{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5MVEOHAE5DIPLU5YUSCVH4IDZT","short_pith_number":"pith:5MVEOHAE","canonical_record":{"source":{"id":"2508.19852","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-27T13:09:55Z","cross_cats_sorted":[],"title_canon_sha256":"65f2a1c0de9dcbb6133082a9f7ede193bbfcff676cf3d2531e875ce7039e4df0","abstract_canon_sha256":"a0043a620aea5145a3b032841440bfd13de38740819c6993c541c90a0e128100"},"schema_version":"1.0"},"canonical_sha256":"eb2a471c04e8d0f5d3b8a48553f103ccf5e7390a129446df460158e003673139","source":{"kind":"arxiv","id":"2508.19852","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.19852","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"arxiv_version","alias_value":"2508.19852v2","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19852","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_12","alias_value":"5MVEOHAE5DIP","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_16","alias_value":"5MVEOHAE5DIPLU5Y","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_8","alias_value":"5MVEOHAE","created_at":"2026-07-05T12:00:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5MVEOHAE5DIPLU5YUSCVH4IDZT","target":"record","payload":{"canonical_record":{"source":{"id":"2508.19852","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-27T13:09:55Z","cross_cats_sorted":[],"title_canon_sha256":"65f2a1c0de9dcbb6133082a9f7ede193bbfcff676cf3d2531e875ce7039e4df0","abstract_canon_sha256":"a0043a620aea5145a3b032841440bfd13de38740819c6993c541c90a0e128100"},"schema_version":"1.0"},"canonical_sha256":"eb2a471c04e8d0f5d3b8a48553f103ccf5e7390a129446df460158e003673139","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:52.477960Z","signature_b64":"hWKD0inprYgoH+TMa1zs3DXbEL+pMAN1y6jWU1ZO48CWGOJTxxezVgGkBjes0d4qGCnDVqzQLFEvx2RyGXV7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb2a471c04e8d0f5d3b8a48553f103ccf5e7390a129446df460158e003673139","last_reissued_at":"2026-07-05T12:00:52.477469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:52.477469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.19852","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":"2026-07-05T12:00:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uZOPn3IBJ5IFgGfcWuWV6BXJmQ4JHnbvAaBA4zYf7ys9+UmiAkCtjr+Pu9KLN8D3CUjyvwbd9npELExgunc4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:39:34.287330Z"},"content_sha256":"eee467630b60538c0e0e99b8825b4e0d59bed03b536bca4526806b0daa93d878","schema_version":"1.0","event_id":"sha256:eee467630b60538c0e0e99b8825b4e0d59bed03b536bca4526806b0daa93d878"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5MVEOHAE5DIPLU5YUSCVH4IDZT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ego-centric Predictive Model Conditioned on Hand Trajectories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binjie Zhang, Mike Zheng Shou","submitted_at":"2025-08-27T13:09:55Z","abstract_excerpt":"In egocentric scenarios, anticipating both the next action and its visual outcome is essential for understanding human-object interactions and for enabling robotic planning. However, existing paradigms fall short of jointly modeling these aspects. Vision-Language-Action (VLA) models focus on action prediction but lack explicit modeling of how actions influence the visual scene, while video prediction models generate future frames without conditioning on specific actions, often resulting in implausible or contextually inconsistent outcomes. To bridge this gap, we propose a unified two-stage pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19852","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/2508.19852/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":"2026-07-05T12:00:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q2KMrDtZvsn+EaIsJMA9qh3JxOIr7+8iqMPjLzPFPgpzWt8Cs92IuXBgjSxJ4cRwuCjlP44VNhuIek+uuRTxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:39:34.287905Z"},"content_sha256":"4336e6c84d582f933968376a7831cd12c6eb70fee7846ce28264a9e94a7a5348","schema_version":"1.0","event_id":"sha256:4336e6c84d582f933968376a7831cd12c6eb70fee7846ce28264a9e94a7a5348"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5MVEOHAE5DIPLU5YUSCVH4IDZT/bundle.json","state_url":"https://pith.