{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LAX5ST4AYDTYVPA3GFXIPUJ3CJ","short_pith_number":"pith:LAX5ST4A","schema_version":"1.0","canonical_sha256":"582fd94f80c0e78abc1b316e87d13b127a7f598ce2cfe162ed1adee834840200","source":{"kind":"arxiv","id":"1904.11487","version":1},"attestation_state":"computed","paper":{"title":"Blurring the Line Between Structure and Learning to Optimize and Adapt Receptive Fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dequan Wang, Evan Shelhamer, Trevor Darrell","submitted_at":"2019-04-25T17:57:10Z","abstract_excerpt":"The visual world is vast and varied, but its variations divide into structured and unstructured factors. We compose free-form filters and structured Gaussian filters, optimized end-to-end, to factorize deep representations and learn both local features and their degree of locality. Our semi-structured composition is strictly more expressive than free-form filtering, and changes in its structured parameters would require changes in free-form architecture. In effect this optimizes over receptive field size and shape, tuning locality to the data and task. Dynamic inference, in which the Gaussian "},"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":"1904.11487","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-25T17:57:10Z","cross_cats_sorted":[],"title_canon_sha256":"8583f3cc447752f4e7bbd379357147d00e6ce4baf7565ca4a8ff73cf4e0a2dfa","abstract_canon_sha256":"9f48e67797a3eab1692ef89a29f246b4de3585e0733267d12ae39704cbf0a848"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:44.752774Z","signature_b64":"7KySmjrGKYF03oakDkbV/pSZLOyO9AVd7pivGAaSCicII4Xdajwi7CTCyFHvl+jphOOqiJksC/hDRqUsZDnDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"582fd94f80c0e78abc1b316e87d13b127a7f598ce2cfe162ed1adee834840200","last_reissued_at":"2026-05-17T23:47:44.752181Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:44.752181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Blurring the Line Between Structure and Learning to Optimize and Adapt Receptive Fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dequan Wang, Evan Shelhamer, Trevor Darrell","submitted_at":"2019-04-25T17:57:10Z","abstract_excerpt":"The visual world is vast and varied, but its variations divide into structured and unstructured factors. We compose free-form filters and structured Gaussian filters, optimized end-to-end, to factorize deep representations and learn both local features and their degree of locality. Our semi-structured composition is strictly more expressive than free-form filtering, and changes in its structured parameters would require changes in free-form architecture. In effect this optimizes over receptive field size and shape, tuning locality to the data and task. Dynamic inference, in which the Gaussian "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11487","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":""},"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":"1904.11487","created_at":"2026-05-17T23:47:44.752259+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.11487v1","created_at":"2026-05-17T23:47:44.752259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11487","created_at":"2026-05-17T23:47:44.752259+00:00"},{"alias_kind":"pith_short_12","alias_value":"LAX5ST4AYDTY","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"LAX5ST4AYDTYVPA3","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"LAX5ST4A","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.03182","citing_title":"Dynamic Scale Inference by Entropy Minimization","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LAX5ST4AYDTYVPA3GFXIPUJ3CJ","json":"https://pith.science/pith/LAX5ST4AYDTYVPA3GFXIPUJ3CJ.json","graph_json":"https://pith.science/api/pith-number/LAX5ST4AYDTYVPA3GFXIPUJ3CJ/graph.json","events_json":"https://pith.science/api/pith-number/LAX5ST4AYDTYVPA3GFXIPUJ3CJ/events.json","paper":"https://pith.science/paper/LAX5ST4A"},"agent_actions":{"view_html":"https://pith.science/pith/LAX5ST4AYDTYVPA3GFXIPUJ3CJ","download_json":"https://pith.science/pith/LAX5ST4AYDTYVPA3GFXIPUJ3CJ.json","view_paper":"https://pith.science/paper/LAX5ST4A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.11487&json=true","fetch_graph":"https://pith.science/api/pith-number/LAX5ST4AYDTYVPA3GFXIPUJ3CJ/graph.json","fetch_events":"https://pith.science/api/pith-number/LAX5ST4AYDTYVPA3GFXIPUJ3CJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LAX5ST4AYDTYVPA3GFXIPUJ3CJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LAX5ST4AYDTYVPA3GFXIPUJ3CJ/action/storage_attestation","attest_author":"https://pith.science/pith/LAX5ST4AYDTYVPA3GFXIPUJ3CJ/action/author_attestation","sign_citation":"https://pith.science/pith/LAX5ST4AYDTYVPA3GFXIPUJ3CJ/action/citation_signature","submit_replication":"https://pith.science/pith/LAX5ST4AYDTYVPA3GFXIPUJ3CJ/action/replication_record"}},"created_at":"2026-05-17T23:47:44.752259+00:00","updated_at":"2026-05-17T23:47:44.752259+00:00"}