{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WJHSTL4QSHXEM27THQHWL5TZ45","short_pith_number":"pith:WJHSTL4Q","canonical_record":{"source":{"id":"2309.15812","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-27T17:36:19Z","cross_cats_sorted":[],"title_canon_sha256":"04f902e43eff2ddbb5a4f65bab4c623e5920a5b6754ce54927d1421dd0552df7","abstract_canon_sha256":"b7dd4788cf19fdcab88c5a97134fa90fa5b759ea07c9e551b4a0b169a1351579"},"schema_version":"1.0"},"canonical_sha256":"b24f29af9091ee466bf33c0f65f679e760531d94784432b70f426b8a71a0a84c","source":{"kind":"arxiv","id":"2309.15812","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15812","created_at":"2026-07-05T06:54:58Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15812v1","created_at":"2026-07-05T06:54:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15812","created_at":"2026-07-05T06:54:58Z"},{"alias_kind":"pith_short_12","alias_value":"WJHSTL4QSHXE","created_at":"2026-07-05T06:54:58Z"},{"alias_kind":"pith_short_16","alias_value":"WJHSTL4QSHXEM27T","created_at":"2026-07-05T06:54:58Z"},{"alias_kind":"pith_short_8","alias_value":"WJHSTL4Q","created_at":"2026-07-05T06:54:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WJHSTL4QSHXEM27THQHWL5TZ45","target":"record","payload":{"canonical_record":{"source":{"id":"2309.15812","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-27T17:36:19Z","cross_cats_sorted":[],"title_canon_sha256":"04f902e43eff2ddbb5a4f65bab4c623e5920a5b6754ce54927d1421dd0552df7","abstract_canon_sha256":"b7dd4788cf19fdcab88c5a97134fa90fa5b759ea07c9e551b4a0b169a1351579"},"schema_version":"1.0"},"canonical_sha256":"b24f29af9091ee466bf33c0f65f679e760531d94784432b70f426b8a71a0a84c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:58.067634Z","signature_b64":"z93Yan8/ZUX+Vxf1EBMhWkpzGxMdWec7HY0y9UuOXY0SKyMeWQrJfMYqEgmm0L+5V75KDpBgrx1ZthBJ8gSQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b24f29af9091ee466bf33c0f65f679e760531d94784432b70f426b8a71a0a84c","last_reissued_at":"2026-07-05T06:54:58.067141Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:58.067141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.15812","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":"2026-07-05T06:54:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qqlGoKfS3N4V5vHAn5HsYHLIsmAEj/ev6G3+pFR+o/bQWHBYh2rlGA8dGVN0dT4IWdB9yiI6+qu19IhsFAeAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:26:42.662247Z"},"content_sha256":"e304a04bc687b4638457de81ddcf75811a0cf38e17c59867f1b5658e44e141fe","schema_version":"1.0","event_id":"sha256:e304a04bc687b4638457de81ddcf75811a0cf38e17c59867f1b5658e44e141fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WJHSTL4QSHXEM27THQHWL5TZ45","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convolutional Networks with Oriented 1D Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandre Kirchmeyer, Jia Deng","submitted_at":"2023-09-27T17:36:19Z","abstract_excerpt":"In computer vision, 2D convolution is arguably the most important operation performed by a ConvNet. Unsurprisingly, it has been the focus of intense software and hardware optimization and enjoys highly efficient implementations. In this work, we ask an intriguing question: can we make a ConvNet work without 2D convolutions? Surprisingly, we find that the answer is yes -- we show that a ConvNet consisting entirely of 1D convolutions can do just as well as 2D on ImageNet classification. Specifically, we find that one key ingredient to a high-performing 1D ConvNet is oriented 1D kernels: 1D kerne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15812","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/2309.15812/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":"2026-07-05T06:54:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DneK9CYPZcnE1y+sQhbKJS0f96zeoDcGvwlcAM1OImkfJiNci/1F/RZq7QgAm0I0OzsJFnmBHcJSp+P+QtW9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:26:42.663149Z"},"content_sha256":"d3f878dfca1a9fd1f76ca8d3a8c949990b50e34d8d3ac246c432bea64ae93edd","schema_version":"1.0","event_id":"sha256:d3f878dfca1a9fd1f76ca8d3a8c949990b50e34d8d3ac246c432bea64ae93edd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WJHSTL4QSHXEM27THQHWL5TZ45/bundle.json","state_url":"https://pith.science/pith