{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:U5C3O7EEN5LMQ632VIUCJHHSVV","short_pith_number":"pith:U5C3O7EE","canonical_record":{"source":{"id":"2512.13609","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-15T18:03:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"19f29ab9f5f71b95e8fbc752b3b51d3db835b8f8327b2454454fe455178e582e","abstract_canon_sha256":"f89072e56889315888a55dc83d87b8b6e2dbe976d9cd2b3e60201ef1663b0f2d"},"schema_version":"1.0"},"canonical_sha256":"a745b77c846f56c87b7aaa28249cf2ad4332b787fd3f77570e7a4cfedafe2a9a","source":{"kind":"arxiv","id":"2512.13609","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.13609","created_at":"2026-05-17T23:39:00Z"},{"alias_kind":"arxiv_version","alias_value":"2512.13609v2","created_at":"2026-05-17T23:39:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.13609","created_at":"2026-05-17T23:39:00Z"},{"alias_kind":"pith_short_12","alias_value":"U5C3O7EEN5LM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"U5C3O7EEN5LMQ632","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"U5C3O7EE","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:U5C3O7EEN5LMQ632VIUCJHHSVV","target":"record","payload":{"canonical_record":{"source":{"id":"2512.13609","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-15T18:03:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"19f29ab9f5f71b95e8fbc752b3b51d3db835b8f8327b2454454fe455178e582e","abstract_canon_sha256":"f89072e56889315888a55dc83d87b8b6e2dbe976d9cd2b3e60201ef1663b0f2d"},"schema_version":"1.0"},"canonical_sha256":"a745b77c846f56c87b7aaa28249cf2ad4332b787fd3f77570e7a4cfedafe2a9a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:00.508673Z","signature_b64":"R8S+CKl/SG/OlHhoS1thVEi7K0TZC6kQb2HAA61QDZ6rtRRkoEM+lFZ5DO6fa2GK1noPHTYWamcDSTl8Iq+aCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a745b77c846f56c87b7aaa28249cf2ad4332b787fd3f77570e7a4cfedafe2a9a","last_reissued_at":"2026-05-17T23:39:00.507833Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:00.507833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.13609","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vd5fts8o1VW0/08FX/pk5GZgYp7vs0/QaY4x0QjJiMGsFLza33JRMhDJsV4SFXIaHe0+FNNYuo8bwaQxSHAWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:06:17.675091Z"},"content_sha256":"d06cbafabccd4435816c32f89f13f2c7b929238926e8aca77bac581499917a28","schema_version":"1.0","event_id":"sha256:d06cbafabccd4435816c32f89f13f2c7b929238926e8aca77bac581499917a28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:U5C3O7EEN5LMQ632VIUCJHHSVV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do-Undo Bench: Reversibility for Action Understanding in Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Requiring image generators to apply and then undo real actions tests genuine cause-and-effect understanding.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Apratim Bhattacharyya, Fatih Porikli, Hoang Le, Munawar Hayat, Rajeev Yasarla, Shreya Kadambi, Shweta Mahajan","submitted_at":"2025-12-15T18:03:42Z","abstract_excerpt":"We introduce the Do-Undo task and benchmark to address a critical gap in vision-language models: understanding and generating plausible scene transformations driven by real-world actions. Unlike prior work that relies on prompt-based image generation and editing to perform action-conditioned image manipulation, our training hypothesis requires models to simulate the outcome of a real-world action and then reverse it to the original state. This forward-reverse requirement tests genuine cause-and-effect understanding rather than stylistic or semantic edits. We curate a high-quality benchmark of "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"our training hypothesis requires models to simulate the outcome of a real-world action and then reverse it to the original state. This forward-reverse requirement tests genuine cause-and-effect understanding rather than stylistic or semantic edits.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the curated high-quality benchmark of reversible actions from real-world scenarios actually isolates genuine cause-and-effect understanding rather than other visual or linguistic cues.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Do-Undo Bench is a new evaluation task and dataset that forces models to simulate forward action effects and then undo them to measure genuine action understanding in image generation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Requiring image generators to apply and then undo real actions tests genuine cause-and-effect understanding.