{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O2MBKA3B77QNBJKY5KEDMTTJAL","short_pith_number":"pith:O2MBKA3B","schema_version":"1.0","canonical_sha256":"7698150361ffe0d0a558ea88364e6902ea4681d5401afab2bea639eee989de52","source":{"kind":"arxiv","id":"2404.16828","version":3},"attestation_state":"computed","paper":{"title":"Made to Order: Discovering monotonic temporal changes via self-supervised video ordering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Charig Yang, Weidi Xie","submitted_at":"2024-04-25T17:59:56Z","abstract_excerpt":"Our objective is to discover and localize monotonic temporal changes in a sequence of images. To achieve this, we exploit a simple proxy task of ordering a shuffled image sequence, with `time' serving as a supervisory signal, since only changes that are monotonic with time can give rise to the correct ordering. We also introduce a transformer-based model for ordering of image sequences of arbitrary length with built-in attribution maps. After training, the model successfully discovers and localizes monotonic changes while ignoring cyclic and stochastic ones. We demonstrate applications of the "},"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":"2404.16828","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-25T17:59:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6c1caa974f3d344df3bf47b21ad879c6e6ebab724effdc1b32dfaf7c7b3db45d","abstract_canon_sha256":"0b4dc50ee21096d69811915e6c120fd8a56fc2970ab9f780c885a0a8a11e53f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:49.707374Z","signature_b64":"1ygNZQpykL3to/7RIX91Va9kClDX6OKj02hFXUytsO7Mat7FrjYLpwkNTVkJz6YwRqX5hx2dfz3cfomLCjEnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7698150361ffe0d0a558ea88364e6902ea4681d5401afab2bea639eee989de52","last_reissued_at":"2026-07-05T08:54:49.706892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:49.706892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Made to Order: Discovering monotonic temporal changes via self-supervised video ordering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Charig Yang, Weidi Xie","submitted_at":"2024-04-25T17:59:56Z","abstract_excerpt":"Our objective is to discover and localize monotonic temporal changes in a sequence of images. To achieve this, we exploit a simple proxy task of ordering a shuffled image sequence, with `time' serving as a supervisory signal, since only changes that are monotonic with time can give rise to the correct ordering. We also introduce a transformer-based model for ordering of image sequences of arbitrary length with built-in attribution maps. After training, the model successfully discovers and localizes monotonic changes while ignoring cyclic and stochastic ones. We demonstrate applications of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16828","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/2404.16828/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":"2404.16828","created_at":"2026-07-05T08:54:49.706955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.16828v3","created_at":"2026-07-05T08:54:49.706955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16828","created_at":"2026-07-05T08:54:49.706955+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2MBKA3B77QN","created_at":"2026-07-05T08:54:49.706955+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2MBKA3B77QNBJKY","created_at":"2026-07-05T08:54:49.706955+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2MBKA3B","created_at":"2026-07-05T08:54:49.706955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.13511","citing_title":"Adapting MLLMs for Nuanced Video Retrieval","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O2MBKA3B77QNBJKY5KEDMTTJAL","json":"https://pith.science/pith/O2MBKA3B77QNBJKY5KEDMTTJAL.json","graph_json":"https://pith.science/api/pith-number/O2MBKA3B77QNBJKY5KEDMTTJAL/graph.json","events_json":"https://pith.science/api/pith-number/O2MBKA3B77QNBJKY5KEDMTTJAL/events.json","paper":"https://pith.science/paper/O2MBKA3B"},"agent_actions":{"view_html":"https://pith.science/pith/O2MBKA3B77QNBJKY5KEDMTTJAL","download_json":"https://pith.science/pith/O2MBKA3B77QNBJKY5KEDMTTJAL.json","view_paper":"https://pith.science/paper/O2MBKA3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.16828&json=true","fetch_graph":"https://pith.science/api/pith-number/O2MBKA3B77QNBJKY5KEDMTTJAL/graph.json","fetch_events":"https://pith.science/api/pith-number/O2MBKA3B77QNBJKY5KEDMTTJAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2MBKA3B77QNBJKY5KEDMTTJAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2MBKA3B77QNBJKY5KEDMTTJAL/action/storage_attestation","attest_author":"https://pith.science/pith/O2MBKA3B77QNBJKY5KEDMTTJAL/action/author_attestation","sign_citation":"https://pith.science/pith/O2MBKA3B77QNBJKY5KEDMTTJAL/action/citation_signature","submit_replication":"https://pith.science/pith/O2MBKA3B77QNBJKY5KEDMTTJAL/action/replication_record"}},"created_at":"2026-07-05T08:54:49.706955+00:00","updated_at":"2026-07-05T08:54:49.706955+00:00"}