{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:Y5X4CILB4TWFXO2EQ3AUSIN6JX","short_pith_number":"pith:Y5X4CILB","canonical_record":{"source":{"id":"1805.08630","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.FL","submitted_at":"2018-05-22T14:33:24Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"8b38f02f5ac0e863ce83faca391cbdad2d49b49b2b42c10980ad2fd220243aaf","abstract_canon_sha256":"48c08f40849499cb5b79f54f8d86beca4d0948ec3f3c8909107fade0e610436f"},"schema_version":"1.0"},"canonical_sha256":"c76fc12161e4ec5bbb4486c14921be4ddcda32f6e88db3d72b38eb65ee2200db","source":{"kind":"arxiv","id":"1805.08630","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08630","created_at":"2026-05-17T23:50:59Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08630v1","created_at":"2026-05-17T23:50:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08630","created_at":"2026-05-17T23:50:59Z"},{"alias_kind":"pith_short_12","alias_value":"Y5X4CILB4TWF","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Y5X4CILB4TWFXO2E","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Y5X4CILB","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:Y5X4CILB4TWFXO2EQ3AUSIN6JX","target":"record","payload":{"canonical_record":{"source":{"id":"1805.08630","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.FL","submitted_at":"2018-05-22T14:33:24Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"8b38f02f5ac0e863ce83faca391cbdad2d49b49b2b42c10980ad2fd220243aaf","abstract_canon_sha256":"48c08f40849499cb5b79f54f8d86beca4d0948ec3f3c8909107fade0e610436f"},"schema_version":"1.0"},"canonical_sha256":"c76fc12161e4ec5bbb4486c14921be4ddcda32f6e88db3d72b38eb65ee2200db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:59.676074Z","signature_b64":"YkqwJ454wQK1Y5A6tTjj3SiGXc1SI5F1LS9O5kKPJtOB6DU6BTQBhxYCqRK/noq57wdKbcKsK2w1i2zizKw9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c76fc12161e4ec5bbb4486c14921be4ddcda32f6e88db3d72b38eb65ee2200db","last_reissued_at":"2026-05-17T23:50:59.675537Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:59.675537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.08630","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":"2026-05-17T23:50:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gDpI/9NP3ieUBtuVbAlMHKEmWT7ov7NlVOi221yB6SWcLbrHvlKuqQO9PfNJ7ztA1M3g70z4f9NbRbzk9qdNBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T09:23:57.313176Z"},"content_sha256":"dde46aa8a0cf2d78d513374e61841ca0cb44fe4f975b2aae6ea5503f6668fc80","schema_version":"1.0","event_id":"sha256:dde46aa8a0cf2d78d513374e61841ca0cb44fe4f975b2aae6ea5503f6668fc80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:Y5X4CILB4TWFXO2EQ3AUSIN6JX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Estimating probabilistic context-free grammars for proteins using contact map constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.FL","authors_text":"Fran\\c{c}ois Coste, Juliette Talibart, Witold Dyrka","submitted_at":"2018-05-22T14:33:24Z","abstract_excerpt":"Learning language of protein sequences, which captures non-local interactions between amino acids close in the spatial structure, is a long-standing bioinformatics challenge, which requires at least context-free grammars. However, complex character of protein interactions impedes unsupervised learning of context-free grammars. Using structural information to constrain the syntactic trees proved effective in learning probabilistic natural and RNA languages. In this work, we establish a framework for learning probabilistic context-free grammars for protein sequences from syntactic trees partiall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08630","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":"2026-05-17T23:50:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3a5AocYxUQgpQ9JW9D9CcHHW3dhsiLgzwMp+pdSocDF/5AvAOqBVjqCrOB9XK/vENpVGObTW9V5Gj89JXGX8Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T09:23:57.313548Z"},"content_sha256":"c164d5179f0a6f65202c7f5146d774697f211f8cf8b32433f4cb4303d068ae59","schema_version":"1.0","event_id":"sha256:c164d5179f0a6f65202c7f5146d774697f211f8cf8b32433f4cb4303d068ae59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y5X4CILB4TWFXO2EQ3AUSIN6JX/bundle.json","state_url":"https://pith.science/pith/Y5X4CILB4TWFXO2EQ3AUSIN6JX