{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LN7L4IB5ZV6LZKQIQG62G2YSDT","short_pith_number":"pith:LN7L4IB5","canonical_record":{"source":{"id":"2605.13470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T12:57:17Z","cross_cats_sorted":[],"title_canon_sha256":"646ff408ca698a7375cd8290c1bc287c1cbdc5728dd427d7a238b649fc0ed620","abstract_canon_sha256":"c70ea4baf94dba8269c1915a0e5e48e8f1a5652d59506b4e9a7859b62170d1e2"},"schema_version":"1.0"},"canonical_sha256":"5b7ebe203dcd7cbcaa0881bda36b121ce22d2d72d626255d7d177f885502bd48","source":{"kind":"arxiv","id":"2605.13470","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13470","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13470v1","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13470","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"LN7L4IB5ZV6L","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"LN7L4IB5ZV6LZKQI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"LN7L4IB5","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LN7L4IB5ZV6LZKQIQG62G2YSDT","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T12:57:17Z","cross_cats_sorted":[],"title_canon_sha256":"646ff408ca698a7375cd8290c1bc287c1cbdc5728dd427d7a238b649fc0ed620","abstract_canon_sha256":"c70ea4baf94dba8269c1915a0e5e48e8f1a5652d59506b4e9a7859b62170d1e2"},"schema_version":"1.0"},"canonical_sha256":"5b7ebe203dcd7cbcaa0881bda36b121ce22d2d72d626255d7d177f885502bd48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:41.554238Z","signature_b64":"aE8OICTledJ90MPxEIB3ijCq6jrY10DTaFAgsm3+XIFI4UBgZJtu5qCnsUHtAzTvXKcZsgF3xra0IRE1R+JcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b7ebe203dcd7cbcaa0881bda36b121ce22d2d72d626255d7d177f885502bd48","last_reissued_at":"2026-05-18T02:44:41.553752Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:41.553752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13470","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":"2026-05-18T02:44:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3BMduWub2veNl2yADSd+d3h9VIwoIuqdNG49xpPue7HxgjtaWO/rxGr+kM3PzY7N++66vNTcJ2Z4ONKVYthNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T11:38:52.875552Z"},"content_sha256":"cd9103fa18083970f4d380bca1d959670214b32ef37b840fce7e7d59580770b8","schema_version":"1.0","event_id":"sha256:cd9103fa18083970f4d380bca1d959670214b32ef37b840fce7e7d59580770b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LN7L4IB5ZV6LZKQIQG62G2YSDT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Twincher: Bijective Representation Learning for Robust Inversion of Continuous Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Twincher learns bijective representations of outputs aligned with parameters to enable robust inversion of continuous systems under noise.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arkady Gonoskov","submitted_at":"2026-05-13T12:57:17Z","abstract_excerpt":"Recent advances in AI have been primarily driven by large-scale neural architectures that excel at function approximation, rather than by tailored inductive biases and inference or learning strategies that could be important for resource-efficient real-world perception and planning through the solution of inverse problems. In this work, we consider the possibility of enabling robust inversion of continuous forward processes $p \\mapsto y$ by learning representations of $y$ that are bijectively aligned with $p$ while remaining insensitive to perturbations in $y$ caused by noise or model mismatch"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Twincher enables robust and efficient iterative inverse inference by learning bijective representations of y that are aligned with p while remaining insensitive to perturbations in y caused by noise or model mismatch, exhibiting improved data efficiency and robustness compared to a baseline inverse-modeling approach.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That stacks of structured diffeomorphic transformations combined with adversarial training will produce representations that remain bijectively aligned and perturbation-insensitive when applied to real-world continuous systems beyond the synthetic examples shown.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Twincher learns bijective representations of observations aligned with continuous system parameters to enable robust iterative inversion, showing better data efficiency and noise tolerance than standard inverse modeling on synthetic systems.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Twincher learns bijective representations of outputs aligned with parameters to enable robust inversion of continuous systems under noise.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b1e01904efdc8ebf329b00dc08968036a44fa003a57a5bbe5055c69ea0812664"},"source":{"id":"2605.13470","kind":"arxiv","version":1},"verdict":{"id":"6e5b52cc-492f-4f97-a3ca-e6cdc0c9bc61","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:09:05.488911Z","strongest_claim":"Twincher enables robust and efficient iterative inverse inference by learning bijective representations of y that are aligned with p while remaining insensitive to perturbations in y caused by noise or model mismatch, exhibiting improved data efficiency and robustness compared to a baseline inverse-modeling approach.","one_line_summary":"Twincher learns bijective representations of observations aligned with continuous system parameters to enable robust iterative inversion, showing better data efficiency and noise tolerance than standard inverse modeling on synthetic systems.