{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5ME27IVZNG3KZ2QCJP253JB3B6","short_pith_number":"pith:5ME27IVZ","canonical_record":{"source":{"id":"2507.19272","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T13:52:31Z","cross_cats_sorted":[],"title_canon_sha256":"bb5ba9223c3e4d1e3c47f1e7683c45cac670f5a740fee288ee83ad660f7b77f0","abstract_canon_sha256":"d42c1352cd578ccba16362808fb4ca8227e4302b2bef172abfa7aa8e4f1dffcd"},"schema_version":"1.0"},"canonical_sha256":"eb09afa2b969b6acea024bf5dda43b0fa5e14a3cf8cf31bb868e2015903e9c53","source":{"kind":"arxiv","id":"2507.19272","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19272","created_at":"2026-07-05T11:43:22Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19272v1","created_at":"2026-07-05T11:43:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19272","created_at":"2026-07-05T11:43:22Z"},{"alias_kind":"pith_short_12","alias_value":"5ME27IVZNG3K","created_at":"2026-07-05T11:43:22Z"},{"alias_kind":"pith_short_16","alias_value":"5ME27IVZNG3KZ2QC","created_at":"2026-07-05T11:43:22Z"},{"alias_kind":"pith_short_8","alias_value":"5ME27IVZ","created_at":"2026-07-05T11:43:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5ME27IVZNG3KZ2QCJP253JB3B6","target":"record","payload":{"canonical_record":{"source":{"id":"2507.19272","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T13:52:31Z","cross_cats_sorted":[],"title_canon_sha256":"bb5ba9223c3e4d1e3c47f1e7683c45cac670f5a740fee288ee83ad660f7b77f0","abstract_canon_sha256":"d42c1352cd578ccba16362808fb4ca8227e4302b2bef172abfa7aa8e4f1dffcd"},"schema_version":"1.0"},"canonical_sha256":"eb09afa2b969b6acea024bf5dda43b0fa5e14a3cf8cf31bb868e2015903e9c53","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:22.673984Z","signature_b64":"e1LGBU1SfUIynL72vXOhIu5iad9/IeRwXK3FbXk3etPIdlwHgBaD4QnWRae6E8MZmswID01dY3I2JFT//AX1DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb09afa2b969b6acea024bf5dda43b0fa5e14a3cf8cf31bb868e2015903e9c53","last_reissued_at":"2026-07-05T11:43:22.673494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:22.673494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.19272","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":"2026-07-05T11:43:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jxMRchCH1z06t95v1FMx+yFbzkRJUIMLXk661iO4kov/Hh4cEqAcylT8vP1SujcMPzOMOKgserQ2+DKdyMDjBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:10:04.872029Z"},"content_sha256":"aaedb9bbb26e3d4d5a2d308756f73faa7857e4adb01df88bf88e64a7f95cf121","schema_version":"1.0","event_id":"sha256:aaedb9bbb26e3d4d5a2d308756f73faa7857e4adb01df88bf88e64a7f95cf121"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5ME27IVZNG3KZ2QCJP253JB3B6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video Self-Distillation for Single-Image Encoders: A Step Toward Physically Plausible Perception","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Marcel Simon, Seul-Ki Yeom, Tae-Ho Kim","submitted_at":"2025-07-25T13:52:31Z","abstract_excerpt":"Self-supervised image encoders such as DINO have recently gained significant interest for learning robust visual features without labels. However, most SSL methods train on static images and miss the temporal cues inherent in videos. We introduce a video-distilled single-image encoder trained to predict the next-frame representation from the current frame. This simple objective injects 3D spatial and temporal priors without optical flow or tracking. When pre-training on a single 2-hour video, our approach raises the mean Intersection-over-Union (mIoU) on ADE20K from 35.0 (DoRA) to 36.4 while r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19272","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/2507.19272/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":"2026-07-05T11:43:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GafX43abBaWvYDtC4mDY1iQMlli/6eRv6RZc12kLdtbJWIZwG/6xp1I785PgGxUk4tzrOm9QEnMrxfoqIW4YDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:10:04.872716Z"},"content_sha256":"b2dbb040b11f65813aaf87e612b94ff37f79f85f2282e5cad59f066aa380eb9f","schema_version":"1.0","event_id":"sha256:b2dbb040b11f65813aaf87e612b94ff37f79f85f2282e5cad59f066aa380eb9f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5ME27IVZNG3KZ2QCJP253JB3B6/bundle.json","state