{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OL7NOBB4SQOJVB43CTSP3ZM7NP","short_pith_number":"pith:OL7NOBB4","canonical_record":{"source":{"id":"1806.03961","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-06T11:09:35Z","cross_cats_sorted":[],"title_canon_sha256":"362e23a9d585db3cc689158bf078dbbccd30b0b9acdc476d21e99a2c23a213d9","abstract_canon_sha256":"3772f16f2b7e14308613b9c59fd87b0998fcb08e7caaa6a5056e110aa7477a2f"},"schema_version":"1.0"},"canonical_sha256":"72fed7043c941c9a879b14e4fde59f6bdc19bfc84f05d86aedae9255d1f2681a","source":{"kind":"arxiv","id":"1806.03961","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.03961","created_at":"2026-05-18T00:13:41Z"},{"alias_kind":"arxiv_version","alias_value":"1806.03961v1","created_at":"2026-05-18T00:13:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03961","created_at":"2026-05-18T00:13:41Z"},{"alias_kind":"pith_short_12","alias_value":"OL7NOBB4SQOJ","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OL7NOBB4SQOJVB43","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OL7NOBB4","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OL7NOBB4SQOJVB43CTSP3ZM7NP","target":"record","payload":{"canonical_record":{"source":{"id":"1806.03961","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-06T11:09:35Z","cross_cats_sorted":[],"title_canon_sha256":"362e23a9d585db3cc689158bf078dbbccd30b0b9acdc476d21e99a2c23a213d9","abstract_canon_sha256":"3772f16f2b7e14308613b9c59fd87b0998fcb08e7caaa6a5056e110aa7477a2f"},"schema_version":"1.0"},"canonical_sha256":"72fed7043c941c9a879b14e4fde59f6bdc19bfc84f05d86aedae9255d1f2681a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:41.404414Z","signature_b64":"tepwh1dbBgeolNLTPun5hnmb8PbkdhSIdejUeBLtgZU6AAz+OaQV0kjhBA1BE69+5KWx/bGf/WqyfdhORVOPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72fed7043c941c9a879b14e4fde59f6bdc19bfc84f05d86aedae9255d1f2681a","last_reissued_at":"2026-05-18T00:13:41.403667Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:41.403667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.03961","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":"2026-05-18T00:13:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ridv06tE98jwfXPxNDvT0oemDXzaOhg3c2CHBswaJAkkk4DGmfgeYitdJMkXPrGV/UQogJ5uRmrwTQb16sFACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T20:01:12.157019Z"},"content_sha256":"0101a6cf4468650ae85b08d67dfb8532240b94b8d31be3464949c9e59df86c10","schema_version":"1.0","event_id":"sha256:0101a6cf4468650ae85b08d67dfb8532240b94b8d31be3464949c9e59df86c10"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OL7NOBB4SQOJVB43CTSP3ZM7NP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attention Incorporate Network: A network can adapt various data size","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Sun, Liangbo He","submitted_at":"2018-06-06T11:09:35Z","abstract_excerpt":"In traditional neural networks for image processing, the inputs of the neural networks should be the same size such as 224*224*3. But how can we train the neural net model with different input size? A common way to do is image deformation which accompany a problem of information loss (e.g. image crop or wrap). Sequence model(RNN, LSTM, etc.) can accept different size of input like text and audio. But one disadvantage for sequence model is that the previous information will become more fragmentary during the transfer in time step, it will make the network hard to train especially for long seque"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03961","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:13:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qOUfgIuIwkhMtjgSOtjxJhKIKHO3OLlqfjFekVo6PZ3H4bxK23rlngbvNsCdkrCaupZUJVinmzrB21Og+o3EAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T20:01:12.157399Z"},"content_sha256":"38bc1b38fc9d23a803e8070d5375673472de8ad87a89efc482bd0642ca5788d1","schema_version":"1.0","event_id":"sha256:38bc1b38fc9d23a803e8070d5375673472de8ad87a89efc482bd0642ca5788d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OL7NOBB4SQOJVB43CTSP3ZM7NP/bundle.json","state_url":"https://pith.science/pith/OL7NOBB4SQOJVB43