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That stacks of structured diffeomorphic transformations combined with adversarial training will produce representations that remain bijectively aligned and perturbation-insensitive when applied to real-world continuous systems beyond the synthetic examples shown.","pith_extraction_headline":"Twincher learns bijective representations of outputs aligned with parameters to enable robust inversion of continuous systems under noise."},"references":{"count":51,"sample":[{"doi":"","year":2020,"title":"Scaling laws for neural language models","work_id":"b48c8baf-a113-4a87-b196-8c68ba20002a","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1998,"title":"Gradient-based learning applied to document recognition.Proc","work_id":"ab3edb5c-5be8-4527-84cf-1099f7ff4fce","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Gomez, Lukasz Kaiser, and Illia Polosukhin","work_id":"d33dc346-1e7f-4df8-9c56-7ee1cda28d9e","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"On the inductive bias of neural tangent kernels, 2019","work_id":"96438aa8-cab6-4796-9fa4-7162495cc90d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Challenging common assumptions in the unsupervised learning of disentangled representations","work_id":"ba4ff1c1-53b6-437d-b3b2-79ec991316d3","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":51,"snapshot_sha256":"4bf67b2bdfe8922c5a9c29244614d825271b66418795e58c54c5348c92d57ee4","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":"6e5b52cc-492f-4f97-a3ca-e6cdc0c9bc61"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1BMWyiNAnwBW9swCvB+CQati0f/tZjTVeNKxRDw5M72fNnNk5kVxyZ5CBboMvao2Dg16ASqe2BOpPj0yG53SCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T11:38:52.876065Z"},"content_sha256":"b567eedbb2b8f541d46a40e9e719e6aea9611f652f99583c82cb4e61c287a0c0","schema_version":"1.0","event_id":"sha256:b567eedbb2b8f541d46a40e9e719e6aea9611f652f99583c82cb4e61c287a0c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LN7L4IB5ZV6LZKQIQG62G2YSDT/bundle.json","state_url":"https://pith.science/pith/LN7L4IB5ZV6LZKQIQG62G2YSDT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LN7L4IB5ZV6LZKQIQG62G2YSDT/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":"2026-05-28T11:38:52Z","links":{"resolver":"https://pith.science/pith/LN7L4IB5ZV6LZKQIQG62G2YSDT","bundle":"https://pith.science/pith/LN7L4IB5ZV6LZKQIQG62G2YSDT/bundle.json","state":"https://pith.science/pith/LN7L4IB5ZV6LZKQIQG62G2YSDT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LN7L4IB5ZV6LZKQIQG62G2YSDT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LN7L4IB5ZV6LZKQIQG62G2YSDT","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":"c70ea4baf94dba8269c1915a0e5e48e8f1a5652d59506b4e9a7859b62170d1e2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T12:57:17Z","title_canon_sha256":"646ff408ca698a7375cd8290c1bc287c1cbdc5728dd427d7a238b649fc0ed620"},"schema_version":"1.0","source":{"id":"2605.13470","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13470","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13470v1","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13470","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"LN7L4IB5ZV6L","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"LN7L4IB5ZV6LZKQI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"LN7L4IB5","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:b567eedbb2b8f541d46a40e9e719e6aea9611f652f99583c82cb4e61c287a0c0","target":"graph","created_at":"2026-05-18T02:44:41Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Twincher enables robust and efficient iterative inverse inference by learning bijective representations of y that are aligned with p while remaining insensitive to perturbations in y caused by noise or model mismatch, exhibiting improved data efficiency and robustness compared to a baseline inverse-modeling approach."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That stacks of structured diffeomorphic transformations combined with adversarial training will produce representations that remain bijectively aligned and perturbation-insensitive when applied to real-world continuous systems beyond the synthetic examples shown."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Twincher learns bijective representations of observations aligned with continuous system parameters to enable robust iterative inversion, showing better data efficiency and noise tolerance than standard inverse modeling on synthetic systems."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Twincher learns bijective representations of outputs aligned with parameters to enable robust inversion of continuous systems under noise."