{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KTWN7CGZLJ53XJX7WLHR4ZWYSW","short_pith_number":"pith:KTWN7CGZ","canonical_record":{"source":{"id":"2504.13122","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-17T17:39:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"216671987c58f5142fbfba53e0c7b3c7fe5d31312a59caa38ae9abaef2edfe5b","abstract_canon_sha256":"c9d683c1d561444693df2cca09aa911a7be6bea9852d8c54ed00974021f785c6"},"schema_version":"1.0"},"canonical_sha256":"54ecdf88d95a7bbba6ffb2cf1e66d895a075d9a3219ae9e4ac3b66bb742607d6","source":{"kind":"arxiv","id":"2504.13122","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13122","created_at":"2026-07-05T10:50:37Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13122v1","created_at":"2026-07-05T10:50:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13122","created_at":"2026-07-05T10:50:37Z"},{"alias_kind":"pith_short_12","alias_value":"KTWN7CGZLJ53","created_at":"2026-07-05T10:50:37Z"},{"alias_kind":"pith_short_16","alias_value":"KTWN7CGZLJ53XJX7","created_at":"2026-07-05T10:50:37Z"},{"alias_kind":"pith_short_8","alias_value":"KTWN7CGZ","created_at":"2026-07-05T10:50:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KTWN7CGZLJ53XJX7WLHR4ZWYSW","target":"record","payload":{"canonical_record":{"source":{"id":"2504.13122","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-17T17:39:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"216671987c58f5142fbfba53e0c7b3c7fe5d31312a59caa38ae9abaef2edfe5b","abstract_canon_sha256":"c9d683c1d561444693df2cca09aa911a7be6bea9852d8c54ed00974021f785c6"},"schema_version":"1.0"},"canonical_sha256":"54ecdf88d95a7bbba6ffb2cf1e66d895a075d9a3219ae9e4ac3b66bb742607d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:37.770976Z","signature_b64":"vlr0zgHf4U/JoQNg3RyRaEA0eNThBWzBhOBGcxbSojTZEV+Suz7URUd/7frtfU/t/+CmItbHRuHN5+nQE27OBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54ecdf88d95a7bbba6ffb2cf1e66d895a075d9a3219ae9e4ac3b66bb742607d6","last_reissued_at":"2026-07-05T10:50:37.770270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:37.770270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.13122","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":"2026-07-05T10:50:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mx8XoqS61wF5/8W/TNMPniiI+VUsD7rWqj4qMpGUjU9O7rM4lCdTyIqd9Jl9nXsO2pdCMQ2uqY+3acTi0NnPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:18:40.044134Z"},"content_sha256":"9d3532ddfbed40a9c5b9bf8ba3c23e81c761f2902dff782ecbc5408f35d21fca","schema_version":"1.0","event_id":"sha256:9d3532ddfbed40a9c5b9bf8ba3c23e81c761f2902dff782ecbc5408f35d21fca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KTWN7CGZLJ53XJX7WLHR4ZWYSW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hanwang Zhang, Haodong Chen, Hao Fei, Haojian Huang, Jinlan Fu, Meng Luo, Shengqiong Wu, Xinya Du","submitted_at":"2025-04-17T17:39:41Z","abstract_excerpt":"Large Video Models (LVMs) built upon Large Language Models (LLMs) have shown promise in video understanding but often suffer from misalignment with human intuition and video hallucination issues. To address these challenges, we introduce VistaDPO, a novel framework for Video Hierarchical Spatial-Temporal Direct Preference Optimization. VistaDPO enhances text-video preference alignment across three hierarchical levels: i) Instance Level, aligning overall video content with responses; ii) Temporal Level, aligning video temporal semantics with event descriptions; and iii) Perceptive Level, aligni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13122","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/2504.13122/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":"2026-07-05T10:50:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9J9Ff0dI194XRqju8Dq4VWjkG1sqaUU5Nr2zGihq94CLNP44/u/f76ytVbY2xhEdiJMoCEBZlJhhdU7KzX0cDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:18:40.045126Z"},"content_sha256":"599962d05094a7d284e88fc951a52e27dd6abba3453e50fe0ae6558a5c99d99d","schema_version":"1.0","event_id":"sha256:599962d05094a7d284e88fc951a52e27dd6abba3453e50fe0ae6558a5c99d99d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KTWN7CGZLJ53XJX7WLHR4ZWYSW/bundle.json","state_url":"https://pith.science/pith/KTWN7CGZLJ53XJX7WLHR4ZWYSW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KTWN7CGZLJ53XJX7WLHR4ZWYSW/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":"2026-08-08T19:18:40Z","links":{"resolver":"https://pith.science/pith/KTWN7CGZLJ53XJX7WLHR4ZWYSW","bundle":"https://pith.science/pith/KTWN7CGZLJ53XJX7WLHR4ZWYSW/bundle.json","state":"https://pith.science/pith/KTWN7CGZLJ53XJX7WLHR4ZWYSW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KTWN7CGZLJ53XJX7WLHR4ZWYSW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KTWN7CGZLJ53XJX7WLHR4ZWYSW","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":"c9d683c1d561444693df2cca09aa911a7be6bea9852d8c54ed00974021f785c6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-17T17:39:41Z","title_canon_sha256":"216671987c58f5142fbfba53e0c7b3c7fe5d31312a59caa38ae9abaef2edfe5b"},"schema_version":"1.0","source":{"id":"2504.13122","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13122","created_at":"2026-07-05T10:50:37Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13122v1","created_at":"2026-07-05T10:50:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13122","created_at":"2026-07-05T10:50:37Z"},{"alias_kind":"pith_short_12","alias_value":"KTWN7CGZLJ53","created_at":"2026-07-05T10:50:37Z"},{"alias_kind":"pith_short_16","alias_value":"KTWN7CGZLJ53XJX7","created_at":"2026-07-05T10:50:37Z"},{"alias_kind":"pith_short_8","alias_value":"KTWN7CGZ","created_at":"2026-07-05T10:50:37Z"}],"graph_snapshots":[{"event_id":"sha256:599962d05094a7d284e88fc951a52e27dd6abba3453e50fe0ae6558a5c99d99d","target":"graph","created_at":"2026-07-05T10:50:37Z","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/2504.13122/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Video Models (LVMs) built upon Large Language Models (LLMs) have shown promise in video understanding but often suffer from misalignment with human intuition and video hallucination issues. To address these challenges, we introduce VistaDPO, a novel framework for Video Hierarchical Spatial-Temporal Direct Preference Optimization. VistaDPO enhances text-video preference alignment across three hierarchical levels: i) Instance Level, aligning overall video content with responses; ii) Temporal Level, aligning video temporal semantics with event descriptions; and iii) Perceptive Level, aligni","authors_text":"Hanwang Zhang, Haodong Chen, Hao Fei, Haojian Huang, Jinlan Fu, Meng Luo, Shengqiong Wu, Xinya Du","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-17T17:39:41Z","title":"VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13122","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":"sha256:9d3532ddfbed40a9c5b9bf8ba3c23e81c761f2902dff782ecbc5408f35d21fca","target":"record","created_at":"2026-07-05T10:50:37Z","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":"c9d683c1d561444693df2cca09aa911a7be6bea9852d8c54ed00974021f785c6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-17T17:39:41Z","title_canon_sha256":"216671987c58f5142fbfba53e0c7b3c7fe5d31312a59caa38ae9abaef2edfe5b"},"schema_version":"1.0","source":{"id":"2504.13122","kind":"arxiv","version":1}},"canonical_sha256":"54ecdf88d95a7bbba6ffb2cf1e66d895a075d9a3219ae9e4ac3b66bb742607d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54ecdf88d95a7bbba6ffb2cf1e66d895a075d9a3219ae9e4ac3b66bb742607d6","first_computed_at":"2026-07-05T10:50:37.770270Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:37.770270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vlr0zgHf4U/JoQNg3RyRaEA0eNThBWzBhOBGcxbSojTZEV+Suz7URUd/7frtfU/t/+CmItbHRuHN5+nQE27OBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:37.770976Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.13122","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d3532ddfbed40a9c5b9bf8ba3c23e81c761f2902dff782ecbc5408f35d21fca","sha256:599962d05094a7d284e88fc951a52e27dd6abba3453e50fe0ae6558a5c99d99d"],"state_sha256":"268072b77054b15e4071e1548167ded876edda58af348933ca555a8d1a45c1c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5jsmq8ROKmqv6h+oMGk2uz0fj8HXfimR1PINH2CK6zkAjk9y1uUWQc5QdCCW5X3+LG/CNQXLqjt1rdPyTlacDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:18:40.051930Z","bundle_sha256":"86b99d6f2af0aea69d5b588a44b190fbb118571ff41adcc3e06d239b22fa022e"}}