{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:LGOCP66KABPMR2ZUWZSXL2XQFM","short_pith_number":"pith:LGOCP66K","canonical_record":{"source":{"id":"2006.06649","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-11T17:42:49Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"cd78d09021976b74fe6cacc483b62413df9737e9db9d54eeb52402457477034d","abstract_canon_sha256":"4a2fb1f101653e55b195683d674c5a7d7b124f4a392a760ad2f25295973e866e"},"schema_version":"1.0"},"canonical_sha256":"599c27fbca005ec8eb34b66575eaf02b0109d090f9dd088069549914fcf7403e","source":{"kind":"arxiv","id":"2006.06649","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.06649","created_at":"2026-07-05T01:22:48Z"},{"alias_kind":"arxiv_version","alias_value":"2006.06649v2","created_at":"2026-07-05T01:22:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06649","created_at":"2026-07-05T01:22:48Z"},{"alias_kind":"pith_short_12","alias_value":"LGOCP66KABPM","created_at":"2026-07-05T01:22:48Z"},{"alias_kind":"pith_short_16","alias_value":"LGOCP66KABPMR2ZU","created_at":"2026-07-05T01:22:48Z"},{"alias_kind":"pith_short_8","alias_value":"LGOCP66K","created_at":"2026-07-05T01:22:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:LGOCP66KABPMR2ZUWZSXL2XQFM","target":"record","payload":{"canonical_record":{"source":{"id":"2006.06649","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-11T17:42:49Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"cd78d09021976b74fe6cacc483b62413df9737e9db9d54eeb52402457477034d","abstract_canon_sha256":"4a2fb1f101653e55b195683d674c5a7d7b124f4a392a760ad2f25295973e866e"},"schema_version":"1.0"},"canonical_sha256":"599c27fbca005ec8eb34b66575eaf02b0109d090f9dd088069549914fcf7403e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:22:48.151493Z","signature_b64":"FI4Dpxd2JAOSTdZO1hu2sOuGAEpmB7jH8IJeUSmvtS5L+eQPr3YtD816SIyb7hrFAjrAVARIhHrr3rLlUO/9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"599c27fbca005ec8eb34b66575eaf02b0109d090f9dd088069549914fcf7403e","last_reissued_at":"2026-07-05T01:22:48.151058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:22:48.151058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.06649","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:22:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4aq5Sd/0XixYrADP72iTuKeoXfWFrbND5tz4KD0Lsm3XYIZsvc58KB6eYxTqIIAXqR40iw+Kf/6+zmfc0pKNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:42:16.165416Z"},"content_sha256":"85e5b0dd5c1cc65b248de0d8b0493a49f7ee7577e67b89f4808197620644d56b","schema_version":"1.0","event_id":"sha256:85e5b0dd5c1cc65b248de0d8b0493a49f7ee7577e67b89f4808197620644d56b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:LGOCP66KABPMR2ZUWZSXL2XQFM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Qing Li, Siyuan Huang, Song-Chun Zhu, Ying Nian Wu, Yining Hong, Yixin Chen","submitted_at":"2020-06-11T17:42:49Z","abstract_excerpt":"The goal of neural-symbolic computation is to integrate the connectionist and symbolist paradigms. Prior methods learn the neural-symbolic models using reinforcement learning (RL) approaches, which ignore the error propagation in the symbolic reasoning module and thus converge slowly with sparse rewards. In this paper, we address these issues and close the loop of neural-symbolic learning by (1) introducing the \\textbf{grammar} model as a \\textit{symbolic prior} to bridge neural perception and symbolic reasoning, and (2) proposing a novel \\textbf{back-search} algorithm which mimics the top-dow"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06649","kind":"arxiv","version":2},"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/2006.06649/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":"2026-07-05T01:22:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oogt/2Db2psll4kfruBNz4roOxeHeY2W44IPgszlqNGsYud2CICPStIdw26b5wl/xQ7fgOBcoPuqOkw4urARDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:42:16.165852Z"},"content_sha256":"04f2abb3ab712af74f1443bffee490411d86ad5db00a731fa52d13c36bc6c11c","schema_version":"1.0","event_id":"sha256:04f2abb3ab712af74f1443bffee490411d86ad5db00a731fa52d13c36bc6c11c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LGOCP66KABPMR2ZUWZSXL2XQFM/bundle.json","state_url":"https://pith.science/pith/LGOCP66KABPMR2