{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HD4RJVILRL5OGFF2UWZIVIPVMV","short_pith_number":"pith:HD4RJVIL","canonical_record":{"source":{"id":"1807.08179","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-21T17:09:16Z","cross_cats_sorted":[],"title_canon_sha256":"2c1561ee36d158403e37169c58d6720a71dabf8583d5a0ad6d7db2c9624dea86","abstract_canon_sha256":"dcbf82ad56fa29ed3453595da7eb9f46f542d48cdeeeae532cc78138ae4b47a9"},"schema_version":"1.0"},"canonical_sha256":"38f914d50b8afae314baa5b28aa1f56544e807ea0b610883ca7f61cff8ff77e8","source":{"kind":"arxiv","id":"1807.08179","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.08179","created_at":"2026-05-18T00:10:08Z"},{"alias_kind":"arxiv_version","alias_value":"1807.08179v1","created_at":"2026-05-18T00:10:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.08179","created_at":"2026-05-18T00:10:08Z"},{"alias_kind":"pith_short_12","alias_value":"HD4RJVILRL5O","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HD4RJVILRL5OGFF2","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HD4RJVIL","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HD4RJVILRL5OGFF2UWZIVIPVMV","target":"record","payload":{"canonical_record":{"source":{"id":"1807.08179","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-21T17:09:16Z","cross_cats_sorted":[],"title_canon_sha256":"2c1561ee36d158403e37169c58d6720a71dabf8583d5a0ad6d7db2c9624dea86","abstract_canon_sha256":"dcbf82ad56fa29ed3453595da7eb9f46f542d48cdeeeae532cc78138ae4b47a9"},"schema_version":"1.0"},"canonical_sha256":"38f914d50b8afae314baa5b28aa1f56544e807ea0b610883ca7f61cff8ff77e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:08.985858Z","signature_b64":"pEOOHvd1LLRiOl//h8NyX5ezU4uhcdB+nHjBOI+yuBdwGaSRsyYxSIs0A9Ksv3oR/lZ5UOcD5VRmfCial32TCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38f914d50b8afae314baa5b28aa1f56544e807ea0b610883ca7f61cff8ff77e8","last_reissued_at":"2026-05-18T00:10:08.985228Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:08.985228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.08179","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":"2026-05-18T00:10:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IoUuslxP+6OD5kZ2TSKsvyUVVhtpU7cFgB8d4AfcZX/NeTYb/AdeIUo0ftFiOOJg6+jvAlSaL8Y0Es7EzSrCAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T23:16:12.145109Z"},"content_sha256":"420628fcbc4a287a8d38e126ab7141b2444598a4202e51da2f8506566ac183a1","schema_version":"1.0","event_id":"sha256:420628fcbc4a287a8d38e126ab7141b2444598a4202e51da2f8506566ac183a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HD4RJVILRL5OGFF2UWZIVIPVMV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inductive Visual Localisation: Factorised Training for Superior Generalisation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Ankush Gupta","submitted_at":"2018-07-21T17:09:16Z","abstract_excerpt":"End-to-end trained Recurrent Neural Networks (RNNs) have been successfully applied to numerous problems that require processing sequences, such as image captioning, machine translation, and text recognition. However, RNNs often struggle to generalise to sequences longer than the ones encountered during training. In this work, we propose to optimise neural networks explicitly for induction. The idea is to first decompose the problem in a sequence of inductive steps and then to explicitly train the RNN to reproduce such steps. Generalisation is achieved as the RNN is not allowed to learn an arbi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.08179","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":"2026-05-18T00:10:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2uJFvR/wh6Qz5OIshCsAQ3dPQdFnVHvesCDuSnUE1gzKeQwGNpW0Gl0/tfuK9fr40RxaNJOdThf8NOIT9urIDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T23:16:12.145775Z"},"content_sha256":"76014e22b7144a7c869b129dba7631d2de65b2ba699a3b239e01c531c87ce13b","schema_version":"1.0","event_id":"sha256:76014e22b7144a7c869b129dba7631d2de65b2ba699a3b239e01c531c87ce13b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HD4RJVILRL5OGFF2UWZIVIPVMV/bundle.json","state_url":"https://pith.science/pith/HD4RJVILRL5