{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JSVQZCGHWPOJYKRT4MQDLVL5RH","short_pith_number":"pith:JSVQZCGH","schema_version":"1.0","canonical_sha256":"4cab0c88c7b3dc9c2a33e32035d57d89faa2a3fca7a3cac9083140eb1b3e9240","source":{"kind":"arxiv","id":"2303.13800","version":5},"attestation_state":"computed","paper":{"title":"Aligning Step-by-Step Instructional Diagrams to Video Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anoop Cherian, Cristian Rodriguez, Jiahao Zhang, Stephen Gould, Yanbin Liu, Yizhak Ben-Shabat","submitted_at":"2023-03-24T04:45:45Z","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"},"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":"2303.13800","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-24T04:45:45Z","cross_cats_sorted":[],"title_canon_sha256":"89ded6b9e6c7aae0157a97959f1122cad7afe2cf320237b0f0b86f2bf7209bd9","abstract_canon_sha256":"382944632fe84f75b9c3232996051fc330c4476a724c84289e121c6b547aad36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:18.699512Z","signature_b64":"niVyy8+8i6AVt/PoRpUCMRjhzUpzuPN5QwSm/dE+oym8jl5OTIIWOw1M/Q+gM1qH2oUEVAQtQ5NpCd90RoABDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cab0c88c7b3dc9c2a33e32035d57d89faa2a3fca7a3cac9083140eb1b3e9240","last_reissued_at":"2026-07-05T09:42:18.698962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:18.698962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aligning Step-by-Step Instructional Diagrams to Video Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anoop Cherian, Cristian Rodriguez, Jiahao Zhang, Stephen Gould, Yanbin Liu, Yizhak Ben-Shabat","submitted_at":"2023-03-24T04:45:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13800","kind":"arxiv","version":5},"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/2303.13800/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":"2303.13800","created_at":"2026-07-05T09:42:18.699020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.13800v5","created_at":"2026-07-05T09:42:18.699020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13800","created_at":"2026-07-05T09:42:18.699020+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSVQZCGHWPOJ","created_at":"2026-07-05T09:42:18.699020+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSVQZCGHWPOJYKRT","created_at":"2026-07-05T09:42:18.699020+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSVQZCGH","created_at":"2026-07-05T09:42:18.699020+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JSVQZCGHWPOJYKRT4MQDLVL5RH","json":"https://pith.science/pith/JSVQZCGHWPOJYKRT4MQDLVL5RH.json","graph_json":"https://pith.science/api/pith-number/JSVQZCGHWPOJYKRT4MQDLVL5RH/graph.json","events_json":"https://pith.science/api/pith-number/JSVQZCGHWPOJYKRT4MQDLVL5RH/events.json","paper":"https://pith.science/paper/JSVQZCGH"},"agent_actions":{"view_html":"https://pith.science/pith/JSVQZCGHWPOJYKRT4MQDLVL5RH","download_json":"https://pith.science/pith/JSVQZCGHWPOJYKRT4MQDLVL5RH.json","view_paper":"https://pith.science/paper/JSVQZCGH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.13800&json=true","fetch_graph":"https://pith.science/api/pith-number/JSVQZCGHWPOJYKRT4MQDLVL5RH/graph.json","fetch_events":"https://pith.science/api/pith-number/JSVQZCGHWPOJYKRT4MQDLVL5RH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSVQZCGHWPOJYKRT4MQDLVL5RH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSVQZCGHWPOJYKRT4MQDLVL5RH/action/storage_attestation","attest_author":"https://pith.science/pith/JSVQZCGHWPOJYKRT4MQDLVL5RH/action/author_attestation","sign_citation":"https://pith.science/pith/JSVQZCGHWPOJYKRT4MQDLVL5RH/action/citation_signature","submit_replication":"https://pith.science/pith/JSVQZCGHWPOJYKRT4MQDLVL5RH/action/replication_record"}},"created_at":"2026-07-05T09:42:18.699020+00:00","updated_at":"2026-07-05T09:42:18.699020+00:00"}