{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ARQD372AVD7GSKTBBBKT52TISH","short_pith_number":"pith:ARQD372A","canonical_record":{"source":{"id":"2505.16993","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T17:55:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d4f877ad5780c9a065d0f4436848ec5a82c56e7e6f004a9a9d7fea2de26d628d","abstract_canon_sha256":"0c0084193fbb3fe4f96830e7f34f08d14b0e9a2dbf300f6dd4d54c129cf072f9"},"schema_version":"1.0"},"canonical_sha256":"04603dff40a8fe692a6108553eea6891db2677b02a9a5a11ca3b651fbf4ade02","source":{"kind":"arxiv","id":"2505.16993","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16993","created_at":"2026-07-05T11:07:44Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16993v1","created_at":"2026-07-05T11:07:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16993","created_at":"2026-07-05T11:07:44Z"},{"alias_kind":"pith_short_12","alias_value":"ARQD372AVD7G","created_at":"2026-07-05T11:07:44Z"},{"alias_kind":"pith_short_16","alias_value":"ARQD372AVD7GSKTB","created_at":"2026-07-05T11:07:44Z"},{"alias_kind":"pith_short_8","alias_value":"ARQD372A","created_at":"2026-07-05T11:07:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ARQD372AVD7GSKTBBBKT52TISH","target":"record","payload":{"canonical_record":{"source":{"id":"2505.16993","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T17:55:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d4f877ad5780c9a065d0f4436848ec5a82c56e7e6f004a9a9d7fea2de26d628d","abstract_canon_sha256":"0c0084193fbb3fe4f96830e7f34f08d14b0e9a2dbf300f6dd4d54c129cf072f9"},"schema_version":"1.0"},"canonical_sha256":"04603dff40a8fe692a6108553eea6891db2677b02a9a5a11ca3b651fbf4ade02","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:44.224351Z","signature_b64":"yj7gdtyyIJ0EerJkVJIWI2yH902KDJX39C5QLr4WdtoHk1N4BLRS+doiHSh58NG8DGDoHd2KthAkeXDRnvEdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04603dff40a8fe692a6108553eea6891db2677b02a9a5a11ca3b651fbf4ade02","last_reissued_at":"2026-07-05T11:07:44.223825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:44.223825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.16993","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:07:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AyYqhqcRkPhdnoYAL5W1L8WNiFKg4BuU6qXMtvyVqsL25gpltm3LbME2NcBZPWTi26ICNV8kkWtqEWh5F5vFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:32:24.687005Z"},"content_sha256":"460843d13c1f602722d799d8c16d5347a3a9992f23e323ce7e822c321a3f69b3","schema_version":"1.0","event_id":"sha256:460843d13c1f602722d799d8c16d5347a3a9992f23e323ce7e822c321a3f69b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ARQD372AVD7GSKTBBBKT52TISH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Native Segmentation Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aljo\\v{s}a O\\v{s}ep, Guillem Bras\\'o, Laura Leal-Taix\\'e","submitted_at":"2025-05-22T17:55:20Z","abstract_excerpt":"Uniform downsampling remains the de facto standard for reducing spatial resolution in vision backbones. In this work, we propose an alternative design built around a content-aware spatial grouping layer, that dynamically assigns tokens to a reduced set based on image boundaries and their semantic content. Stacking our grouping layer across consecutive backbone stages results in hierarchical segmentation that arises natively in the feature extraction process, resulting in our coined Native Segmentation Vision Transformer. We show that a careful design of our architecture enables the emergence o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16993","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/2505.16993/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":"2026-07-05T11:07:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IVFSpYIkVNSGMyM1GH8ZrHf7gjZRHPxK55dW2rcYnpGXvqOtX3QsWX4MD55COqQJcFRFi2Eco8WZ/4k2yJnxBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:32:24.687856Z"},"content_sha256":"a37b342f83a73a86c749688c0ffe9d9aaf7dbaaa1c6ce5857f50172f295b12da","schema_version":"1.0","event_id":"sha256:a37b342f83a73a86c749688c0ffe9d9aaf7dbaaa1c6ce5857f50172f295b12da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ARQD372AVD7GSKTBBBKT52TISH/bundle.json","state_url":"https://pith.science/pith/ARQD372