science/pith/5MVEOHAE5DIPLU5YUSCVH4IDZT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5MVEOHAE5DIPLU5YUSCVH4IDZT/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":"2026-08-06T02:39:34Z","links":{"resolver":"https://pith.science/pith/5MVEOHAE5DIPLU5YUSCVH4IDZT","bundle":"https://pith.science/pith/5MVEOHAE5DIPLU5YUSCVH4IDZT/bundle.json","state":"https://pith.science/pith/5MVEOHAE5DIPLU5YUSCVH4IDZT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5MVEOHAE5DIPLU5YUSCVH4IDZT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5MVEOHAE5DIPLU5YUSCVH4IDZT","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":"a0043a620aea5145a3b032841440bfd13de38740819c6993c541c90a0e128100","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-27T13:09:55Z","title_canon_sha256":"65f2a1c0de9dcbb6133082a9f7ede193bbfcff676cf3d2531e875ce7039e4df0"},"schema_version":"1.0","source":{"id":"2508.19852","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.19852","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"arxiv_version","alias_value":"2508.19852v2","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19852","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_12","alias_value":"5MVEOHAE5DIP","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_16","alias_value":"5MVEOHAE5DIPLU5Y","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_8","alias_value":"5MVEOHAE","created_at":"2026-07-05T12:00:52Z"}],"graph_snapshots":[{"event_id":"sha256:4336e6c84d582f933968376a7831cd12c6eb70fee7846ce28264a9e94a7a5348","target":"graph","created_at":"2026-07-05T12:00:52Z","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/2508.19852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In egocentric scenarios, anticipating both the next action and its visual outcome is essential for understanding human-object interactions and for enabling robotic planning. However, existing paradigms fall short of jointly modeling these aspects. Vision-Language-Action (VLA) models focus on action prediction but lack explicit modeling of how actions influence the visual scene, while video prediction models generate future frames without conditioning on specific actions, often resulting in implausible or contextually inconsistent outcomes. To bridge this gap, we propose a unified two-stage pre","authors_text":"Binjie Zhang, Mike Zheng Shou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-27T13:09:55Z","title":"Ego-centric Predictive Model Conditioned on Hand Trajectories"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19852","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:eee467630b60538c0e0e99b8825b4e0d59bed03b536bca4526806b0daa93d878","target":"record","created_at":"2026-07-05T12:00:52Z","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":"a0043a620aea5145a3b032841440bfd13de38740819c6993c541c90a0e128100","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-27T13:09:55Z","title_canon_sha256":"65f2a1c0de9dcbb6133082a9f7ede193bbfcff676cf3d2531e875ce7039e4df0"},"schema_version":"1.0","source":{"id":"2508.19852","kind":"arxiv","version":2}},"canonical_sha256":"eb2a471c04e8d0f5d3b8a48553f103ccf5e7390a129446df460158e003673139","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb2a471c04e8d0f5d3b8a48553f103ccf5e7390a129446df460158e003673139","first_computed_at":"2026-07-05T12:00:52.477469Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:52.477469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hWKD0inprYgoH+TMa1zs3DXbEL+pMAN1y6jWU1ZO48CWGOJTxxezVgGkBjes0d4qGCnDVqzQLFEvx2RyGXV7Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:52.477960Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.19852","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eee467630b60538c0e0e99b8825b4e0d59bed03b536bca4526806b0daa93d878","sha256:4336e6c84d582f933968376a7831cd12c6eb70fee7846ce28264a9e94a7a5348"],"state_sha256":"2c6b8bbbe460a8fd5931015564364d7fc26e1176a84fcf217308dceab3d579a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dAc9G0mQQ5ntieT4+Hg6AEt/Rtrsd5LpRQk98t015P9DIVLB69mOCx/vLYVZjXqwLNodkZ88Hc6ikRKhskvMBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:39:34.292702Z","bundle_sha256":"c1ee8c8117b6487be2711aaffada1997af358a95143f4432f968b7c1b024ab4b"}}