{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OMQKGES5K7726YJ64A5BPIBXDR","short_pith_number":"pith:OMQKGES5","canonical_record":{"source":{"id":"2405.16382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T23:55:47Z","cross_cats_sorted":[],"title_canon_sha256":"fd0fd1b665df0afa0e745fe73784017f565fa1aa11dc381032eeeaf952b490fc","abstract_canon_sha256":"f8fa070fe3526eb376e8ef46560aa96f6c8777c953b32a41b9690ce5e1b1eb8b"},"schema_version":"1.0"},"canonical_sha256":"7320a3125d57ffaf613ee03a17a0371c41ae8faad825fdc950622cfc8a6712d2","source":{"kind":"arxiv","id":"2405.16382","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16382","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16382v1","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16382","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"pith_short_12","alias_value":"OMQKGES5K772","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"pith_short_16","alias_value":"OMQKGES5K7726YJ6","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"pith_short_8","alias_value":"OMQKGES5","created_at":"2026-07-05T08:23:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OMQKGES5K7726YJ64A5BPIBXDR","target":"record","payload":{"canonical_record":{"source":{"id":"2405.16382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T23:55:47Z","cross_cats_sorted":[],"title_canon_sha256":"fd0fd1b665df0afa0e745fe73784017f565fa1aa11dc381032eeeaf952b490fc","abstract_canon_sha256":"f8fa070fe3526eb376e8ef46560aa96f6c8777c953b32a41b9690ce5e1b1eb8b"},"schema_version":"1.0"},"canonical_sha256":"7320a3125d57ffaf613ee03a17a0371c41ae8faad825fdc950622cfc8a6712d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:29.379326Z","signature_b64":"3wLmr/fkycYnbvnDM8Yy+97x99FqIKDKJSgOzYbntmGYukl57MuvO9ZHKRDbBC47TARuFbEdJNTRalrl1IWxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7320a3125d57ffaf613ee03a17a0371c41ae8faad825fdc950622cfc8a6712d2","last_reissued_at":"2026-07-05T08:23:29.378882Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:29.378882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.16382","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":"2026-07-05T08:23:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kJ261q7EQkddltu89SNhFf1AfqR664ordVEh3Q5tgtwppm0Az/gksnoLO7zRJm7bzoi8aYNSPyhonhPk2gpGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:55:50.564981Z"},"content_sha256":"4dc37abd7e770baa489c3b5d10343dc0b25c78d4c44a777c0ee00072811ef89d","schema_version":"1.0","event_id":"sha256:4dc37abd7e770baa489c3b5d10343dc0b25c78d4c44a777c0ee00072811ef89d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OMQKGES5K7726YJ64A5BPIBXDR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video Prediction Models as General Visual Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"James Maier, Nishanth Mohankumar","submitted_at":"2024-05-25T23:55:47Z","abstract_excerpt":"This study explores the potential of open-source video conditional generation models as encoders for downstream tasks, focusing on instance segmentation using the BAIR Robot Pushing Dataset. The researchers propose using video prediction models as general visual encoders, leveraging their ability to capture critical spatial and temporal information which is essential for tasks such as instance segmentation. Inspired by human vision studies, particularly Gestalts principle of common fate, the approach aims to develop a latent space representative of motion from images to effectively discern for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16382","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/2405.16382/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":"2026-07-05T08:23:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3cQsdJf6pnEuMh+NyJIm/7H5IE6VuUa+RS7joRy5Qqzugrb3OXV/ZO91s5nI+UpyR01u0mfMdLGSp1gyRMnkDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:55:50.565485Z"},"content_sha256":"71720dc9447dcfca093e64c7126bf90e8276a85a8673c7fe0816198f7d881d4c","schema_version":"1.0","event_id":"sha256:71720dc9447dcfca093e64c7126bf90e8276a85a8673c7fe0816198f7d881d4c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OMQKGES5K7726YJ64A5BPIBXDR/bundle.json","state_url":"https://pith.science