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"480eb27bf12949776cf156439f290f5f8e923735597504dedb52e3f3c03f13f6"},"source":{"id":"2512.13609","kind":"arxiv","version":2},"verdict":{"id":"85ac5aef-347b-45f3-a495-4dd4ef9829eb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T22:07:13.024071Z","strongest_claim":"our training hypothesis requires models to simulate the outcome of a real-world action and then reverse it to the original state. This forward-reverse requirement tests genuine cause-and-effect understanding rather than stylistic or semantic edits.","one_line_summary":"Do-Undo Bench is a new evaluation task and dataset that forces models to simulate forward action effects and then undo them to measure genuine action understanding in image generation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the curated high-quality benchmark of reversible actions from real-world scenarios actually isolates genuine cause-and-effect understanding rather than other visual or linguistic cues.","pith_extraction_headline":"Requiring image generators to apply and then undo real actions tests genuine cause-and-effect understanding."},"references":{"count":36,"sample":[{"doi":"","year":2024,"title":"Unibench: Visual reasoning requires rethinking vision- language beyond scaling.Advances in Neural Information Processing Systems, 37:82411–82437, 2024","work_id":"2e38bbe8-063d-44d3-93a3-0ff530253581","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning","work_id":"09215448-e68a-4168-89b7-9d9a83a0e51f","ref_index":2,"cited_arxiv_id":"2503.15558","is_internal_anchor":true},{"doi":"","year":2018,"title":"Long-term image boundary prediction","work_id":"c8bd781e-7050-49eb-b5f4-0ef9c394bda3","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Visual jenga: Discovering object dependencies via counterfactual inpainting","work_id":"0cbf5c2c-76ca-4283-bd7e-ab9252f14a18","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"In- structpix2pix: Learning to follow image editing instructions","work_id":"02ea0df2-52bb-4d47-b481-bdaec89376a0","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":36,"snapshot_sha256":"3e3aa11e2e71f2080b66d45639eff485d2a00ca2e04c2251ce08c679381666fd","internal_anchors":5},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ad0664dae266f8553b3dd2d1f167e20b6bd8e7e3311768e922c050a849d2cfd9"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"85ac5aef-347b-45f3-a495-4dd4ef9829eb"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GA9hOjnd4WbfbwwIava5B7t5Pwbla5Rb0lZ5MAkzUJZxQHLcnhu4k3TuXveXh9mwtJzd5vjIvg+68B8Zwhl4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:06:17.675756Z"},"content_sha256":"6aa014ae5fd406a2381406a49c87b4ebbcec1108bb14fc9724ee60d129603ab5","schema_version":"1.0","event_id":"sha256:6aa014ae5fd406a2381406a49c87b4ebbcec1108bb14fc9724ee60d129603ab5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U5C3O7EEN5LMQ632VIUCJHHSVV/bundle.json","state_url":"https://pith.science/pith/U5C3O7EEN5LMQ632VIUCJHHSVV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U5C3O7EEN5LMQ632VIUCJHHSVV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T11:06:17Z","links":{"resolver":"https://pith.science/pith/U5C3O7EEN5LMQ632VIUCJHHSVV","bundle":"https://pith.science/pith/U5C3O7EEN5LMQ632VIUCJHHSVV/bundle.json","state":"https://pith.science/pith/U5C3O7EEN5LMQ632VIUCJHHSVV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U5C3O7EEN5LMQ632VIUCJHHSVV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U5C3O7EEN5LMQ632VIUCJHHSVV","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":"f89072e56889315888a55dc83d87b8b6e2dbe976d9cd2b3e60201ef1663b0f2d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-15T18:03:42Z","title_canon_sha256":"19f29ab9f5f71b95e8fbc752b3b51d3db835b8f8327b2454454fe455178e582e"},"schema_version":"1.0","source":{"id":"2512.13609","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.13609","created_at":"2026-05-17T23:39:00Z"},{"alias_kind":"arxiv_version","alias_value":"2512.13609v2","created_at":"2026-05-17T23:39:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.13609","created_at":"2026-05-17T23:39:00Z"},{"alias_kind":"pith_short_12","alias_value":"U5C3O7EEN5LM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"U5C3O7EEN5LMQ632","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"U5C3O7EE","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:6aa014ae5fd406a2381406a49c87b4ebbcec1108bb14fc9724ee60d129603ab5","target":"graph","created_at":"2026-05-17T23:39:00Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"our training hypothesis requires models to simulate the outcome of a real-world action and then reverse it to the original state. This forward-reverse requirement tests genuine cause-and-effect understanding rather than stylistic or semantic edits."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the curated high-quality benchmark of reversible actions from real-world scenarios actually isolates genuine cause-and-effect understanding rather than other visual or linguistic cues."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Do-Undo Bench is a new evaluation task and dataset that forces models to simulate forward action effects and then undo them to measure genuine action understanding in image generation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Requiring image generators to apply and then undo real actions tests genuine cause-and-effect understanding."