{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q3PWJM5RHB2Z2WT257T3WNWLQ5","short_pith_number":"pith:Q3PWJM5R","canonical_record":{"source":{"id":"2408.07147","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T18:33:45Z","cross_cats_sorted":[],"title_canon_sha256":"cb0668b3f8df5e9795a7bc75d07c7362db72bf35274058ae4fb726aa55187e42","abstract_canon_sha256":"694ce4336a20f5ce5186b1c00d74eee5365a401f73e92baf1e63c529d0e567af"},"schema_version":"1.0"},"canonical_sha256":"86df64b3b138759d5a7aefe7bb36cb87552dce516a0dabf377dee40852efb5d5","source":{"kind":"arxiv","id":"2408.07147","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07147","created_at":"2026-07-05T08:55:11Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07147v1","created_at":"2026-07-05T08:55:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07147","created_at":"2026-07-05T08:55:11Z"},{"alias_kind":"pith_short_12","alias_value":"Q3PWJM5RHB2Z","created_at":"2026-07-05T08:55:11Z"},{"alias_kind":"pith_short_16","alias_value":"Q3PWJM5RHB2Z2WT2","created_at":"2026-07-05T08:55:11Z"},{"alias_kind":"pith_short_8","alias_value":"Q3PWJM5R","created_at":"2026-07-05T08:55:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q3PWJM5RHB2Z2WT257T3WNWLQ5","target":"record","payload":{"canonical_record":{"source":{"id":"2408.07147","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T18:33:45Z","cross_cats_sorted":[],"title_canon_sha256":"cb0668b3f8df5e9795a7bc75d07c7362db72bf35274058ae4fb726aa55187e42","abstract_canon_sha256":"694ce4336a20f5ce5186b1c00d74eee5365a401f73e92baf1e63c529d0e567af"},"schema_version":"1.0"},"canonical_sha256":"86df64b3b138759d5a7aefe7bb36cb87552dce516a0dabf377dee40852efb5d5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:11.481811Z","signature_b64":"AyeW4Y6iBk7fp7RVneuP0NOxDLEehTjQra/qUAA42nD4REz2kSkwiBVGGtzdWR3r6zScLv5sJgy5IGSZeqFRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86df64b3b138759d5a7aefe7bb36cb87552dce516a0dabf377dee40852efb5d5","last_reissued_at":"2026-07-05T08:55:11.481424Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:11.481424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.07147","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:55:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VapB7JCDRmabnM0YsjqqZo3ZTJ7tFUVLR5W0MjxWqPS5LIymAF7H8WbqwldRHT2LzQ1XFaqNF93dBBvBQCauCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:29:06.696855Z"},"content_sha256":"2a62ab817d50bcc37d203169afba675d95dd0136a7605768a7ebe5b62d75e6db","schema_version":"1.0","event_id":"sha256:2a62ab817d50bcc37d203169afba675d95dd0136a7605768a7ebe5b62d75e6db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q3PWJM5RHB2Z2WT257T3WNWLQ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Controlling the World by Sleight of Hand","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Basile Van Hoorick, Carl Vondrick, Richard Zemel, Ruoshi Liu, Sruthi Sudhakar","submitted_at":"2024-08-13T18:33:45Z","abstract_excerpt":"Humans naturally build mental models of object interactions and dynamics, allowing them to imagine how their surroundings will change if they take a certain action. While generative models today have shown impressive results on generating/editing images unconditionally or conditioned on text, current methods do not provide the ability to perform object manipulation conditioned on actions, an important tool for world modeling and action planning. Therefore, we propose to learn an action-conditional generative models by learning from unlabeled videos of human hands interacting with objects. The "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07147","kind":"arxiv","version":1},"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/2408.07147/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:55:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zRkOs+mWws3pbYmIf5pB/pgoeZ38IoN+Bx0JdnO21hrAhYNFa6gHvmo5uMicRIWBXURr+hdY7q2Oa9TwkfkKAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:29:06.697475Z"},"content_sha256":"dca01a78c12cd2042503277a4a368a1c76737e22167d1f6c32babe0d14ded329","schema_version":"1.0","event_id":"sha256:dca01a78c12cd2042503277a4a368a1c76737e22167d1f6c32babe0d14ded329"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q3PWJM5RHB2Z2WT257T3WNWLQ5/bundle.json","state_url":"https://pith.science/pith/Q