{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LCAXW5TLTRPU2KH3H7E2X74NTX","short_pith_number":"pith:LCAXW5TL","schema_version":"1.0","canonical_sha256":"58817b766b9c5f4d28fb3fc9abff8d9dc100e1dcb5dc5cc55d2bb92bf01b4cef","source":{"kind":"arxiv","id":"2603.25739","version":2},"attestation_state":"computed","paper":{"title":"MegaFlow: Zero-Shot Large Displacement Optical Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingxi Zhang, Fangjinhua Wang, Haofei Xu, Marc Pollefeys","submitted_at":"2026-03-26T17:59:51Z","abstract_excerpt":"Accurate estimation of large displacement optical flow remains a critical challenge. Existing methods typically rely on iterative local search or/and domain-specific fine-tuning, which severely limits their performance in large displacement and zero-shot generalization scenarios. To overcome this, we introduce MegaFlow, a simple yet powerful model for zero-shot large displacement optical flow. Rather than relying on highly complex, task-specific architectural designs, MegaFlow adapts powerful pre-trained vision priors to produce temporally consistent motion fields. In particular, we formulate "},"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":"2603.25739","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-26T17:59:51Z","cross_cats_sorted":[],"title_canon_sha256":"c186a090c495c8de924ae252fb0a903fb56926bab7b2600de2cec40b7e319863","abstract_canon_sha256":"e7f2290430ba62ed61519fc31d7f2e3ceaf257c1d5cff7802063eaea503ac3e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T00:19:13.607958Z","signature_b64":"j/mTF2PXRWaspuF+jp8GLLBK4MUL5ytyAVZ5rjs1dHIPxAFQz5brC0rJzqrq69HCJyB/EWACOTTEeh0KMiOYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58817b766b9c5f4d28fb3fc9abff8d9dc100e1dcb5dc5cc55d2bb92bf01b4cef","last_reissued_at":"2026-07-09T00:19:13.607106Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T00:19:13.607106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MegaFlow: Zero-Shot Large Displacement Optical Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingxi Zhang, Fangjinhua Wang, Haofei Xu, Marc Pollefeys","submitted_at":"2026-03-26T17:59:51Z","abstract_excerpt":"Accurate estimation of large displacement optical flow remains a critical challenge. Existing methods typically rely on iterative local search or/and domain-specific fine-tuning, which severely limits their performance in large displacement and zero-shot generalization scenarios. To overcome this, we introduce MegaFlow, a simple yet powerful model for zero-shot large displacement optical flow. Rather than relying on highly complex, task-specific architectural designs, MegaFlow adapts powerful pre-trained vision priors to produce temporally consistent motion fields. In particular, we formulate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.25739","kind":"arxiv","version":2},"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/2603.25739/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":"2603.25739","created_at":"2026-07-09T00:19:13.607225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.25739v2","created_at":"2026-07-09T00:19:13.607225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.25739","created_at":"2026-07-09T00:19:13.607225+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCAXW5TLTRPU","created_at":"2026-07-09T00:19:13.607225+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCAXW5TLTRPU2KH3","created_at":"2026-07-09T00:19:13.607225+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCAXW5TL","created_at":"2026-07-09T00:19:13.607225+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.27817","citing_title":"Turning Video Models into Generalist Robot Policies","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCAXW5TLTRPU2KH3H7E2X74NTX","json":"https://pith.science/pith/LCAXW5TLTRPU2KH3H7E2X74NTX.json","graph_json":"https://pith.science/api/pith-number/LCAXW5TLTRPU2KH3H7E2X74NTX/graph.json","events_json":"https://pith.science/api/pith-number/LCAXW5TLTRPU2KH3H7E2X74NTX/events.json","paper":"https://pith.science/paper/LCAXW5TL"},"agent_actions":{"view_html":"https://pith.science/pith/LCAXW5TLTRPU2KH3H7E2X74NTX","download_json":"https://pith.science/pith/LCAXW5TLTRPU2KH3H7E2X74NTX.json","view_paper":"https://pith.science/paper/LCAXW5TL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.25739&json=true","fetch_graph":"https://pith.science/api/pith-number/LCAXW5TLTRPU2KH3H7E2X74NTX/graph.json","fetch_events":"https://pith.science/api/pith-number/LCAXW5TLTRPU2KH3H7E2X74NTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCAXW5TLTRPU2KH3H7E2X74NTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCAXW5TLTRPU2KH3H7E2X74NTX/action/storage_attestation","attest_author":"https://pith.science/pith/LCAXW5TLTRPU2KH3H7E2X74NTX/action/author_attestation","sign_citation":"https://pith.science/pith/LCAXW5TLTRPU2KH3H7E2X74NTX/action/citation_signature","submit_replication":"https://pith.science/pith/LCAXW5TLTRPU2KH3H7E2X74NTX/action/replication_record"}},"created_at":"2026-07-09T00:19:13.607225+00:00","updated_at":"2026-07-09T00:19:13.607225+00:00"}