}],"snapshot_sha256":"480eb27bf12949776cf156439f290f5f8e923735597504dedb52e3f3c03f13f6"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ad0664dae266f8553b3dd2d1f167e20b6bd8e7e3311768e922c050a849d2cfd9"},"paper":{"abstract_excerpt":"We introduce the Do-Undo task and benchmark to address a critical gap in vision-language models: understanding and generating plausible scene transformations driven by real-world actions. Unlike prior work that relies on prompt-based image generation and editing to perform action-conditioned image manipulation, our training hypothesis requires models to simulate the outcome of a real-world action and then reverse it to the original state. This forward-reverse requirement tests genuine cause-and-effect understanding rather than stylistic or semantic edits. We curate a high-quality benchmark of ","authors_text":"Apratim Bhattacharyya, Fatih Porikli, Hoang Le, Munawar Hayat, Rajeev Yasarla, Shreya Kadambi, Shweta Mahajan","cross_cats":["cs.LG"],"headline":"Requiring image generators to apply and then undo real actions tests genuine cause-and-effect understanding.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-15T18:03:42Z","title":"Do-Undo Bench: Reversibility for Action Understanding in Image Generation"},"references":{"count":36,"internal_anchors":5,"resolved_work":36,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Unibench: Visual reasoning requires rethinking vision- language beyond scaling.Advances in Neural Information Processing Systems, 37:82411–82437, 2024","work_id":"2e38bbe8-063d-44d3-93a3-0ff530253581","year":2024},{"cited_arxiv_id":"2503.15558","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning","work_id":"09215448-e68a-4168-89b7-9d9a83a0e51f","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Long-term image boundary prediction","work_id":"c8bd781e-7050-49eb-b5f4-0ef9c394bda3","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Visual jenga: Discovering object dependencies via counterfactual inpainting","work_id":"0cbf5c2c-76ca-4283-bd7e-ab9252f14a18","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"In- structpix2pix: Learning to follow image editing instructions","work_id":"02ea0df2-52bb-4d47-b481-bdaec89376a0","year":2023}],"snapshot_sha256":"3e3aa11e2e71f2080b66d45639eff485d2a00ca2e04c2251ce08c679381666fd"},"source":{"id":"2512.13609","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T22:07:13.024071Z","id":"85ac5aef-347b-45f3-a495-4dd4ef9829eb","model_set":{"reader":"grok-4.3"},"one_line_summary":"Do-Undo Bench is a new evaluation task and dataset that forces models to simulate forward action effects and then undo them to measure genuine action understanding in image generation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Requiring image generators to apply and then undo real actions tests genuine cause-and-effect understanding.","strongest_claim":"our training hypothesis requires models to simulate the outcome of a real-world action and then reverse it to the original state. This forward-reverse requirement tests genuine cause-and-effect understanding rather than stylistic or semantic edits.","weakest_assumption":"That the curated high-quality benchmark of reversible actions from real-world scenarios actually isolates genuine cause-and-effect understanding rather than other visual or linguistic cues."}},"verdict_id":"85ac5aef-347b-45f3-a495-4dd4ef9829eb"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d06cbafabccd4435816c32f89f13f2c7b929238926e8aca77bac581499917a28","target":"record","created_at":"2026-05-17T23:39:00Z","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":"f89072e56889315888a55dc83d87b8b6e2dbe976d9cd2b3e60201ef1663b0f2d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-15T18:03:42Z","title_canon_sha256":"19f29ab9f5f71b95e8fbc752b3b51d3db835b8f8327b2454454fe455178e582e"},"schema_version":"1.0","source":{"id":"2512.13609","kind":"arxiv","version":2}},"canonical_sha256":"a745b77c846f56c87b7aaa28249cf2ad4332b787fd3f77570e7a4cfedafe2a9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a745b77c846f56c87b7aaa28249cf2ad4332b787fd3f77570e7a4cfedafe2a9a","first_computed_at":"2026-05-17T23:39:00.507833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:00.507833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R8S+CKl/SG/OlHhoS1thVEi7K0TZC6kQb2HAA61QDZ6rtRRkoEM+lFZ5DO6fa2GK1noPHTYWamcDSTl8Iq+aCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:00.508673Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.13609","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d06cbafabccd4435816c32f89f13f2c7b929238926e8aca77bac581499917a28","sha256:6aa014ae5fd406a2381406a49c87b4ebbcec1108bb14fc9724ee60d129603ab5"],"state_sha256":"672f9490931c617b00e0deda406644a8bb8d61e88505e2f351d3abe1b7af9b9d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"seP9NVGPNoeM3qSG+F53S9cO2sxvnhGQcXtGmqihPu4AtgWxcLkoAgE9ILsXC9wTlFyjYafCenS2A/ad08ceBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T11:06:17.678912Z","bundle_sha256":"1448a043ae207106cc8a204a72024bbd3833cdd9d5fef47383fc9749c757b5a1"}}