{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AOHFHKI3FS74D7VT6WCCRA256L","short_pith_number":"pith:AOHFHKI3","schema_version":"1.0","canonical_sha256":"038e53a91b2cbfc1feb3f58428835df2dd83e98e7dd8ff808aea2fae60976921","source":{"kind":"arxiv","id":"2308.16271","version":1},"attestation_state":"computed","paper":{"title":"Emergence of Segmentation with Minimalistic White-Box Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Druv Pai, Sam Buchanan, Shengbang Tong, Tianzhe Chu, Yaodong Yu, Yi Ma, Ziyang Wu","submitted_at":"2023-08-30T19:02:17Z","abstract_excerpt":"Transformer-like models for vision tasks have recently proven effective for a wide range of downstream applications such as segmentation and detection. Previous works have shown that segmentation properties emerge in vision transformers (ViTs) trained using self-supervised methods such as DINO, but not in those trained on supervised classification tasks. In this study, we probe whether segmentation emerges in transformer-based models solely as a result of intricate self-supervised learning mechanisms, or if the same emergence can be achieved under much broader conditions through proper design "},"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":"2308.16271","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-30T19:02:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1493ccfabfd7fc708c9e880826111cc86445fba7bb04d1e9691ecb0f9c8007af","abstract_canon_sha256":"950c012ee90913adc3055d6508e9239a5476d61e8747d5144d12e1d3a8413447"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:24.835916Z","signature_b64":"p8T/1fX1uk75O9pLHEbj7CkchR8sKNwtaoZffiOAfGC5+xEwuDSDLKwhy0tyyICvXzzO8Ditp4hKzgKlSOQmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"038e53a91b2cbfc1feb3f58428835df2dd83e98e7dd8ff808aea2fae60976921","last_reissued_at":"2026-07-05T06:46:24.835417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:24.835417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emergence of Segmentation with Minimalistic White-Box Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Druv Pai, Sam Buchanan, Shengbang Tong, Tianzhe Chu, Yaodong Yu, Yi Ma, Ziyang Wu","submitted_at":"2023-08-30T19:02:17Z","abstract_excerpt":"Transformer-like models for vision tasks have recently proven effective for a wide range of downstream applications such as segmentation and detection. Previous works have shown that segmentation properties emerge in vision transformers (ViTs) trained using self-supervised methods such as DINO, but not in those trained on supervised classification tasks. In this study, we probe whether segmentation emerges in transformer-based models solely as a result of intricate self-supervised learning mechanisms, or if the same emergence can be achieved under much broader conditions through proper design "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16271","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/2308.16271/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":"2308.16271","created_at":"2026-07-05T06:46:24.835477+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.16271v1","created_at":"2026-07-05T06:46:24.835477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16271","created_at":"2026-07-05T06:46:24.835477+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOHFHKI3FS74","created_at":"2026-07-05T06:46:24.835477+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOHFHKI3FS74D7VT","created_at":"2026-07-05T06:46:24.835477+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOHFHKI3","created_at":"2026-07-05T06:46:24.835477+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/AOHFHKI3FS74D7VT6WCCRA256L","json":"https://pith.science/pith/AOHFHKI3FS74D7VT6WCCRA256L.json","graph_json":"https://pith.science/api/pith-number/AOHFHKI3FS74D7VT6WCCRA256L/graph.json","events_json":"https://pith.science/api/pith-number/AOHFHKI3FS74D7VT6WCCRA256L/events.json","paper":"https://pith.science/paper/AOHFHKI3"},"agent_actions":{"view_html":"https://pith.science/pith/AOHFHKI3FS74D7VT6WCCRA256L","download_json":"https://pith.science/pith/AOHFHKI3FS74D7VT6WCCRA256L.json","view_paper":"https://pith.science/paper/AOHFHKI3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.16271&json=true","fetch_graph":"https://pith.science/api/pith-number/AOHFHKI3FS74D7VT6WCCRA256L/graph.json","fetch_events":"https://pith.science/api/pith-number/AOHFHKI3FS74D7VT6WCCRA256L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOHFHKI3FS74D7VT6WCCRA256L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOHFHKI3FS74D7VT6WCCRA256L/action/storage_attestation","attest_author":"https://pith.science/pith/AOHFHKI3FS74D7VT6WCCRA256L/action/author_attestation","sign_citation":"https://pith.science/pith/AOHFHKI3FS74D7VT6WCCRA256L/action/citation_signature","submit_replication":"https://pith.science/pith/AOHFHKI3FS74D7VT6WCCRA256L/action/replication_record"}},"created_at":"2026-07-05T06:46:24.835477+00:00","updated_at":"2026-07-05T06:46:24.835477+00:00"}