{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KJWFJFBNGG22S3CLC4TBV2F44B","short_pith_number":"pith:KJWFJFBN","schema_version":"1.0","canonical_sha256":"526c54942d31b5a96c4b17261ae8bce079854320c6b058a54446b6550ddf3c1f","source":{"kind":"arxiv","id":"2412.01987","version":2},"attestation_state":"computed","paper":{"title":"ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dima Damen, Ivan Laptev, Josef Sivic, Michael Wray, Prajwal Gatti, Tom\\'a\\v{s} Sou\\v{c}ek","submitted_at":"2024-12-02T21:40:17Z","abstract_excerpt":"The goal of this work is to generate step-by-step visual instructions in the form of a sequence of images, given an input image that provides the scene context and the sequence of textual instructions. This is a challenging problem as it requires generating multi-step image sequences to achieve a complex goal while being grounded in a specific environment. Part of the challenge stems from the lack of large-scale training data for this problem. The contribution of this work is thus three-fold. First, we introduce an automatic approach for collecting large step-by-step visual instruction trainin"},"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":"2412.01987","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T21:40:17Z","cross_cats_sorted":[],"title_canon_sha256":"a0131b064dc5b7f12902d83cc564c43caaca1cd9037f3d1e6823b45b3afc4470","abstract_canon_sha256":"7412ba8cb18d6ef1469b4a0a9cef30cc3931edc1b2d90dd6e1c723f605bbca90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:38.984816Z","signature_b64":"1n7LV9kfv9NshlliTrmmGhLlFOS9Z9FHRKvJ/k5Hg5UUMuOk0Vg7nnsTdEwxiT7dp/rPL4szTyAhob2/TT6xCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"526c54942d31b5a96c4b17261ae8bce079854320c6b058a54446b6550ddf3c1f","last_reissued_at":"2026-07-05T10:38:38.984346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:38.984346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dima Damen, Ivan Laptev, Josef Sivic, Michael Wray, Prajwal Gatti, Tom\\'a\\v{s} Sou\\v{c}ek","submitted_at":"2024-12-02T21:40:17Z","abstract_excerpt":"The goal of this work is to generate step-by-step visual instructions in the form of a sequence of images, given an input image that provides the scene context and the sequence of textual instructions. This is a challenging problem as it requires generating multi-step image sequences to achieve a complex goal while being grounded in a specific environment. Part of the challenge stems from the lack of large-scale training data for this problem. The contribution of this work is thus three-fold. First, we introduce an automatic approach for collecting large step-by-step visual instruction trainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01987","kind":"arxiv","version":2},"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/2412.01987/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":"2412.01987","created_at":"2026-07-05T10:38:38.984404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01987v2","created_at":"2026-07-05T10:38:38.984404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01987","created_at":"2026-07-05T10:38:38.984404+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJWFJFBNGG22","created_at":"2026-07-05T10:38:38.984404+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJWFJFBNGG22S3CL","created_at":"2026-07-05T10:38:38.984404+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJWFJFBN","created_at":"2026-07-05T10:38:38.984404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.13821","citing_title":"Stitch-a-Demo: Video Demonstrations from Multistep Descriptions","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26565","citing_title":"DenseStep2M: A Scalable, Training-Free Pipeline for Dense Instructional Video Annotation","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KJWFJFBNGG22S3CLC4TBV2F44B","json":"https://pith.science/pith/KJWFJFBNGG22S3CLC4TBV2F44B.json","graph_json":"https://pith.science/api/pith-number/KJWFJFBNGG22S3CLC4TBV2F44B/graph.json","events_json":"https://pith.science/api/pith-number/KJWFJFBNGG22S3CLC4TBV2F44B/events.json","paper":"https://pith.science/paper/KJWFJFBN"},"agent_actions":{"view_html":"https://pith.science/pith/KJWFJFBNGG22S3CLC4TBV2F44B","download_json":"https://pith.science/pith/KJWFJFBNGG22S3CLC4TBV2F44B.json","view_paper":"https://pith.science/paper/KJWFJFBN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01987&json=true","fetch_graph":"https://pith.science/api/pith-number/KJWFJFBNGG22S3CLC4TBV2F44B/graph.json","fetch_events":"https://pith.science/api/pith-number/KJWFJFBNGG22S3CLC4TBV2F44B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJWFJFBNGG22S3CLC4TBV2F44B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJWFJFBNGG22S3CLC4TBV2F44B/action/storage_attestation","attest_author":"https://pith.science/pith/KJWFJFBNGG22S3CLC4TBV2F44B/action/author_attestation","sign_citation":"https://pith.science/pith/KJWFJFBNGG22S3CLC4TBV2F44B/action/citation_signature","submit_replication":"https://pith.science/pith/KJWFJFBNGG22S3CLC4TBV2F44B/action/replication_record"}},"created_at":"2026-07-05T10:38:38.984404+00:00","updated_at":"2026-07-05T10:38:38.984404+00:00"}