{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KJWFJFBNGG22S3CLC4TBV2F44B","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":"7412ba8cb18d6ef1469b4a0a9cef30cc3931edc1b2d90dd6e1c723f605bbca90","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T21:40:17Z","title_canon_sha256":"a0131b064dc5b7f12902d83cc564c43caaca1cd9037f3d1e6823b45b3afc4470"},"schema_version":"1.0","source":{"id":"2412.01987","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01987","created_at":"2026-07-05T10:38:38Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01987v2","created_at":"2026-07-05T10:38:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01987","created_at":"2026-07-05T10:38:38Z"},{"alias_kind":"pith_short_12","alias_value":"KJWFJFBNGG22","created_at":"2026-07-05T10:38:38Z"},{"alias_kind":"pith_short_16","alias_value":"KJWFJFBNGG22S3CL","created_at":"2026-07-05T10:38:38Z"},{"alias_kind":"pith_short_8","alias_value":"KJWFJFBN","created_at":"2026-07-05T10:38:38Z"}],"graph_snapshots":[{"event_id":"sha256:74238b89f820f6dd0a2b96a8e015b033bb263ba826c4576692172073f54d09e7","target":"graph","created_at":"2026-07-05T10:38:38Z","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/2412.01987/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dima Damen, Ivan Laptev, Josef Sivic, Michael Wray, Prajwal Gatti, Tom\\'a\\v{s} Sou\\v{c}ek","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T21:40:17Z","title":"ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01987","kind":"arxiv","version":2},"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":"sha256:661935c39929b735129b9c173e23da35aa88065fd1195653ad6fa4ef3e0a95c3","target":"record","created_at":"2026-07-05T10:38:38Z","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":"7412ba8cb18d6ef1469b4a0a9cef30cc3931edc1b2d90dd6e1c723f605bbca90","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T21:40:17Z","title_canon_sha256":"a0131b064dc5b7f12902d83cc564c43caaca1cd9037f3d1e6823b45b3afc4470"},"schema_version":"1.0","source":{"id":"2412.01987","kind":"arxiv","version":2}},"canonical_sha256":"526c54942d31b5a96c4b17261ae8bce079854320c6b058a54446b6550ddf3c1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"526c54942d31b5a96c4b17261ae8bce079854320c6b058a54446b6550ddf3c1f","first_computed_at":"2026-07-05T10:38:38.984346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:38.984346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1n7LV9kfv9NshlliTrmmGhLlFOS9Z9FHRKvJ/k5Hg5UUMuOk0Vg7nnsTdEwxiT7dp/rPL4szTyAhob2/TT6xCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:38.984816Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01987","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:661935c39929b735129b9c173e23da35aa88065fd1195653ad6fa4ef3e0a95c3","sha256:74238b89f820f6dd0a2b96a8e015b033bb263ba826c4576692172073f54d09e7"],"state_sha256":"f07e2c7ac7fc61a5fc31806927948ccc6ef23c33b9680bddebe55d4a4edc576f"}