{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UJQ3ZZFKT4BPH5L37QYKHEEMU5","short_pith_number":"pith:UJQ3ZZFK","schema_version":"1.0","canonical_sha256":"a261bce4aa9f02f3f57bfc30a3908ca7777e8d36328fde3268f64e6908e40f2c","source":{"kind":"arxiv","id":"2606.00999","version":1},"attestation_state":"computed","paper":{"title":"SWARD: Stochastic Window-Attention-Based Relational Distillation for Cross-Architectural Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Makineni, Qing Tian","submitted_at":"2026-05-31T04:29:31Z","abstract_excerpt":"Large-scale vision foundation models have driven substantial gains on dense prediction tasks such as semantic segmentation, but their size makes deployment impractical in resource-constrained settings, motivating knowledge distillation as a means of transferring their capabilities to lightweight student networks. However, modern foundation teachers are predominantly transformer-based that encode global context, whereas efficient students are typically convolutional networks with locally biased receptive fields. Existing distillation methods largely assume architectural homogeneity and rely on "},"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":"2606.00999","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T04:29:31Z","cross_cats_sorted":[],"title_canon_sha256":"af44b2773b0ee56ab79b460d307957afd59b3de266f6ba9f64247d2ff695c416","abstract_canon_sha256":"251d8555983dea6429d2122ea628258c5338e39795db7a6b03535d085b665943"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:17.821015Z","signature_b64":"ncPNZ6KVETup+M1qXycL5anbRFyuFx4Kwwih4mlf4Xt2iHw0GT6zi2cv9cy1sq8WkrWXKje+eqH1pGGJ/1kKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a261bce4aa9f02f3f57bfc30a3908ca7777e8d36328fde3268f64e6908e40f2c","last_reissued_at":"2026-06-02T01:04:17.820291Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:17.820291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SWARD: Stochastic Window-Attention-Based Relational Distillation for Cross-Architectural Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Makineni, Qing Tian","submitted_at":"2026-05-31T04:29:31Z","abstract_excerpt":"Large-scale vision foundation models have driven substantial gains on dense prediction tasks such as semantic segmentation, but their size makes deployment impractical in resource-constrained settings, motivating knowledge distillation as a means of transferring their capabilities to lightweight student networks. However, modern foundation teachers are predominantly transformer-based that encode global context, whereas efficient students are typically convolutional networks with locally biased receptive fields. Existing distillation methods largely assume architectural homogeneity and rely on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00999","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/2606.00999/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":"2606.00999","created_at":"2026-06-02T01:04:17.820396+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00999v1","created_at":"2026-06-02T01:04:17.820396+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00999","created_at":"2026-06-02T01:04:17.820396+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJQ3ZZFKT4BP","created_at":"2026-06-02T01:04:17.820396+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJQ3ZZFKT4BPH5L3","created_at":"2026-06-02T01:04:17.820396+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJQ3ZZFK","created_at":"2026-06-02T01:04:17.820396+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/UJQ3ZZFKT4BPH5L37QYKHEEMU5","json":"https://pith.science/pith/UJQ3ZZFKT4BPH5L37QYKHEEMU5.json","graph_json":"https://pith.science/api/pith-number/UJQ3ZZFKT4BPH5L37QYKHEEMU5/graph.json","events_json":"https://pith.science/api/pith-number/UJQ3ZZFKT4BPH5L37QYKHEEMU5/events.json","paper":"https://pith.science/paper/UJQ3ZZFK"},"agent_actions":{"view_html":"https://pith.science/pith/UJQ3ZZFKT4BPH5L37QYKHEEMU5","download_json":"https://pith.science/pith/UJQ3ZZFKT4BPH5L37QYKHEEMU5.json","view_paper":"https://pith.science/paper/UJQ3ZZFK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00999&json=true","fetch_graph":"https://pith.science/api/pith-number/UJQ3ZZFKT4BPH5L37QYKHEEMU5/graph.json","fetch_events":"https://pith.science/api/pith-number/UJQ3ZZFKT4BPH5L37QYKHEEMU5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJQ3ZZFKT4BPH5L37QYKHEEMU5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJQ3ZZFKT4BPH5L37QYKHEEMU5/action/storage_attestation","attest_author":"https://pith.science/pith/UJQ3ZZFKT4BPH5L37QYKHEEMU5/action/author_attestation","sign_citation":"https://pith.science/pith/UJQ3ZZFKT4BPH5L37QYKHEEMU5/action/citation_signature","submit_replication":"https://pith.science/pith/UJQ3ZZFKT4BPH5L37QYKHEEMU5/action/replication_record"}},"created_at":"2026-06-02T01:04:17.820396+00:00","updated_at":"2026-06-02T01:04:17.820396+00:00"}