae856b39bb7395ca3ed82c3524ec767f9d7d3f776eccb76","sha256:7487c9490ba256643c6ccbd3e2e6e1c0b433e22e487b4bf11277c2bc9579888b"],"state_sha256":"2c63af98f6213a7c7f1823430e91c57648bee029d55c1eeb5131f5b38f972d75"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+94h5QxGz99HXvrMvvdHg7kUI/UC3Kg7RGtiNYpybhevOHKPDa6L/ofD19mtJ5c0InyHdhn+mrWpRoqhwakKAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T16:50:53.670259Z","bundle_sha256":"0cd999f3947e428ba28bd376733cabd47f258274e36dc1c5a010891fe7066689"}}