3PWJM5RHB2Z2WT257T3WNWLQ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q3PWJM5RHB2Z2WT257T3WNWLQ5/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":"2026-08-17T23:29:06Z","links":{"resolver":"https://pith.science/pith/Q3PWJM5RHB2Z2WT257T3WNWLQ5","bundle":"https://pith.science/pith/Q3PWJM5RHB2Z2WT257T3WNWLQ5/bundle.json","state":"https://pith.science/pith/Q3PWJM5RHB2Z2WT257T3WNWLQ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q3PWJM5RHB2Z2WT257T3WNWLQ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q3PWJM5RHB2Z2WT257T3WNWLQ5","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":"694ce4336a20f5ce5186b1c00d74eee5365a401f73e92baf1e63c529d0e567af","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T18:33:45Z","title_canon_sha256":"cb0668b3f8df5e9795a7bc75d07c7362db72bf35274058ae4fb726aa55187e42"},"schema_version":"1.0","source":{"id":"2408.07147","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07147","created_at":"2026-07-05T08:55:11Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07147v1","created_at":"2026-07-05T08:55:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07147","created_at":"2026-07-05T08:55:11Z"},{"alias_kind":"pith_short_12","alias_value":"Q3PWJM5RHB2Z","created_at":"2026-07-05T08:55:11Z"},{"alias_kind":"pith_short_16","alias_value":"Q3PWJM5RHB2Z2WT2","created_at":"2026-07-05T08:55:11Z"},{"alias_kind":"pith_short_8","alias_value":"Q3PWJM5R","created_at":"2026-07-05T08:55:11Z"}],"graph_snapshots":[{"event_id":"sha256:dca01a78c12cd2042503277a4a368a1c76737e22167d1f6c32babe0d14ded329","target":"graph","created_at":"2026-07-05T08:55:11Z","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/2408.07147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans naturally build mental models of object interactions and dynamics, allowing them to imagine how their surroundings will change if they take a certain action. While generative models today have shown impressive results on generating/editing images unconditionally or conditioned on text, current methods do not provide the ability to perform object manipulation conditioned on actions, an important tool for world modeling and action planning. Therefore, we propose to learn an action-conditional generative models by learning from unlabeled videos of human hands interacting with objects. The ","authors_text":"Basile Van Hoorick, Carl Vondrick, Richard Zemel, Ruoshi Liu, Sruthi Sudhakar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T18:33:45Z","title":"Controlling the World by Sleight of Hand"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07147","kind":"arxiv","version":1},"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":"sha256:2a62ab817d50bcc37d203169afba675d95dd0136a7605768a7ebe5b62d75e6db","target":"record","created_at":"2026-07-05T08:55:11Z","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":"694ce4336a20f5ce5186b1c00d74eee5365a401f73e92baf1e63c529d0e567af","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T18:33:45Z","title_canon_sha256":"cb0668b3f8df5e9795a7bc75d07c7362db72bf35274058ae4fb726aa55187e42"},"schema_version":"1.0","source":{"id":"2408.07147","kind":"arxiv","version":1}},"canonical_sha256":"86df64b3b138759d5a7aefe7bb36cb87552dce516a0dabf377dee40852efb5d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86df64b3b138759d5a7aefe7bb36cb87552dce516a0dabf377dee40852efb5d5","first_computed_at":"2026-07-05T08:55:11.481424Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:11.481424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AyeW4Y6iBk7fp7RVneuP0NOxDLEehTjQra/qUAA42nD4REz2kSkwiBVGGtzdWR3r6zScLv5sJgy5IGSZeqFRAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:11.481811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.07147","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a62ab817d50bcc37d203169afba675d95dd0136a7605768a7ebe5b62d75e6db","sha256:dca01a78c12cd2042503277a4a368a1c76737e22167d1f6c32babe0d14ded329"],"state_sha256":"28f796b711434d7f830fa442adcfbb0ff0feaba9dbcdc60d51ea7f9b5d6e574b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WEwYNt+FI4Slv3CblbUqzCgE0/xqq9brFFByB0yy8dydj4N1XeHZCpvGwOb2plu2aoVTAiJL5IjpyfU4hsFoCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T23:29:06.703047Z","bundle_sha256":"fd8611fe251c9aabac1274d2501decc3594c5b8f5aef8cec3ff972f643605fbc"}}