{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5HPYDAPF6TL5DROIEHLMFAOOF3","short_pith_number":"pith:5HPYDAPF","schema_version":"1.0","canonical_sha256":"e9df8181e5f4d7d1c5c821d6c281ce2ef71a8a6a213416ee8d3e2995f62244a7","source":{"kind":"arxiv","id":"2607.17120","version":1},"attestation_state":"computed","paper":{"title":"The generator is the tracker: Multi-object tracking by painting persistent identity colours","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiyu Yang, Miel Hostens","submitted_at":"2026-07-19T08:11:44Z","abstract_excerpt":"Multi-object tracking (MOT) is conventionally decomposed into detection followed by association, with object identity maintained as external state: track buffers, motion models, and appearance embeddings. We ask whether a video generator can maintain that state in pixels. We fine-tune a 22B text-to-video diffusion model (LTX-2.3) with a lightweight in-context LoRA to translate an RGB clip into an ID-map clip, a video in which every person is painted a flat, distinct color that persists over time: same color, same identity. Long videos are generated as chained windows, where each window is cond"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.17120","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-19T08:11:44Z","cross_cats_sorted":[],"title_canon_sha256":"b564e38debac4f9ab8830a8678346bdbcec96889fce8406ca4b2045216cf899c","abstract_canon_sha256":"8a383d85f508bacee8eeb9e1d3324ddb0cb00c4d29f5fe172ddeb571cae252f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:16.712108Z","signature_b64":"8fQkCtuObkAa5NUn42IXXPqhR1aUPA1fMb0UaMYMLT5ujaHGTl3TZJ1Uy4AcKL5e5nKZcWTLxnx/4BvAKgpbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9df8181e5f4d7d1c5c821d6c281ce2ef71a8a6a213416ee8d3e2995f62244a7","last_reissued_at":"2026-07-21T01:21:16.711157Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:16.711157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The generator is the tracker: Multi-object tracking by painting persistent identity colours","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiyu Yang, Miel Hostens","submitted_at":"2026-07-19T08:11:44Z","abstract_excerpt":"Multi-object tracking (MOT) is conventionally decomposed into detection followed by association, with object identity maintained as external state: track buffers, motion models, and appearance embeddings. We ask whether a video generator can maintain that state in pixels. We fine-tune a 22B text-to-video diffusion model (LTX-2.3) with a lightweight in-context LoRA to translate an RGB clip into an ID-map clip, a video in which every person is painted a flat, distinct color that persists over time: same color, same identity. Long videos are generated as chained windows, where each window is cond"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17120","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/2607.17120/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.17120","created_at":"2026-07-21T01:21:16.711652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.17120v1","created_at":"2026-07-21T01:21:16.711652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17120","created_at":"2026-07-21T01:21:16.711652+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HPYDAPF6TL5","created_at":"2026-07-21T01:21:16.711652+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HPYDAPF6TL5DROI","created_at":"2026-07-21T01:21:16.711652+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HPYDAPF","created_at":"2026-07-21T01:21:16.711652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5HPYDAPF6TL5DROIEHLMFAOOF3","json":"https://pith.science/pith/5HPYDAPF6TL5DROIEHLMFAOOF3.json","graph_json":"https://pith.science/api/pith-number/5HPYDAPF6TL5DROIEHLMFAOOF3/graph.json","events_json":"https://pith.science/api/pith-number/5HPYDAPF6TL5DROIEHLMFAOOF3/events.json","paper":"https://pith.science/paper/5HPYDAPF"},"agent_actions":{"view_html":"https://pith.science/pith/5HPYDAPF6TL5DROIEHLMFAOOF3","download_json":"https://pith.science/pith/5HPYDAPF6TL5DROIEHLMFAOOF3.json","view_paper":"https://pith.science/paper/5HPYDAPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.17120&json=true","fetch_graph":"https://pith.science/api/pith-number/5HPYDAPF6TL5DROIEHLMFAOOF3/graph.json","fetch_events":"https://pith.science/api/pith-number/5HPYDAPF6TL5DROIEHLMFAOOF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HPYDAPF6TL5DROIEHLMFAOOF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HPYDAPF6TL5DROIEHLMFAOOF3/action/storage_attestation","attest_author":"https://pith.science/pith/5HPYDAPF6TL5DROIEHLMFAOOF3/action/author_attestation","sign_citation":"https://pith.science/pith/5HPYDAPF6TL5DROIEHLMFAOOF3/action/citation_signature","submit_replication":"https://pith.science/pith/5HPYDAPF6TL5DROIEHLMFAOOF3/action/replication_record"}},"created_at":"2026-07-21T01:21:16.711652+00:00","updated_at":"2026-07-21T01:21:16.711652+00:00"}