{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JSVQZCGHWPOJYKRT4MQDLVL5RH","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":"382944632fe84f75b9c3232996051fc330c4476a724c84289e121c6b547aad36","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-24T04:45:45Z","title_canon_sha256":"89ded6b9e6c7aae0157a97959f1122cad7afe2cf320237b0f0b86f2bf7209bd9"},"schema_version":"1.0","source":{"id":"2303.13800","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.13800","created_at":"2026-07-05T09:42:18Z"},{"alias_kind":"arxiv_version","alias_value":"2303.13800v5","created_at":"2026-07-05T09:42:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13800","created_at":"2026-07-05T09:42:18Z"},{"alias_kind":"pith_short_12","alias_value":"JSVQZCGHWPOJ","created_at":"2026-07-05T09:42:18Z"},{"alias_kind":"pith_short_16","alias_value":"JSVQZCGHWPOJYKRT","created_at":"2026-07-05T09:42:18Z"},{"alias_kind":"pith_short_8","alias_value":"JSVQZCGH","created_at":"2026-07-05T09:42:18Z"}],"graph_snapshots":[{"event_id":"sha256:fb426137c6fb0e2c7622ead0ad265d025b89865340bab2d74c986cec8c44ae8b","target":"graph","created_at":"2026-07-05T09:42:18Z","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/2303.13800/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal alignment facilitates the retrieval of instances from one modality when queried using another. In this paper, we consider a novel setting where such an alignment is between (i) instruction steps that are depicted as assembly diagrams (commonly seen in Ikea assembly manuals) and (ii) video segments from in-the-wild videos; these videos comprising an enactment of the assembly actions in the real world. To learn this alignment, we introduce a novel supervised contrastive learning method that learns to align videos with the subtle details in the assembly diagrams, guided by a set of nov","authors_text":"Anoop Cherian, Cristian Rodriguez, Jiahao Zhang, Stephen Gould, Yanbin Liu, Yizhak Ben-Shabat","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-24T04:45:45Z","title":"Aligning Step-by-Step Instructional Diagrams to Video Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13800","kind":"arxiv","version":5},"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:bec14da5436f2f5466ad3e342e82071315e36322e91dbd6a8efbfb9aeabae66e","target":"record","created_at":"2026-07-05T09:42:18Z","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":"382944632fe84f75b9c3232996051fc330c4476a724c84289e121c6b547aad36","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-24T04:45:45Z","title_canon_sha256":"89ded6b9e6c7aae0157a97959f1122cad7afe2cf320237b0f0b86f2bf7209bd9"},"schema_version":"1.0","source":{"id":"2303.13800","kind":"arxiv","version":5}},"canonical_sha256":"4cab0c88c7b3dc9c2a33e32035d57d89faa2a3fca7a3cac9083140eb1b3e9240","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cab0c88c7b3dc9c2a33e32035d57d89faa2a3fca7a3cac9083140eb1b3e9240","first_computed_at":"2026-07-05T09:42:18.698962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:18.698962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"niVyy8+8i6AVt/PoRpUCMRjhzUpzuPN5QwSm/dE+oym8jl5OTIIWOw1M/Q+gM1qH2oUEVAQtQ5NpCd90RoABDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:18.699512Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.13800","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bec14da5436f2f5466ad3e342e82071315e36322e91dbd6a8efbfb9aeabae66e","sha256:fb426137c6fb0e2c7622ead0ad265d025b89865340bab2d74c986cec8c44ae8b"],"state_sha256":"a597ad6ff3237b7645ee393578e23a1dfdca0908848828f73b488dd6d71caa59"}