/WJHSTL4QSHXEM27THQHWL5TZ45/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WJHSTL4QSHXEM27THQHWL5TZ45/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":"2026-08-14T19:26:42Z","links":{"resolver":"https://pith.science/pith/WJHSTL4QSHXEM27THQHWL5TZ45","bundle":"https://pith.science/pith/WJHSTL4QSHXEM27THQHWL5TZ45/bundle.json","state":"https://pith.science/pith/WJHSTL4QSHXEM27THQHWL5TZ45/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WJHSTL4QSHXEM27THQHWL5TZ45/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WJHSTL4QSHXEM27THQHWL5TZ45","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":"b7dd4788cf19fdcab88c5a97134fa90fa5b759ea07c9e551b4a0b169a1351579","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-27T17:36:19Z","title_canon_sha256":"04f902e43eff2ddbb5a4f65bab4c623e5920a5b6754ce54927d1421dd0552df7"},"schema_version":"1.0","source":{"id":"2309.15812","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15812","created_at":"2026-07-05T06:54:58Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15812v1","created_at":"2026-07-05T06:54:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15812","created_at":"2026-07-05T06:54:58Z"},{"alias_kind":"pith_short_12","alias_value":"WJHSTL4QSHXE","created_at":"2026-07-05T06:54:58Z"},{"alias_kind":"pith_short_16","alias_value":"WJHSTL4QSHXEM27T","created_at":"2026-07-05T06:54:58Z"},{"alias_kind":"pith_short_8","alias_value":"WJHSTL4Q","created_at":"2026-07-05T06:54:58Z"}],"graph_snapshots":[{"event_id":"sha256:d3f878dfca1a9fd1f76ca8d3a8c949990b50e34d8d3ac246c432bea64ae93edd","target":"graph","created_at":"2026-07-05T06:54:58Z","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/2309.15812/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In computer vision, 2D convolution is arguably the most important operation performed by a ConvNet. Unsurprisingly, it has been the focus of intense software and hardware optimization and enjoys highly efficient implementations. In this work, we ask an intriguing question: can we make a ConvNet work without 2D convolutions? Surprisingly, we find that the answer is yes -- we show that a ConvNet consisting entirely of 1D convolutions can do just as well as 2D on ImageNet classification. Specifically, we find that one key ingredient to a high-performing 1D ConvNet is oriented 1D kernels: 1D kerne","authors_text":"Alexandre Kirchmeyer, Jia Deng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-27T17:36:19Z","title":"Convolutional Networks with Oriented 1D Kernels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15812","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:e304a04bc687b4638457de81ddcf75811a0cf38e17c59867f1b5658e44e141fe","target":"record","created_at":"2026-07-05T06:54:58Z","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":"b7dd4788cf19fdcab88c5a97134fa90fa5b759ea07c9e551b4a0b169a1351579","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-27T17:36:19Z","title_canon_sha256":"04f902e43eff2ddbb5a4f65bab4c623e5920a5b6754ce54927d1421dd0552df7"},"schema_version":"1.0","source":{"id":"2309.15812","kind":"arxiv","version":1}},"canonical_sha256":"b24f29af9091ee466bf33c0f65f679e760531d94784432b70f426b8a71a0a84c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b24f29af9091ee466bf33c0f65f679e760531d94784432b70f426b8a71a0a84c","first_computed_at":"2026-07-05T06:54:58.067141Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:54:58.067141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z93Yan8/ZUX+Vxf1EBMhWkpzGxMdWec7HY0y9UuOXY0SKyMeWQrJfMYqEgmm0L+5V75KDpBgrx1ZthBJ8gSQDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:54:58.067634Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.15812","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e304a04bc687b4638457de81ddcf75811a0cf38e17c59867f1b5658e44e141fe","sha256:d3f878dfca1a9fd1f76ca8d3a8c949990b50e34d8d3ac246c432bea64ae93edd"],"state_sha256":"2b75d05cee370db3f22822bec3fc88c1408efd2a8a5fb9085b442f8339d6ae2e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HIsPZNuOusL1ycWRph20xn9+Bnb10zWKrRdyO5SBAEe/3NNs110zesZ7ysedMNqEPJTHNin8i0uyS3heyTKvAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:26:42.679370Z","bundle_sha256":"348f3b1c8fa7c4637787dcca210ddec63ac09c44ca9d93ad946a446c7c721a21"}}