{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XIDZT3DHD2XAY3KY5NX5TXLARE","short_pith_number":"pith:XIDZT3DH","canonical_record":{"source":{"id":"2412.06016","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T18:21:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"60ac878c3a93fa8794fa232c3fa926dece27077605db151f93beb887f56fefd6","abstract_canon_sha256":"b3fd8107dedd9b763b6407e11ed22d5dd278762ce9d53f3fa036af5de0719304"},"schema_version":"1.0"},"canonical_sha256":"ba0799ec671eae0c6d58eb6fd9dd608915a947b1b1a5b2c1526654aca710b532","source":{"kind":"arxiv","id":"2412.06016","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06016","created_at":"2026-07-05T10:45:14Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06016v3","created_at":"2026-07-05T10:45:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06016","created_at":"2026-07-05T10:45:14Z"},{"alias_kind":"pith_short_12","alias_value":"XIDZT3DHD2XA","created_at":"2026-07-05T10:45:14Z"},{"alias_kind":"pith_short_16","alias_value":"XIDZT3DHD2XAY3KY","created_at":"2026-07-05T10:45:14Z"},{"alias_kind":"pith_short_8","alias_value":"XIDZT3DH","created_at":"2026-07-05T10:45:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XIDZT3DHD2XAY3KY5NX5TXLARE","target":"record","payload":{"canonical_record":{"source":{"id":"2412.06016","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T18:21:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"60ac878c3a93fa8794fa232c3fa926dece27077605db151f93beb887f56fefd6","abstract_canon_sha256":"b3fd8107dedd9b763b6407e11ed22d5dd278762ce9d53f3fa036af5de0719304"},"schema_version":"1.0"},"canonical_sha256":"ba0799ec671eae0c6d58eb6fd9dd608915a947b1b1a5b2c1526654aca710b532","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:14.981912Z","signature_b64":"2f/WGHfMZql3IgEm8lGt8XefO7eDULC3fhCUOWnq0ikLBNeAojk23PszRup/pFjLFw8h+SnOE3b9pwhatK/iAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba0799ec671eae0c6d58eb6fd9dd608915a947b1b1a5b2c1526654aca710b532","last_reissued_at":"2026-07-05T10:45:14.981443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:14.981443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.06016","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:45:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E3lga7wVWyBhRePa9SdsaitOEKI7eukLXaC0J3jn5T6oVcorxVDf7jw2QgMi4Pa9oCK/fysP0S+wBF0rOzeXDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:55:34.793041Z"},"content_sha256":"10442bf222cf81d6149ea1939dffe95db41b720b33fb670d528c7b4d3edb0c13","schema_version":"1.0","event_id":"sha256:10442bf222cf81d6149ea1939dffe95db41b720b33fb670d528c7b4d3edb0c13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XIDZT3DHD2XAY3KY5NX5TXLARE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chun-Hao Paul Huang, Duygu Ceylan, Hyeonho Jeong, Jong Chul Ye, Niloy Mitra","submitted_at":"2024-12-08T18:21:00Z","abstract_excerpt":"While recent foundational video generators produce visually rich output, they still struggle with appearance drift, where objects gradually degrade or change inconsistently across frames, breaking visual coherence. We hypothesize that this is because there is no explicit supervision in terms of spatial tracking at the feature level. We propose Track4Gen, a spatially aware video generator that combines video diffusion loss with point tracking across frames, providing enhanced spatial supervision on the diffusion features. Track4Gen merges the video generation and point tracking tasks into a sin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06016","kind":"arxiv","version":3},"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/2412.06016/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":"2026-07-05T10:45:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lr7xyzrvbNrYVto/kb/QIArsgkbhmhsU5+YXHSjvCILjfrWQ8pPfvta9OvsT+8PZGnBMstCDkMSK6fBT3G83Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:55:34.793578Z"},"content_sha256":"87aea113b99bf6b4d4c131d407349a62ef61c3d0d653358cf28bf0606d7c1574","schema_version":"1.0","event_id":"sha256:87aea113b99bf6b4d4c131d407349a62ef61c3d0d653358cf28bf0606d7c1574"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XIDZT3DHD2XAY3KY5NX5TXLARE/bundle.json","state_url":"https://pith.science/pith/XIDZT3DHD2XAY3KY5NX5TXLARE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XIDZT3DHD2XAY3KY5NX5TXLARE/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":"2026-08-05T14:55:34Z","links":{"resolver":"https://pith.science/pith/XIDZT3DHD2XAY3KY5NX5TXLARE","bundle":"https://pith.science/pith/XIDZT3DHD2XAY3KY5NX5TXLARE/bundle.json","state":"https://pith.science/pith/XIDZT3DHD2XAY3KY5NX5TXLARE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XIDZT3DHD2XAY3KY5NX5TXLARE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XIDZT3DHD2XAY3KY5NX5TXLARE","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":"b3fd8107dedd9b763b6407e11ed22d5dd278762ce9d53f3fa036af5de0719304","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T18:21:00Z","title_canon_sha256":"60ac878c3a93fa8794fa232c3fa926dece27077605db151f93beb887f56fefd6"},"schema_version":"1.0","source":{"id":"2412.06016","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06016","created_at":"2026-07-05T10:45:14Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06016v3","created_at":"2026-07-05T10:45:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06016","created_at":"2026-07-05T10:45:14Z"},{"alias_kind":"pith_short_12","alias_value":"XIDZT3DHD2XA","created_at":"2026-07-05T10:45:14Z"},{"alias_kind":"pith_short_16","alias_value":"XIDZT3DHD2XAY3KY","created_at":"2026-07-05T10:45:14Z"},{"alias_kind":"pith_short_8","alias_value":"XIDZT3DH","created_at":"2026-07-05T10:45:14Z"}],"graph_snapshots":[{"event_id":"sha256:87aea113b99bf6b4d4c131d407349a62ef61c3d0d653358cf28bf0606d7c1574","target":"graph","created_at":"2026-07-05T10:45:14Z","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/2412.06016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While recent foundational video generators produce visually rich output, they still struggle with appearance drift, where objects gradually degrade or change inconsistently across frames, breaking visual coherence. We hypothesize that this is because there is no explicit supervision in terms of spatial tracking at the feature level. We propose Track4Gen, a spatially aware video generator that combines video diffusion loss with point tracking across frames, providing enhanced spatial supervision on the diffusion features. Track4Gen merges the video generation and point tracking tasks into a sin","authors_text":"Chun-Hao Paul Huang, Duygu Ceylan, Hyeonho Jeong, Jong Chul Ye, Niloy Mitra","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T18:21:00Z","title":"Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06016","kind":"arxiv","version":3},"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":"sha256:10442bf222cf81d6149ea1939dffe95db41b720b33fb670d528c7b4d3edb0c13","target":"record","created_at":"2026-07-05T10:45:14Z","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":"b3fd8107dedd9b763b6407e11ed22d5dd278762ce9d53f3fa036af5de0719304","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T18:21:00Z","title_canon_sha256":"60ac878c3a93fa8794fa232c3fa926dece27077605db151f93beb887f56fefd6"},"schema_version":"1.0","source":{"id":"2412.06016","kind":"arxiv","version":3}},"canonical_sha256":"ba0799ec671eae0c6d58eb6fd9dd608915a947b1b1a5b2c1526654aca710b532","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba0799ec671eae0c6d58eb6fd9dd608915a947b1b1a5b2c1526654aca710b532","first_computed_at":"2026-07-05T10:45:14.981443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:14.981443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2f/WGHfMZql3IgEm8lGt8XefO7eDULC3fhCUOWnq0ikLBNeAojk23PszRup/pFjLFw8h+SnOE3b9pwhatK/iAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:14.981912Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06016","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10442bf222cf81d6149ea1939dffe95db41b720b33fb670d528c7b4d3edb0c13","sha256:87aea113b99bf6b4d4c131d407349a62ef61c3d0d653358cf28bf0606d7c1574"],"state_sha256":"ff14b4a77ea7ec1b096c0ffbc3a7144a24e9f2c8a89a65dbec15380f779bf3f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yxE5I0Kj5X0VVVaf6MBI4xwievSI0khKcdJBtzVT88ogrLYLqXcQLha8efYpVXTkBErYe3rjJjLz4iKmBZaFCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T14:55:34.809800Z","bundle_sha256":"dda4b803c32b6897b5fdf2e0e221cedc166aed0aef318e9ed15578f4dfd49e0b"}}