ZUWZSXL2XQFM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LGOCP66KABPMR2ZUWZSXL2XQFM/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":"2026-07-07T15:42:16Z","links":{"resolver":"https://pith.science/pith/LGOCP66KABPMR2ZUWZSXL2XQFM","bundle":"https://pith.science/pith/LGOCP66KABPMR2ZUWZSXL2XQFM/bundle.json","state":"https://pith.science/pith/LGOCP66KABPMR2ZUWZSXL2XQFM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LGOCP66KABPMR2ZUWZSXL2XQFM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LGOCP66KABPMR2ZUWZSXL2XQFM","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":"4a2fb1f101653e55b195683d674c5a7d7b124f4a392a760ad2f25295973e866e","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-11T17:42:49Z","title_canon_sha256":"cd78d09021976b74fe6cacc483b62413df9737e9db9d54eeb52402457477034d"},"schema_version":"1.0","source":{"id":"2006.06649","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.06649","created_at":"2026-07-05T01:22:48Z"},{"alias_kind":"arxiv_version","alias_value":"2006.06649v2","created_at":"2026-07-05T01:22:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06649","created_at":"2026-07-05T01:22:48Z"},{"alias_kind":"pith_short_12","alias_value":"LGOCP66KABPM","created_at":"2026-07-05T01:22:48Z"},{"alias_kind":"pith_short_16","alias_value":"LGOCP66KABPMR2ZU","created_at":"2026-07-05T01:22:48Z"},{"alias_kind":"pith_short_8","alias_value":"LGOCP66K","created_at":"2026-07-05T01:22:48Z"}],"graph_snapshots":[{"event_id":"sha256:04f2abb3ab712af74f1443bffee490411d86ad5db00a731fa52d13c36bc6c11c","target":"graph","created_at":"2026-07-05T01:22:48Z","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/2006.06649/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of neural-symbolic computation is to integrate the connectionist and symbolist paradigms. Prior methods learn the neural-symbolic models using reinforcement learning (RL) approaches, which ignore the error propagation in the symbolic reasoning module and thus converge slowly with sparse rewards. In this paper, we address these issues and close the loop of neural-symbolic learning by (1) introducing the \\textbf{grammar} model as a \\textit{symbolic prior} to bridge neural perception and symbolic reasoning, and (2) proposing a novel \\textbf{back-search} algorithm which mimics the top-dow","authors_text":"Qing Li, Siyuan Huang, Song-Chun Zhu, Ying Nian Wu, Yining Hong, Yixin Chen","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-11T17:42:49Z","title":"Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06649","kind":"arxiv","version":2},"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":"sha256:85e5b0dd5c1cc65b248de0d8b0493a49f7ee7577e67b89f4808197620644d56b","target":"record","created_at":"2026-07-05T01:22:48Z","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":"4a2fb1f101653e55b195683d674c5a7d7b124f4a392a760ad2f25295973e866e","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-11T17:42:49Z","title_canon_sha256":"cd78d09021976b74fe6cacc483b62413df9737e9db9d54eeb52402457477034d"},"schema_version":"1.0","source":{"id":"2006.06649","kind":"arxiv","version":2}},"canonical_sha256":"599c27fbca005ec8eb34b66575eaf02b0109d090f9dd088069549914fcf7403e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"599c27fbca005ec8eb34b66575eaf02b0109d090f9dd088069549914fcf7403e","first_computed_at":"2026-07-05T01:22:48.151058Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:22:48.151058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FI4Dpxd2JAOSTdZO1hu2sOuGAEpmB7jH8IJeUSmvtS5L+eQPr3YtD816SIyb7hrFAjrAVARIhHrr3rLlUO/9CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:22:48.151493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.06649","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85e5b0dd5c1cc65b248de0d8b0493a49f7ee7577e67b89f4808197620644d56b","sha256:04f2abb3ab712af74f1443bffee490411d86ad5db00a731fa52d13c36bc6c11c"],"state_sha256":"ecfbce06f9fbd895012942b38963dc1a0d812ce1587eec8fedcb214a40e895ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jZDCntciMuvQaxSH38og3rfTxkOmEdKI0yEuwa/ZQ8fDLqdUaXQzr4vxfgHuYerk5fxIfACjH5XyZAVDyP1tBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:42:16.167872Z","bundle_sha256":"9edb8ac5ee67983ce8801c850bac2d197dd20aa92e7331f148eaa60f128a311f"}}