/pith/OMQKGES5K7726YJ64A5BPIBXDR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OMQKGES5K7726YJ64A5BPIBXDR/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":"2026-08-23T17:55:50Z","links":{"resolver":"https://pith.science/pith/OMQKGES5K7726YJ64A5BPIBXDR","bundle":"https://pith.science/pith/OMQKGES5K7726YJ64A5BPIBXDR/bundle.json","state":"https://pith.science/pith/OMQKGES5K7726YJ64A5BPIBXDR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OMQKGES5K7726YJ64A5BPIBXDR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OMQKGES5K7726YJ64A5BPIBXDR","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":"f8fa070fe3526eb376e8ef46560aa96f6c8777c953b32a41b9690ce5e1b1eb8b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T23:55:47Z","title_canon_sha256":"fd0fd1b665df0afa0e745fe73784017f565fa1aa11dc381032eeeaf952b490fc"},"schema_version":"1.0","source":{"id":"2405.16382","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16382","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16382v1","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16382","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"pith_short_12","alias_value":"OMQKGES5K772","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"pith_short_16","alias_value":"OMQKGES5K7726YJ6","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"pith_short_8","alias_value":"OMQKGES5","created_at":"2026-07-05T08:23:29Z"}],"graph_snapshots":[{"event_id":"sha256:71720dc9447dcfca093e64c7126bf90e8276a85a8673c7fe0816198f7d881d4c","target":"graph","created_at":"2026-07-05T08:23:29Z","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/2405.16382/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study explores the potential of open-source video conditional generation models as encoders for downstream tasks, focusing on instance segmentation using the BAIR Robot Pushing Dataset. The researchers propose using video prediction models as general visual encoders, leveraging their ability to capture critical spatial and temporal information which is essential for tasks such as instance segmentation. Inspired by human vision studies, particularly Gestalts principle of common fate, the approach aims to develop a latent space representative of motion from images to effectively discern for","authors_text":"James Maier, Nishanth Mohankumar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T23:55:47Z","title":"Video Prediction Models as General Visual Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16382","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":"sha256:4dc37abd7e770baa489c3b5d10343dc0b25c78d4c44a777c0ee00072811ef89d","target":"record","created_at":"2026-07-05T08:23:29Z","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":"f8fa070fe3526eb376e8ef46560aa96f6c8777c953b32a41b9690ce5e1b1eb8b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T23:55:47Z","title_canon_sha256":"fd0fd1b665df0afa0e745fe73784017f565fa1aa11dc381032eeeaf952b490fc"},"schema_version":"1.0","source":{"id":"2405.16382","kind":"arxiv","version":1}},"canonical_sha256":"7320a3125d57ffaf613ee03a17a0371c41ae8faad825fdc950622cfc8a6712d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7320a3125d57ffaf613ee03a17a0371c41ae8faad825fdc950622cfc8a6712d2","first_computed_at":"2026-07-05T08:23:29.378882Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:29.378882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3wLmr/fkycYnbvnDM8Yy+97x99FqIKDKJSgOzYbntmGYukl57MuvO9ZHKRDbBC47TARuFbEdJNTRalrl1IWxCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:29.379326Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16382","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4dc37abd7e770baa489c3b5d10343dc0b25c78d4c44a777c0ee00072811ef89d","sha256:71720dc9447dcfca093e64c7126bf90e8276a85a8673c7fe0816198f7d881d4c"],"state_sha256":"e8d4d8d9a2bf150874802fb6b8f71f878f2d6fada7a2d767e6a9ab4b3d05dd15"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qEcPM8XA9jqeo9ZvAhmFF4sTAIb5q9/gjQpuu/QyJSIaGiWJvIzkJ5xa+sjrUrPOEG9z3NaCoL+tAYXHSL16AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T17:55:50.569485Z","bundle_sha256":"c0936b8a30bdfeafa36d4ad134b4d3a5a382e323ee73d9c695cab4c89ecfe067"}}