{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RJB3OHRP46XH2H3YI7MF4WDTI7","short_pith_number":"pith:RJB3OHRP","canonical_record":{"source":{"id":"2601.17950","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-25T18:59:45Z","cross_cats_sorted":[],"title_canon_sha256":"794d3687fb772a310639722bab43252b95383413f00565b6fb3525905fd4e3f5","abstract_canon_sha256":"cb55742023183cdff0bcdebc9882dd88634a58916926e96ac37abb35972742cd"},"schema_version":"1.0"},"canonical_sha256":"8a43b71e2fe7ae7d1f7847d85e587347da6b8c91113be4178ef175e4677caaee","source":{"kind":"arxiv","id":"2601.17950","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.17950","created_at":"2026-07-21T01:20:42Z"},{"alias_kind":"arxiv_version","alias_value":"2601.17950v2","created_at":"2026-07-21T01:20:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.17950","created_at":"2026-07-21T01:20:42Z"},{"alias_kind":"pith_short_12","alias_value":"RJB3OHRP46XH","created_at":"2026-07-21T01:20:42Z"},{"alias_kind":"pith_short_16","alias_value":"RJB3OHRP46XH2H3Y","created_at":"2026-07-21T01:20:42Z"},{"alias_kind":"pith_short_8","alias_value":"RJB3OHRP","created_at":"2026-07-21T01:20:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RJB3OHRP46XH2H3YI7MF4WDTI7","target":"record","payload":{"canonical_record":{"source":{"id":"2601.17950","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-25T18:59:45Z","cross_cats_sorted":[],"title_canon_sha256":"794d3687fb772a310639722bab43252b95383413f00565b6fb3525905fd4e3f5","abstract_canon_sha256":"cb55742023183cdff0bcdebc9882dd88634a58916926e96ac37abb35972742cd"},"schema_version":"1.0"},"canonical_sha256":"8a43b71e2fe7ae7d1f7847d85e587347da6b8c91113be4178ef175e4677caaee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:20:42.616236Z","signature_b64":"P5kYavb3PNBb9L8i21nJLWcwQ96X+yDwbQa/9FdSgWLNydNa1hE7UyyrID5L+EEGPlDcOUysAVJt44RTapHJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a43b71e2fe7ae7d1f7847d85e587347da6b8c91113be4178ef175e4677caaee","last_reissued_at":"2026-07-21T01:20:42.615267Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:20:42.615267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.17950","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-21T01:20:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X1KNRgsIp80lsQt/HE63pQGPLptgEsUm3UDa+V1noGo9jL3ay2Nq3kV7e3bcbFvEsCoOQFtnuhoSAR2PUaxvDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:57:39.745179Z"},"content_sha256":"60ea59548784aeb5840cb310a408112354fa54cf24d18b38a59fc6ca8c38798b","schema_version":"1.0","event_id":"sha256:60ea59548784aeb5840cb310a408112354fa54cf24d18b38a59fc6ca8c38798b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RJB3OHRP46XH2H3YI7MF4WDTI7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Anirud Aggarwal, Matthew Walmer, Saksham Suri","submitted_at":"2026-01-25T18:59:45Z","abstract_excerpt":"The space of task-agnostic feature upsampling has emerged as a promising area of research to efficiently create denser features from pre-trained visual backbones. These methods act as a shortcut to achieve dense features for a fraction of the cost by learning to map low-resolution features to high-resolution versions. While early works in this space used iterative upsampling approaches, more recent works have switched to cross-attention-based methods, which risk falling into the same efficiency scaling problems of the backbones they are upsampling. In this work, we demonstrate that iterative u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.17950","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/2601.17950/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":"2026-07-21T01:20:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tLpf7J8cv0EiXyxnCOVWHaJFSEGVIOJYtR6yBq9qme6KRBohQ+qOPWwexAKBz+LeDg/yepC/BbUDXNPiiY6UBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:57:39.745673Z"},"content_sha256":"72303ec2c0a4885184c253ebb23a1d2eadb04c364b48891e68ec65fd09cdc3cb","schema_version":"1.0","event_id":"sha256:72303ec2c0a4885184c253ebb23a1d2eadb04c364b48891e68ec65fd09cdc3cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RJB3OHRP46XH2H3YI7MF4WDTI7/bundle.json","state_url":"https://pith.science/pith/RJB3OHRP46XH2H3YI7MF4WDTI7