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y5X4CILB4TWFXO2EQ3AUSIN6JX/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":"2026-06-20T09:23:57Z","links":{"resolver":"https://pith.science/pith/Y5X4CILB4TWFXO2EQ3AUSIN6JX","bundle":"https://pith.science/pith/Y5X4CILB4TWFXO2EQ3AUSIN6JX/bundle.json","state":"https://pith.science/pith/Y5X4CILB4TWFXO2EQ3AUSIN6JX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y5X4CILB4TWFXO2EQ3AUSIN6JX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Y5X4CILB4TWFXO2EQ3AUSIN6JX","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":"48c08f40849499cb5b79f54f8d86beca4d0948ec3f3c8909107fade0e610436f","cross_cats_sorted":["q-bio.BM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.FL","submitted_at":"2018-05-22T14:33:24Z","title_canon_sha256":"8b38f02f5ac0e863ce83faca391cbdad2d49b49b2b42c10980ad2fd220243aaf"},"schema_version":"1.0","source":{"id":"1805.08630","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08630","created_at":"2026-05-17T23:50:59Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08630v1","created_at":"2026-05-17T23:50:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08630","created_at":"2026-05-17T23:50:59Z"},{"alias_kind":"pith_short_12","alias_value":"Y5X4CILB4TWF","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Y5X4CILB4TWFXO2E","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Y5X4CILB","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:c164d5179f0a6f65202c7f5146d774697f211f8cf8b32433f4cb4303d068ae59","target":"graph","created_at":"2026-05-17T23:50:59Z","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":"Learning language of protein sequences, which captures non-local interactions between amino acids close in the spatial structure, is a long-standing bioinformatics challenge, which requires at least context-free grammars. However, complex character of protein interactions impedes unsupervised learning of context-free grammars. Using structural information to constrain the syntactic trees proved effective in learning probabilistic natural and RNA languages. In this work, we establish a framework for learning probabilistic context-free grammars for protein sequences from syntactic trees partiall","authors_text":"Fran\\c{c}ois Coste, Juliette Talibart, Witold Dyrka","cross_cats":["q-bio.BM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.FL","submitted_at":"2018-05-22T14:33:24Z","title":"Estimating probabilistic context-free grammars for proteins using contact map constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08630","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:dde46aa8a0cf2d78d513374e61841ca0cb44fe4f975b2aae6ea5503f6668fc80","target":"record","created_at":"2026-05-17T23:50:59Z","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":"48c08f40849499cb5b79f54f8d86beca4d0948ec3f3c8909107fade0e610436f","cross_cats_sorted":["q-bio.BM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.FL","submitted_at":"2018-05-22T14:33:24Z","title_canon_sha256":"8b38f02f5ac0e863ce83faca391cbdad2d49b49b2b42c10980ad2fd220243aaf"},"schema_version":"1.0","source":{"id":"1805.08630","kind":"arxiv","version":1}},"canonical_sha256":"c76fc12161e4ec5bbb4486c14921be4ddcda32f6e88db3d72b38eb65ee2200db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c76fc12161e4ec5bbb4486c14921be4ddcda32f6e88db3d72b38eb65ee2200db","first_computed_at":"2026-05-17T23:50:59.675537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:59.675537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YkqwJ454wQK1Y5A6tTjj3SiGXc1SI5F1LS9O5kKPJtOB6DU6BTQBhxYCqRK/noq57wdKbcKsK2w1i2zizKw9Cw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:59.676074Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.08630","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dde46aa8a0cf2d78d513374e61841ca0cb44fe4f975b2aae6ea5503f6668fc80","sha256:c164d5179f0a6f65202c7f5146d774697f211f8cf8b32433f4cb4303d068ae59"],"state_sha256":"7f6c8405ac8ad1b291a463b674fd01fb537b8a518f135cf78cea7804b1c48d33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vEa5IXlKZXyEWsazYxhUL8+gdPNBcSbOK08Y3/EF7Wlt/okAOCB4gJTfQdSbchUpgQZXfA3g0VI4d1sb/nMWDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T09:23:57.315541Z","bundle_sha256":"b73969288b78eb005e10a23ecae2391797d33352c0da24183ea5d76323145a4d"}}