}],"snapshot_sha256":"b1e01904efdc8ebf329b00dc08968036a44fa003a57a5bbe5055c69ea0812664"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Recent advances in AI have been primarily driven by large-scale neural architectures that excel at function approximation, rather than by tailored inductive biases and inference or learning strategies that could be important for resource-efficient real-world perception and planning through the solution of inverse problems. In this work, we consider the possibility of enabling robust inversion of continuous forward processes $p \\mapsto y$ by learning representations of $y$ that are bijectively aligned with $p$ while remaining insensitive to perturbations in $y$ caused by noise or model mismatch","authors_text":"Arkady Gonoskov","cross_cats":[],"headline":"Twincher learns bijective representations of outputs aligned with parameters to enable robust inversion of continuous systems under noise.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T12:57:17Z","title":"Twincher: Bijective Representation Learning for Robust Inversion of Continuous Systems"},"references":{"count":51,"internal_anchors":0,"resolved_work":51,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Scaling laws for neural language models","work_id":"b48c8baf-a113-4a87-b196-8c68ba20002a","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Gradient-based learning applied to document recognition.Proc","work_id":"ab3edb5c-5be8-4527-84cf-1099f7ff4fce","year":1998},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Gomez, Lukasz Kaiser, and Illia Polosukhin","work_id":"d33dc346-1e7f-4df8-9c56-7ee1cda28d9e","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"On the inductive bias of neural tangent kernels, 2019","work_id":"96438aa8-cab6-4796-9fa4-7162495cc90d","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Challenging common assumptions in the unsupervised learning of disentangled representations","work_id":"ba4ff1c1-53b6-437d-b3b2-79ec991316d3","year":2018}],"snapshot_sha256":"4bf67b2bdfe8922c5a9c29244614d825271b66418795e58c54c5348c92d57ee4"},"source":{"id":"2605.13470","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:09:05.488911Z","id":"6e5b52cc-492f-4f97-a3ca-e6cdc0c9bc61","model_set":{"reader":"grok-4.3"},"one_line_summary":"Twincher learns bijective representations of observations aligned with continuous system parameters to enable robust iterative inversion, showing better data efficiency and noise tolerance than standard inverse modeling on synthetic systems.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Twincher learns bijective representations of outputs aligned with parameters to enable robust inversion of continuous systems under noise.","strongest_claim":"Twincher enables robust and efficient iterative inverse inference by learning bijective representations of y that are aligned with p while remaining insensitive to perturbations in y caused by noise or model mismatch, exhibiting improved data efficiency and robustness compared to a baseline inverse-modeling approach.","weakest_assumption":"That stacks of structured diffeomorphic transformations combined with adversarial training will produce representations that remain bijectively aligned and perturbation-insensitive when applied to real-world continuous systems beyond the synthetic examples shown."}},"verdict_id":"6e5b52cc-492f-4f97-a3ca-e6cdc0c9bc61"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cd9103fa18083970f4d380bca1d959670214b32ef37b840fce7e7d59580770b8","target":"record","created_at":"2026-05-18T02:44:41Z","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":"c70ea4baf94dba8269c1915a0e5e48e8f1a5652d59506b4e9a7859b62170d1e2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T12:57:17Z","title_canon_sha256":"646ff408ca698a7375cd8290c1bc287c1cbdc5728dd427d7a238b649fc0ed620"},"schema_version":"1.0","source":{"id":"2605.13470","kind":"arxiv","version":1}},"canonical_sha256":"5b7ebe203dcd7cbcaa0881bda36b121ce22d2d72d626255d7d177f885502bd48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b7ebe203dcd7cbcaa0881bda36b121ce22d2d72d626255d7d177f885502bd48","first_computed_at":"2026-05-18T02:44:41.553752Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:41.553752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aE8OICTledJ90MPxEIB3ijCq6jrY10DTaFAgsm3+XIFI4UBgZJtu5qCnsUHtAzTvXKcZsgF3xra0IRE1R+JcAg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:41.554238Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13470","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd9103fa18083970f4d380bca1d959670214b32ef37b840fce7e7d59580770b8","sha256:b567eedbb2b8f541d46a40e9e719e6aea9611f652f99583c82cb4e61c287a0c0"],"state_sha256":"b572d8eac1f837ec9e63959492075bafba1f4efcc3d84090c4ae52557580fbb0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1TH5XlaJARwnIrx2scyfYhp3kNR3LUxl6lxRB+YmX9Sb95ggc3H+eHF88PVTYcAmhwdzyGP3LVXPDtVWyjrTDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T11:38:52.878468Z","bundle_sha256":"c28278fef8d965b49fe213c8f8e6b57bd538733206031f3ee4452d27479b5f0a"}}