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RJB3OHRP46XH2H3YI7MF4WDTI7/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":"2026-08-04T01:57:39Z","links":{"resolver":"https://pith.science/pith/RJB3OHRP46XH2H3YI7MF4WDTI7","bundle":"https://pith.science/pith/RJB3OHRP46XH2H3YI7MF4WDTI7/bundle.json","state":"https://pith.science/pith/RJB3OHRP46XH2H3YI7MF4WDTI7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RJB3OHRP46XH2H3YI7MF4WDTI7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RJB3OHRP46XH2H3YI7MF4WDTI7","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":"cb55742023183cdff0bcdebc9882dd88634a58916926e96ac37abb35972742cd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-25T18:59:45Z","title_canon_sha256":"794d3687fb772a310639722bab43252b95383413f00565b6fb3525905fd4e3f5"},"schema_version":"1.0","source":{"id":"2601.17950","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.17950","created_at":"2026-07-21T01:20:42Z"},{"alias_kind":"arxiv_version","alias_value":"2601.17950v2","created_at":"2026-07-21T01:20:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.17950","created_at":"2026-07-21T01:20:42Z"},{"alias_kind":"pith_short_12","alias_value":"RJB3OHRP46XH","created_at":"2026-07-21T01:20:42Z"},{"alias_kind":"pith_short_16","alias_value":"RJB3OHRP46XH2H3Y","created_at":"2026-07-21T01:20:42Z"},{"alias_kind":"pith_short_8","alias_value":"RJB3OHRP","created_at":"2026-07-21T01:20:42Z"}],"graph_snapshots":[{"event_id":"sha256:72303ec2c0a4885184c253ebb23a1d2eadb04c364b48891e68ec65fd09cdc3cb","target":"graph","created_at":"2026-07-21T01:20:42Z","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/2601.17950/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The space of task-agnostic feature upsampling has emerged as a promising area of research to efficiently create denser features from pre-trained visual backbones. These methods act as a shortcut to achieve dense features for a fraction of the cost by learning to map low-resolution features to high-resolution versions. While early works in this space used iterative upsampling approaches, more recent works have switched to cross-attention-based methods, which risk falling into the same efficiency scaling problems of the backbones they are upsampling. In this work, we demonstrate that iterative u","authors_text":"Abhinav Shrivastava, Anirud Aggarwal, Matthew Walmer, Saksham Suri","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-25T18:59:45Z","title":"UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.17950","kind":"arxiv","version":2},"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":"sha256:60ea59548784aeb5840cb310a408112354fa54cf24d18b38a59fc6ca8c38798b","target":"record","created_at":"2026-07-21T01:20:42Z","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":"cb55742023183cdff0bcdebc9882dd88634a58916926e96ac37abb35972742cd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-25T18:59:45Z","title_canon_sha256":"794d3687fb772a310639722bab43252b95383413f00565b6fb3525905fd4e3f5"},"schema_version":"1.0","source":{"id":"2601.17950","kind":"arxiv","version":2}},"canonical_sha256":"8a43b71e2fe7ae7d1f7847d85e587347da6b8c91113be4178ef175e4677caaee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a43b71e2fe7ae7d1f7847d85e587347da6b8c91113be4178ef175e4677caaee","first_computed_at":"2026-07-21T01:20:42.615267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:20:42.615267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P5kYavb3PNBb9L8i21nJLWcwQ96X+yDwbQa/9FdSgWLNydNa1hE7UyyrID5L+EEGPlDcOUysAVJt44RTapHJCg==","signature_status":"signed_v1","signed_at":"2026-07-21T01:20:42.616236Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.17950","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60ea59548784aeb5840cb310a408112354fa54cf24d18b38a59fc6ca8c38798b","sha256:72303ec2c0a4885184c253ebb23a1d2eadb04c364b48891e68ec65fd09cdc3cb"],"state_sha256":"01487d479499484022a610c07b01030259c2270553db0c7277e9a44d8681a58b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dP40pNhF787x9JG1SVFAVnlSZNJbu98wnXS45vJ3y5NOm1L/oH422kmT8wGtGtWPSgcP++qUXnnF0+LD0H9DAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T01:57:39.749837Z","bundle_sha256":"31447f1e7142c352cc654aaaf76886062d22b882a5d7fe679421babd336a33c7"}}