{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IRF2X5JKDRDIGLHTO3MDOVAYAZ","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":"08addef349274c1b39a2e59e751e969a604f266cc20604a56c004cd5410e0699","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-09T13:54:56Z","title_canon_sha256":"5904d85e0bd79d8e2fb365474b4d334cbfb51f9e65071b0362849de47883d92a"},"schema_version":"1.0","source":{"id":"2112.04928","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.04928","created_at":"2026-07-05T03:39:27Z"},{"alias_kind":"arxiv_version","alias_value":"2112.04928v1","created_at":"2026-07-05T03:39:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04928","created_at":"2026-07-05T03:39:27Z"},{"alias_kind":"pith_short_12","alias_value":"IRF2X5JKDRDI","created_at":"2026-07-05T03:39:27Z"},{"alias_kind":"pith_short_16","alias_value":"IRF2X5JKDRDIGLHT","created_at":"2026-07-05T03:39:27Z"},{"alias_kind":"pith_short_8","alias_value":"IRF2X5JK","created_at":"2026-07-05T03:39:27Z"}],"graph_snapshots":[{"event_id":"sha256:0b3c3a897b9ebe738747b54d82bbbfea6b75b76bae5064aceefabeaea4e16d30","target":"graph","created_at":"2026-07-05T03:39:27Z","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/2112.04928/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A comprehensive understanding of vision and language and their interrelation are crucial to realize the underlying similarities and differences between these modalities and to learn more generalized, meaningful representations. In recent years, most of the works related to Text-to-Image synthesis and Image-to-Text generation, focused on supervised generative deep architectures to solve the problems, where very little interest was placed on learning the similarities between the embedding spaces across modalities. In this paper, we propose a novel self-supervised deep learning based approach tow","authors_text":"Anindya Sundar Das, Sriparna Saha","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-09T13:54:56Z","title":"Self-Supervised Image-to-Text and Text-to-Image Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04928","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":"sha256:4aa531967a19a9198864c010d00fa5a6ed7be544e3414af96c8fc500bc666fbd","target":"record","created_at":"2026-07-05T03:39:27Z","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":"08addef349274c1b39a2e59e751e969a604f266cc20604a56c004cd5410e0699","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-09T13:54:56Z","title_canon_sha256":"5904d85e0bd79d8e2fb365474b4d334cbfb51f9e65071b0362849de47883d92a"},"schema_version":"1.0","source":{"id":"2112.04928","kind":"arxiv","version":1}},"canonical_sha256":"444babf52a1c46832cf376d8375418065926e927f2338a3d9f766276c324320f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"444babf52a1c46832cf376d8375418065926e927f2338a3d9f766276c324320f","first_computed_at":"2026-07-05T03:39:27.255515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:39:27.255515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S2Jcg8v7g9PAMv3QAJ7LJdSR1cdK5Gim3BZLDppLKNqORR1L6UgudRBIoOrRrLMOYHLxwoo9Tm7s4nJWU7gEDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:39:27.255993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.04928","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4aa531967a19a9198864c010d00fa5a6ed7be544e3414af96c8fc500bc666fbd","sha256:0b3c3a897b9ebe738747b54d82bbbfea6b75b76bae5064aceefabeaea4e16d30"],"state_sha256":"e1b0f9e7b74dd323781eb1b0e7bf6ff2041a253f1f12f5c26f6f3a523572264a"}