_url":"https://pith.science/pith/5ME27IVZNG3KZ2QCJP253JB3B6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5ME27IVZNG3KZ2QCJP253JB3B6/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":"2026-08-17T18:10:04Z","links":{"resolver":"https://pith.science/pith/5ME27IVZNG3KZ2QCJP253JB3B6","bundle":"https://pith.science/pith/5ME27IVZNG3KZ2QCJP253JB3B6/bundle.json","state":"https://pith.science/pith/5ME27IVZNG3KZ2QCJP253JB3B6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5ME27IVZNG3KZ2QCJP253JB3B6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5ME27IVZNG3KZ2QCJP253JB3B6","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":"d42c1352cd578ccba16362808fb4ca8227e4302b2bef172abfa7aa8e4f1dffcd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T13:52:31Z","title_canon_sha256":"bb5ba9223c3e4d1e3c47f1e7683c45cac670f5a740fee288ee83ad660f7b77f0"},"schema_version":"1.0","source":{"id":"2507.19272","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19272","created_at":"2026-07-05T11:43:22Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19272v1","created_at":"2026-07-05T11:43:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19272","created_at":"2026-07-05T11:43:22Z"},{"alias_kind":"pith_short_12","alias_value":"5ME27IVZNG3K","created_at":"2026-07-05T11:43:22Z"},{"alias_kind":"pith_short_16","alias_value":"5ME27IVZNG3KZ2QC","created_at":"2026-07-05T11:43:22Z"},{"alias_kind":"pith_short_8","alias_value":"5ME27IVZ","created_at":"2026-07-05T11:43:22Z"}],"graph_snapshots":[{"event_id":"sha256:b2dbb040b11f65813aaf87e612b94ff37f79f85f2282e5cad59f066aa380eb9f","target":"graph","created_at":"2026-07-05T11:43:22Z","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/2507.19272/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised image encoders such as DINO have recently gained significant interest for learning robust visual features without labels. However, most SSL methods train on static images and miss the temporal cues inherent in videos. We introduce a video-distilled single-image encoder trained to predict the next-frame representation from the current frame. This simple objective injects 3D spatial and temporal priors without optical flow or tracking. When pre-training on a single 2-hour video, our approach raises the mean Intersection-over-Union (mIoU) on ADE20K from 35.0 (DoRA) to 36.4 while r","authors_text":"Marcel Simon, Seul-Ki Yeom, Tae-Ho Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T13:52:31Z","title":"Video Self-Distillation for Single-Image Encoders: A Step Toward Physically Plausible Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19272","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:aaedb9bbb26e3d4d5a2d308756f73faa7857e4adb01df88bf88e64a7f95cf121","target":"record","created_at":"2026-07-05T11:43:22Z","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":"d42c1352cd578ccba16362808fb4ca8227e4302b2bef172abfa7aa8e4f1dffcd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T13:52:31Z","title_canon_sha256":"bb5ba9223c3e4d1e3c47f1e7683c45cac670f5a740fee288ee83ad660f7b77f0"},"schema_version":"1.0","source":{"id":"2507.19272","kind":"arxiv","version":1}},"canonical_sha256":"eb09afa2b969b6acea024bf5dda43b0fa5e14a3cf8cf31bb868e2015903e9c53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb09afa2b969b6acea024bf5dda43b0fa5e14a3cf8cf31bb868e2015903e9c53","first_computed_at":"2026-07-05T11:43:22.673494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:22.673494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e1LGBU1SfUIynL72vXOhIu5iad9/IeRwXK3FbXk3etPIdlwHgBaD4QnWRae6E8MZmswID01dY3I2JFT//AX1DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:22.673984Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19272","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aaedb9bbb26e3d4d5a2d308756f73faa7857e4adb01df88bf88e64a7f95cf121","sha256:b2dbb040b11f65813aaf87e612b94ff37f79f85f2282e5cad59f066aa380eb9f"],"state_sha256":"72669112d5ef7de0db7d220c5449116a577691c639453b52410ecc7c0086109f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IPCoqUt9Fd+2yxHn0U3uJT6oGn864bZGh2RkXJ56ZfS3qFZjZLh9f66UTcAEBTwdUqZ5JhI23D6H1xdXiNy+CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T18:10:04.879842Z","bundle_sha256":"17769acbc669f54ba35519851c999078a37d9f78497b4fd9982f83fb4f796636"}}