{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NNWP5NRNUP5MS6FFNTWZ5ZNIMA","short_pith_number":"pith:NNWP5NRN","canonical_record":{"source":{"id":"2606.28215","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-26T16:05:58Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"c675c7fa42e3c200d1c11aaf6ef92506c262d879daaccc00cca899b62ddbb2ef","abstract_canon_sha256":"1666294ef86e53466709250061a4cbf93112bac44f8b386fda8d0e898d7c7cf0"},"schema_version":"1.0"},"canonical_sha256":"6b6cfeb62da3fac978a56ced9ee5a8603d050e21c39de3ed13c241ece5d318d2","source":{"kind":"arxiv","id":"2606.28215","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28215","created_at":"2026-06-29T01:15:09Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28215v1","created_at":"2026-06-29T01:15:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28215","created_at":"2026-06-29T01:15:09Z"},{"alias_kind":"pith_short_12","alias_value":"NNWP5NRNUP5M","created_at":"2026-06-29T01:15:09Z"},{"alias_kind":"pith_short_16","alias_value":"NNWP5NRNUP5MS6FF","created_at":"2026-06-29T01:15:09Z"},{"alias_kind":"pith_short_8","alias_value":"NNWP5NRN","created_at":"2026-06-29T01:15:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NNWP5NRNUP5MS6FFNTWZ5ZNIMA","target":"record","payload":{"canonical_record":{"source":{"id":"2606.28215","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-26T16:05:58Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"c675c7fa42e3c200d1c11aaf6ef92506c262d879daaccc00cca899b62ddbb2ef","abstract_canon_sha256":"1666294ef86e53466709250061a4cbf93112bac44f8b386fda8d0e898d7c7cf0"},"schema_version":"1.0"},"canonical_sha256":"6b6cfeb62da3fac978a56ced9ee5a8603d050e21c39de3ed13c241ece5d318d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:15:09.555220Z","signature_b64":"bhI1eG+wRwrrLUI5dKcGFi6IEJiVVxJY0Qm9+3sqTHp+U5CVA0oUTBRApStrOz/2a/WdPqKClpQGaD2SiRpyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b6cfeb62da3fac978a56ced9ee5a8603d050e21c39de3ed13c241ece5d318d2","last_reissued_at":"2026-06-29T01:15:09.554823Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:15:09.554823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.28215","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":"2026-06-29T01:15:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qbH3/fBx06Dxn4tW4gT6q4tRFZwOs0Hy1M1O00GAysfDEaLA4HC4pf/5hoyC/dCjphkSebNhgaMC6XwDB3LCAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T19:42:28.559000Z"},"content_sha256":"2ca511210be2515122443ba8069184fe4852b66acc8c4a27d8ed36edb706835a","schema_version":"1.0","event_id":"sha256:2ca511210be2515122443ba8069184fe4852b66acc8c4a27d8ed36edb706835a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NNWP5NRNUP5MS6FFNTWZ5ZNIMA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Boran Wen, Chenyang Yu, Haoyuan Wang, Jiaxin Li, Li Zhang, Mingyu Zhang, Ruiyang Liu, Su Linxiang, Xinrui Shi, Yichen Zhao, Yifan Ding, Yong-Lu Li, Yuxiang WU, Zhenkai Zhang","submitted_at":"2026-06-26T16:05:58Z","abstract_excerpt":"Extracting dynamic 4D object interactions from massive, in-the-wild monocular videos offers a highly efficient data collection pathway for scaling Embodied AI and training VLAs. However, existing monocular 4D reconstruction methods primarily focus on isolated objects, often failing under the severe occlusions and complex dynamics inherent in multi-object interactions. To bridge this gap, we propose HAT-4D, the first agentic framework designed to reconstruct the 3D geometry, temporal dynamics, and physical interactions of multiple objects from a single video. By integrating VLMs with a multi-le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28215","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/2606.28215/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":"2026-06-29T01:15:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D0G4MDeegpQtS4AQoxy6f+k7X6IRfhp3qSQIiXqcDwJ//CYWTJJl2iDD2etY/mBCHxRJ9Gscaa5y00ZCujxiCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T19:42:28.559380Z"},"content_sha256":"2f5dae0e0ea876be5edbd8177322c495c16956dd2ecf1e6ab1508aef6dcc4560","schema_version":"1.0","event_id":"sha256:2f5dae0e0ea876be5edbd8177322c495c16956dd2ecf1e6ab1508aef6dcc4560"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NNWP5NRNUP5MS6FFNTWZ5ZNIMA/bundle.json","state_url":"https://pith.science/pith/NNWP5NRNUP5MS6FFNTWZ5ZNIMA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