OGFF2UWZIVIPVMV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HD4RJVILRL5OGFF2UWZIVIPVMV/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":"2026-05-31T23:16:12Z","links":{"resolver":"https://pith.science/pith/HD4RJVILRL5OGFF2UWZIVIPVMV","bundle":"https://pith.science/pith/HD4RJVILRL5OGFF2UWZIVIPVMV/bundle.json","state":"https://pith.science/pith/HD4RJVILRL5OGFF2UWZIVIPVMV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HD4RJVILRL5OGFF2UWZIVIPVMV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HD4RJVILRL5OGFF2UWZIVIPVMV","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":"dcbf82ad56fa29ed3453595da7eb9f46f542d48cdeeeae532cc78138ae4b47a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-21T17:09:16Z","title_canon_sha256":"2c1561ee36d158403e37169c58d6720a71dabf8583d5a0ad6d7db2c9624dea86"},"schema_version":"1.0","source":{"id":"1807.08179","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.08179","created_at":"2026-05-18T00:10:08Z"},{"alias_kind":"arxiv_version","alias_value":"1807.08179v1","created_at":"2026-05-18T00:10:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.08179","created_at":"2026-05-18T00:10:08Z"},{"alias_kind":"pith_short_12","alias_value":"HD4RJVILRL5O","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HD4RJVILRL5OGFF2","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HD4RJVIL","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:76014e22b7144a7c869b129dba7631d2de65b2ba699a3b239e01c531c87ce13b","target":"graph","created_at":"2026-05-18T00:10:08Z","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":"End-to-end trained Recurrent Neural Networks (RNNs) have been successfully applied to numerous problems that require processing sequences, such as image captioning, machine translation, and text recognition. However, RNNs often struggle to generalise to sequences longer than the ones encountered during training. In this work, we propose to optimise neural networks explicitly for induction. The idea is to first decompose the problem in a sequence of inductive steps and then to explicitly train the RNN to reproduce such steps. Generalisation is achieved as the RNN is not allowed to learn an arbi","authors_text":"Andrea Vedaldi, Andrew Zisserman, Ankush Gupta","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-21T17:09:16Z","title":"Inductive Visual Localisation: Factorised Training for Superior Generalisation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.08179","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":"sha256:420628fcbc4a287a8d38e126ab7141b2444598a4202e51da2f8506566ac183a1","target":"record","created_at":"2026-05-18T00:10:08Z","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":"dcbf82ad56fa29ed3453595da7eb9f46f542d48cdeeeae532cc78138ae4b47a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-21T17:09:16Z","title_canon_sha256":"2c1561ee36d158403e37169c58d6720a71dabf8583d5a0ad6d7db2c9624dea86"},"schema_version":"1.0","source":{"id":"1807.08179","kind":"arxiv","version":1}},"canonical_sha256":"38f914d50b8afae314baa5b28aa1f56544e807ea0b610883ca7f61cff8ff77e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38f914d50b8afae314baa5b28aa1f56544e807ea0b610883ca7f61cff8ff77e8","first_computed_at":"2026-05-18T00:10:08.985228Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:08.985228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pEOOHvd1LLRiOl//h8NyX5ezU4uhcdB+nHjBOI+yuBdwGaSRsyYxSIs0A9Ksv3oR/lZ5UOcD5VRmfCial32TCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:08.985858Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.08179","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:420628fcbc4a287a8d38e126ab7141b2444598a4202e51da2f8506566ac183a1","sha256:76014e22b7144a7c869b129dba7631d2de65b2ba699a3b239e01c531c87ce13b"],"state_sha256":"ae042ef9d9a04ee11bb9ef6f48e5054eca5850ad67bbff02b0093e36886ebb6f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nfexVAtyoh4o+RSZWngNcXZGbfk2NPlJx/dLQ+jmxwvsI+zWgWbrBnPmblyvKa4das/ogkrfsICcGytYkS3ODA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T23:16:12.149704Z","bundle_sha256":"a7c0267f7d6f7686b3a88e1b1c27b827538e3be13c34d4e0f00d383ce5ef2684"}}