{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ATXFU7BP4HZ4634LFZKBVHWECL","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":"8cc34e141636fc153521d6cf85a9ccb02526ea87f0bae6624b41094a67a5b218","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-25T20:58:17Z","title_canon_sha256":"c8093b0fed14101dfa9fc572666897c72e1f0c9e49cdc206cf0e540e30113c7b"},"schema_version":"1.0","source":{"id":"2204.11964","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.11964","created_at":"2026-07-05T05:54:29Z"},{"alias_kind":"arxiv_version","alias_value":"2204.11964v3","created_at":"2026-07-05T05:54:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.11964","created_at":"2026-07-05T05:54:29Z"},{"alias_kind":"pith_short_12","alias_value":"ATXFU7BP4HZ4","created_at":"2026-07-05T05:54:29Z"},{"alias_kind":"pith_short_16","alias_value":"ATXFU7BP4HZ4634L","created_at":"2026-07-05T05:54:29Z"},{"alias_kind":"pith_short_8","alias_value":"ATXFU7BP","created_at":"2026-07-05T05:54:29Z"}],"graph_snapshots":[{"event_id":"sha256:b448942522f55b8c20ec5f7186b475d3de7736999df82116a678b32ec385a0a0","target":"graph","created_at":"2026-07-05T05:54:29Z","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/2204.11964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we extend scene understanding to include that of human sketch. The result is a complete trilogy of scene representation from three diverse and complementary modalities -- sketch, photo, and text. Instead of learning a rigid three-way embedding and be done with it, we focus on learning a flexible joint embedding that fully supports the ``optionality\" that this complementarity brings. Our embedding supports optionality on two axes: (i) optionality across modalities -- use any combination of modalities as query for downstream tasks like retrieval, (ii) optionality across tasks -- s","authors_text":"Aneeshan Sain, Ayan Kumar Bhunia, Pinaki Nath Chowdhury, Subhadeep Koley, Tao Xiang, Yi-Zhe Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-25T20:58:17Z","title":"SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.11964","kind":"arxiv","version":3},"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":"sha256:5535c9ffee86c25e0e1973366c3209c2986bc668b81ebc3b64fef1fcda1f4dab","target":"record","created_at":"2026-07-05T05:54:29Z","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":"8cc34e141636fc153521d6cf85a9ccb02526ea87f0bae6624b41094a67a5b218","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-25T20:58:17Z","title_canon_sha256":"c8093b0fed14101dfa9fc572666897c72e1f0c9e49cdc206cf0e540e30113c7b"},"schema_version":"1.0","source":{"id":"2204.11964","kind":"arxiv","version":3}},"canonical_sha256":"04ee5a7c2fe1f3cf6f8b2e541a9ec412d997ea557bb7e95793eb4a0ddeb66bbf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04ee5a7c2fe1f3cf6f8b2e541a9ec412d997ea557bb7e95793eb4a0ddeb66bbf","first_computed_at":"2026-07-05T05:54:29.004676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:54:29.004676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JJJpc6OxRbvmDt94c7r6LTWxHLDoixS0X/He02yCnuLYBi3kdsvnrhaNPlopkgvxbvMkc3J35tH8i1pMHmtnCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:54:29.005175Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.11964","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5535c9ffee86c25e0e1973366c3209c2986bc668b81ebc3b64fef1fcda1f4dab","sha256:b448942522f55b8c20ec5f7186b475d3de7736999df82116a678b32ec385a0a0"],"state_sha256":"a5b02e11d2da650eda79d8dbf27cbb1b549f452a259e398c8411f014231e20e1"}