{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:OQKMZIWXX547VZWCZMM55T5EYF","short_pith_number":"pith:OQKMZIWX","canonical_record":{"source":{"id":"1609.05566","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-18T23:16:14Z","cross_cats_sorted":[],"title_canon_sha256":"ceeab50187cbdd5ba57d03f154cb0f6dfad2f17b511bd9e586d84bd4447fd65a","abstract_canon_sha256":"5e48debc0285ce51f0e651245124c5fef37de28a599fb39e0bf456bb5cf1b4f0"},"schema_version":"1.0"},"canonical_sha256":"7414cca2d7bf79fae6c2cb19decfa4c146eb83a5e9d8e1b02927b05acde3e387","source":{"kind":"arxiv","id":"1609.05566","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.05566","created_at":"2026-05-18T01:04:26Z"},{"alias_kind":"arxiv_version","alias_value":"1609.05566v1","created_at":"2026-05-18T01:04:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.05566","created_at":"2026-05-18T01:04:26Z"},{"alias_kind":"pith_short_12","alias_value":"OQKMZIWXX547","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OQKMZIWXX547VZWC","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OQKMZIWX","created_at":"2026-05-18T12:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:OQKMZIWXX547VZWCZMM55T5EYF","target":"record","payload":{"canonical_record":{"source":{"id":"1609.05566","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-18T23:16:14Z","cross_cats_sorted":[],"title_canon_sha256":"ceeab50187cbdd5ba57d03f154cb0f6dfad2f17b511bd9e586d84bd4447fd65a","abstract_canon_sha256":"5e48debc0285ce51f0e651245124c5fef37de28a599fb39e0bf456bb5cf1b4f0"},"schema_version":"1.0"},"canonical_sha256":"7414cca2d7bf79fae6c2cb19decfa4c146eb83a5e9d8e1b02927b05acde3e387","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:26.013051Z","signature_b64":"WjdvCbN4q9b2WtsizqBaO88Lfhi7MFZls740XIejgmYpPZ0gTv5fEn6i+SSbHaueqf206OxJeHSPMtUAomW/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7414cca2d7bf79fae6c2cb19decfa4c146eb83a5e9d8e1b02927b05acde3e387","last_reissued_at":"2026-05-18T01:04:26.012222Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:26.012222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.05566","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":"2026-05-18T01:04:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wnjgzOzoc6gOFZYZzwv9hC2BC2PKF1XqtMQ4YvIEOyswqPMai6mooreOPMnRogwco9y6JK4IiWQdOb4J2UsmDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T17:59:14.085508Z"},"content_sha256":"de2cb83af436bac5fb1f192b83ed02da279864dcfb0b99aebd8efd93783db597","schema_version":"1.0","event_id":"sha256:de2cb83af436bac5fb1f192b83ed02da279864dcfb0b99aebd8efd93783db597"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:OQKMZIWXX547VZWCZMM55T5EYF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Label-Free Supervision of Neural Networks with Physics and Domain Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Russell Stewart, Stefano Ermon","submitted_at":"2016-09-18T23:16:14Z","abstract_excerpt":"In many machine learning applications, labeled data is scarce and obtaining more labels is expensive. We introduce a new approach to supervising neural networks by specifying constraints that should hold over the output space, rather than direct examples of input-output pairs. These constraints are derived from prior domain knowledge, e.g., from known laws of physics. We demonstrate the effectiveness of this approach on real world and simulated computer vision tasks. We are able to train a convolutional neural network to detect and track objects without any labeled examples. Our approach can s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.05566","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":"2026-05-18T01:04:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TgoX73n6gdP8QhirfC2GGM8xlf7njbI8KgOqMdkedxDgRgSNklI+2JlXJ7LgMK8b6gZZPD1AeIx1QRHieC15Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T17:59:14.085859Z"},"content_sha256":"e172cb9870bb364e348ee35677c02e8112f26ec68c73aff5e983deee1df2b786","schema_version":"1.0","event_id":"sha256:e172cb9870bb364e348ee35677c02e8112f26ec68c73aff5e983deee1df2b786"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OQKMZIWXX547VZWCZMM55T5EYF/bundle.json","state_url":