NNWP5NRNUP5MS6FFNTWZ5ZNIMA/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":"2026-06-29T19:42:28Z","links":{"resolver":"https://pith.science/pith/NNWP5NRNUP5MS6FFNTWZ5ZNIMA","bundle":"https://pith.science/pith/NNWP5NRNUP5MS6FFNTWZ5ZNIMA/bundle.json","state":"https://pith.science/pith/NNWP5NRNUP5MS6FFNTWZ5ZNIMA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NNWP5NRNUP5MS6FFNTWZ5ZNIMA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NNWP5NRNUP5MS6FFNTWZ5ZNIMA","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":"1666294ef86e53466709250061a4cbf93112bac44f8b386fda8d0e898d7c7cf0","cross_cats_sorted":["cs.AI","cs.GR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-26T16:05:58Z","title_canon_sha256":"c675c7fa42e3c200d1c11aaf6ef92506c262d879daaccc00cca899b62ddbb2ef"},"schema_version":"1.0","source":{"id":"2606.28215","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28215","created_at":"2026-06-29T01:15:09Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28215v1","created_at":"2026-06-29T01:15:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28215","created_at":"2026-06-29T01:15:09Z"},{"alias_kind":"pith_short_12","alias_value":"NNWP5NRNUP5M","created_at":"2026-06-29T01:15:09Z"},{"alias_kind":"pith_short_16","alias_value":"NNWP5NRNUP5MS6FF","created_at":"2026-06-29T01:15:09Z"},{"alias_kind":"pith_short_8","alias_value":"NNWP5NRN","created_at":"2026-06-29T01:15:09Z"}],"graph_snapshots":[{"event_id":"sha256:2f5dae0e0ea876be5edbd8177322c495c16956dd2ecf1e6ab1508aef6dcc4560","target":"graph","created_at":"2026-06-29T01:15:09Z","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/2606.28215/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Extracting dynamic 4D object interactions from massive, in-the-wild monocular videos offers a highly efficient data collection pathway for scaling Embodied AI and training VLAs. However, existing monocular 4D reconstruction methods primarily focus on isolated objects, often failing under the severe occlusions and complex dynamics inherent in multi-object interactions. To bridge this gap, we propose HAT-4D, the first agentic framework designed to reconstruct the 3D geometry, temporal dynamics, and physical interactions of multiple objects from a single video. By integrating VLMs with a multi-le","authors_text":"Boran Wen, Chenyang Yu, Haoyuan Wang, Jiaxin Li, Li Zhang, Mingyu Zhang, Ruiyang Liu, Su Linxiang, Xinrui Shi, Yichen Zhao, Yifan Ding, Yong-Lu Li, Yuxiang WU, Zhenkai Zhang","cross_cats":["cs.AI","cs.GR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-26T16:05:58Z","title":"HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28215","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":"sha256:2ca511210be2515122443ba8069184fe4852b66acc8c4a27d8ed36edb706835a","target":"record","created_at":"2026-06-29T01:15:09Z","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":"1666294ef86e53466709250061a4cbf93112bac44f8b386fda8d0e898d7c7cf0","cross_cats_sorted":["cs.AI","cs.GR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-26T16:05:58Z","title_canon_sha256":"c675c7fa42e3c200d1c11aaf6ef92506c262d879daaccc00cca899b62ddbb2ef"},"schema_version":"1.0","source":{"id":"2606.28215","kind":"arxiv","version":1}},"canonical_sha256":"6b6cfeb62da3fac978a56ced9ee5a8603d050e21c39de3ed13c241ece5d318d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b6cfeb62da3fac978a56ced9ee5a8603d050e21c39de3ed13c241ece5d318d2","first_computed_at":"2026-06-29T01:15:09.554823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T01:15:09.554823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bhI1eG+wRwrrLUI5dKcGFi6IEJiVVxJY0Qm9+3sqTHp+U5CVA0oUTBRApStrOz/2a/WdPqKClpQGaD2SiRpyCQ==","signature_status":"signed_v1","signed_at":"2026-06-29T01:15:09.555220Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.28215","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ca511210be2515122443ba8069184fe4852b66acc8c4a27d8ed36edb706835a","sha256:2f5dae0e0ea876be5edbd8177322c495c16956dd2ecf1e6ab1508aef6dcc4560"],"state_sha256":"a264c16e8a2d5ea91e1464718009c5f7a86cc8824961620b0b8c3b9c81ffc097"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wvkO1uOcEyyyWWu+wzJg+U3cNA6uL5PcTBDOzGVIZVJdZH8zVhR/F4an+avTv/EN0bq/7pzBTidbed8Z+QyPAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T19:42:28.561399Z","bundle_sha256":"bbf124a51c689a60ae1e874319f19d30c0fff2fb70579ba16a9ed288e570de38"}}