CTSP3ZM7NP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OL7NOBB4SQOJVB43CTSP3ZM7NP/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":"2026-05-26T20:01:12Z","links":{"resolver":"https://pith.science/pith/OL7NOBB4SQOJVB43CTSP3ZM7NP","bundle":"https://pith.science/pith/OL7NOBB4SQOJVB43CTSP3ZM7NP/bundle.json","state":"https://pith.science/pith/OL7NOBB4SQOJVB43CTSP3ZM7NP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OL7NOBB4SQOJVB43CTSP3ZM7NP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OL7NOBB4SQOJVB43CTSP3ZM7NP","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":"3772f16f2b7e14308613b9c59fd87b0998fcb08e7caaa6a5056e110aa7477a2f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-06T11:09:35Z","title_canon_sha256":"362e23a9d585db3cc689158bf078dbbccd30b0b9acdc476d21e99a2c23a213d9"},"schema_version":"1.0","source":{"id":"1806.03961","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.03961","created_at":"2026-05-18T00:13:41Z"},{"alias_kind":"arxiv_version","alias_value":"1806.03961v1","created_at":"2026-05-18T00:13:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03961","created_at":"2026-05-18T00:13:41Z"},{"alias_kind":"pith_short_12","alias_value":"OL7NOBB4SQOJ","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OL7NOBB4SQOJVB43","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OL7NOBB4","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:38bc1b38fc9d23a803e8070d5375673472de8ad87a89efc482bd0642ca5788d1","target":"graph","created_at":"2026-05-18T00:13:41Z","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"},"paper":{"abstract_excerpt":"In traditional neural networks for image processing, the inputs of the neural networks should be the same size such as 224*224*3. But how can we train the neural net model with different input size? A common way to do is image deformation which accompany a problem of information loss (e.g. image crop or wrap). Sequence model(RNN, LSTM, etc.) can accept different size of input like text and audio. But one disadvantage for sequence model is that the previous information will become more fragmentary during the transfer in time step, it will make the network hard to train especially for long seque","authors_text":"Hao Sun, Liangbo He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-06T11:09:35Z","title":"Attention Incorporate Network: A network can adapt various data size"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03961","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":"sha256:0101a6cf4468650ae85b08d67dfb8532240b94b8d31be3464949c9e59df86c10","target":"record","created_at":"2026-05-18T00:13:41Z","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":"3772f16f2b7e14308613b9c59fd87b0998fcb08e7caaa6a5056e110aa7477a2f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-06T11:09:35Z","title_canon_sha256":"362e23a9d585db3cc689158bf078dbbccd30b0b9acdc476d21e99a2c23a213d9"},"schema_version":"1.0","source":{"id":"1806.03961","kind":"arxiv","version":1}},"canonical_sha256":"72fed7043c941c9a879b14e4fde59f6bdc19bfc84f05d86aedae9255d1f2681a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72fed7043c941c9a879b14e4fde59f6bdc19bfc84f05d86aedae9255d1f2681a","first_computed_at":"2026-05-18T00:13:41.403667Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:41.403667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tepwh1dbBgeolNLTPun5hnmb8PbkdhSIdejUeBLtgZU6AAz+OaQV0kjhBA1BE69+5KWx/bGf/WqyfdhORVOPDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:41.404414Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.03961","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0101a6cf4468650ae85b08d67dfb8532240b94b8d31be3464949c9e59df86c10","sha256:38bc1b38fc9d23a803e8070d5375673472de8ad87a89efc482bd0642ca5788d1"],"state_sha256":"c27eace543c2e15a6d190ba3452c00114398ea20617aedee07cbf1f41bb05c0c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4F/1AY2960j3zy2NUThLYkdOL8P7bn0K/vKh6Djj90EeYPGIMgeGsM+kOmz9xrYzZua983NAL+5qLcYEDWvYBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T20:01:12.159825Z","bundle_sha256":"667b8f9673f636acefb205c4cd91a68119e3fdd28752446be7406967c2a27839"}}