"https://pith.science/pith/OQKMZIWXX547VZWCZMM55T5EYF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OQKMZIWXX547VZWCZMM55T5EYF/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":"2026-06-02T17:59:14Z","links":{"resolver":"https://pith.science/pith/OQKMZIWXX547VZWCZMM55T5EYF","bundle":"https://pith.science/pith/OQKMZIWXX547VZWCZMM55T5EYF/bundle.json","state":"https://pith.science/pith/OQKMZIWXX547VZWCZMM55T5EYF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OQKMZIWXX547VZWCZMM55T5EYF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:OQKMZIWXX547VZWCZMM55T5EYF","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":"5e48debc0285ce51f0e651245124c5fef37de28a599fb39e0bf456bb5cf1b4f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-18T23:16:14Z","title_canon_sha256":"ceeab50187cbdd5ba57d03f154cb0f6dfad2f17b511bd9e586d84bd4447fd65a"},"schema_version":"1.0","source":{"id":"1609.05566","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.05566","created_at":"2026-05-18T01:04:26Z"},{"alias_kind":"arxiv_version","alias_value":"1609.05566v1","created_at":"2026-05-18T01:04:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.05566","created_at":"2026-05-18T01:04:26Z"},{"alias_kind":"pith_short_12","alias_value":"OQKMZIWXX547","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OQKMZIWXX547VZWC","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OQKMZIWX","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:e172cb9870bb364e348ee35677c02e8112f26ec68c73aff5e983deee1df2b786","target":"graph","created_at":"2026-05-18T01:04:26Z","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 many machine learning applications, labeled data is scarce and obtaining more labels is expensive. We introduce a new approach to supervising neural networks by specifying constraints that should hold over the output space, rather than direct examples of input-output pairs. These constraints are derived from prior domain knowledge, e.g., from known laws of physics. We demonstrate the effectiveness of this approach on real world and simulated computer vision tasks. We are able to train a convolutional neural network to detect and track objects without any labeled examples. Our approach can s","authors_text":"Russell Stewart, Stefano Ermon","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-18T23:16:14Z","title":"Label-Free Supervision of Neural Networks with Physics and Domain Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.05566","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:de2cb83af436bac5fb1f192b83ed02da279864dcfb0b99aebd8efd93783db597","target":"record","created_at":"2026-05-18T01:04:26Z","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":"5e48debc0285ce51f0e651245124c5fef37de28a599fb39e0bf456bb5cf1b4f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-18T23:16:14Z","title_canon_sha256":"ceeab50187cbdd5ba57d03f154cb0f6dfad2f17b511bd9e586d84bd4447fd65a"},"schema_version":"1.0","source":{"id":"1609.05566","kind":"arxiv","version":1}},"canonical_sha256":"7414cca2d7bf79fae6c2cb19decfa4c146eb83a5e9d8e1b02927b05acde3e387","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7414cca2d7bf79fae6c2cb19decfa4c146eb83a5e9d8e1b02927b05acde3e387","first_computed_at":"2026-05-18T01:04:26.012222Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:04:26.012222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WjdvCbN4q9b2WtsizqBaO88Lfhi7MFZls740XIejgmYpPZ0gTv5fEn6i+SSbHaueqf206OxJeHSPMtUAomW/CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:04:26.013051Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.05566","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de2cb83af436bac5fb1f192b83ed02da279864dcfb0b99aebd8efd93783db597","sha256:e172cb9870bb364e348ee35677c02e8112f26ec68c73aff5e983deee1df2b786"],"state_sha256":"0a8298b2d248954048f02cd7c8ef68c651ed8bc6c631c80e00baa2738142019f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4m9hNg5bSPAxD8yiyPhZFj8Sz7KDh1uD198SOsJd8ljLLdYskJeXM4ju3EfE2m23kAjo9HMMtzUWHagagK34BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T17:59:14.087967Z","bundle_sha256":"4be54c17ab8b6d77752fcabd57a5edda859930945412afbd5f22d85f67a56117"}}