AVD7GSKTBBBKT52TISH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ARQD372AVD7GSKTBBBKT52TISH/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":"2026-08-09T14:32:24Z","links":{"resolver":"https://pith.science/pith/ARQD372AVD7GSKTBBBKT52TISH","bundle":"https://pith.science/pith/ARQD372AVD7GSKTBBBKT52TISH/bundle.json","state":"https://pith.science/pith/ARQD372AVD7GSKTBBBKT52TISH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ARQD372AVD7GSKTBBBKT52TISH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ARQD372AVD7GSKTBBBKT52TISH","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":"0c0084193fbb3fe4f96830e7f34f08d14b0e9a2dbf300f6dd4d54c129cf072f9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T17:55:20Z","title_canon_sha256":"d4f877ad5780c9a065d0f4436848ec5a82c56e7e6f004a9a9d7fea2de26d628d"},"schema_version":"1.0","source":{"id":"2505.16993","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16993","created_at":"2026-07-05T11:07:44Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16993v1","created_at":"2026-07-05T11:07:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16993","created_at":"2026-07-05T11:07:44Z"},{"alias_kind":"pith_short_12","alias_value":"ARQD372AVD7G","created_at":"2026-07-05T11:07:44Z"},{"alias_kind":"pith_short_16","alias_value":"ARQD372AVD7GSKTB","created_at":"2026-07-05T11:07:44Z"},{"alias_kind":"pith_short_8","alias_value":"ARQD372A","created_at":"2026-07-05T11:07:44Z"}],"graph_snapshots":[{"event_id":"sha256:a37b342f83a73a86c749688c0ffe9d9aaf7dbaaa1c6ce5857f50172f295b12da","target":"graph","created_at":"2026-07-05T11:07:44Z","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/2505.16993/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Uniform downsampling remains the de facto standard for reducing spatial resolution in vision backbones. In this work, we propose an alternative design built around a content-aware spatial grouping layer, that dynamically assigns tokens to a reduced set based on image boundaries and their semantic content. Stacking our grouping layer across consecutive backbone stages results in hierarchical segmentation that arises natively in the feature extraction process, resulting in our coined Native Segmentation Vision Transformer. We show that a careful design of our architecture enables the emergence o","authors_text":"Aljo\\v{s}a O\\v{s}ep, Guillem Bras\\'o, Laura Leal-Taix\\'e","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T17:55:20Z","title":"Native Segmentation Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16993","kind":"arxiv","version":1},"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":"sha256:460843d13c1f602722d799d8c16d5347a3a9992f23e323ce7e822c321a3f69b3","target":"record","created_at":"2026-07-05T11:07:44Z","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":"0c0084193fbb3fe4f96830e7f34f08d14b0e9a2dbf300f6dd4d54c129cf072f9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T17:55:20Z","title_canon_sha256":"d4f877ad5780c9a065d0f4436848ec5a82c56e7e6f004a9a9d7fea2de26d628d"},"schema_version":"1.0","source":{"id":"2505.16993","kind":"arxiv","version":1}},"canonical_sha256":"04603dff40a8fe692a6108553eea6891db2677b02a9a5a11ca3b651fbf4ade02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04603dff40a8fe692a6108553eea6891db2677b02a9a5a11ca3b651fbf4ade02","first_computed_at":"2026-07-05T11:07:44.223825Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:44.223825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yj7gdtyyIJ0EerJkVJIWI2yH902KDJX39C5QLr4WdtoHk1N4BLRS+doiHSh58NG8DGDoHd2KthAkeXDRnvEdCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:44.224351Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16993","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:460843d13c1f602722d799d8c16d5347a3a9992f23e323ce7e822c321a3f69b3","sha256:a37b342f83a73a86c749688c0ffe9d9aaf7dbaaa1c6ce5857f50172f295b12da"],"state_sha256":"7c40edd982f6d5cbc1009d670228a07e0e7949b973d302ecdff9340ff5942fbc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k4OPxTnH/6L7XRKWcjmDDbrGykz83/mvOVk5b/LHpSIZxqRCn3u5cfMyMcDhKB36ctFXoNpczoGD2MhaDFJQCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:32:24.694579Z","bundle_sha256":"aac9f37e5e3b9ecc51ae329a2c13d6adc8ee609b70895706955851e0f53c729c"}}