{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:5KJGTQYPVM5U2XFXLYPUNXDG3S","short_pith_number":"pith:5KJGTQYP","canonical_record":{"source":{"id":"1608.05949","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-08-21T14:58:01Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"f1afdeef344a572dc5a770ca6035c30f152bad33cbe72965695191ca5f29a18b","abstract_canon_sha256":"5c47c9c28b498e544f3005ee0a81bb19e48d83187406980a5336c5b923d0eb5c"},"schema_version":"1.0"},"canonical_sha256":"ea9269c30fab3b4d5cb75e1f46dc66dc9deaced882c7893b0df7e877c1c932b4","source":{"kind":"arxiv","id":"1608.05949","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.05949","created_at":"2026-05-18T01:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"1608.05949v2","created_at":"2026-05-18T01:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.05949","created_at":"2026-05-18T01:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"5KJGTQYPVM5U","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"5KJGTQYPVM5U2XFX","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"5KJGTQYP","created_at":"2026-05-18T12:30:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:5KJGTQYPVM5U2XFXLYPUNXDG3S","target":"record","payload":{"canonical_record":{"source":{"id":"1608.05949","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-08-21T14:58:01Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"f1afdeef344a572dc5a770ca6035c30f152bad33cbe72965695191ca5f29a18b","abstract_canon_sha256":"5c47c9c28b498e544f3005ee0a81bb19e48d83187406980a5336c5b923d0eb5c"},"schema_version":"1.0"},"canonical_sha256":"ea9269c30fab3b4d5cb75e1f46dc66dc9deaced882c7893b0df7e877c1c932b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:49.476251Z","signature_b64":"WsAyVbMLTE9qPuBQYE9relJWZy4plM6/j+cWwNh2mRNfpTejC2c3aiDM5cSVhM1wG3WWHAofYeHo6+CjpIlYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea9269c30fab3b4d5cb75e1f46dc66dc9deaced882c7893b0df7e877c1c932b4","last_reissued_at":"2026-05-18T01:04:49.475849Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:49.475849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1608.05949","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":"2026-05-18T01:04:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n10GU1Qum0IwVdTldPtHjkftNRhUxq70uJ+NyoFEk6/PrFHTL0LvLVpbranCxSHeqTHTAg0+wIHOPlUoAar/Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T05:10:47.702667Z"},"content_sha256":"47d858b10da15dddafda8cbe580cd3f505d27c5e234e8de46a49d75523dc8612","schema_version":"1.0","event_id":"sha256:47d858b10da15dddafda8cbe580cd3f505d27c5e234e8de46a49d75523dc8612"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:5KJGTQYPVM5U2XFXLYPUNXDG3S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributed Representations for Biological Sequence Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Akshay Soni, Dhananjay Kimothi, James M. Hogan, Pravesh Biyani","submitted_at":"2016-08-21T14:58:01Z","abstract_excerpt":"Biological sequence comparison is a key step in inferring the relatedness of various organisms and the functional similarity of their components. Thanks to the Next Generation Sequencing efforts, an abundance of sequence data is now available to be processed for a range of bioinformatics applications. Embedding a biological sequence over a nucleotide or amino acid alphabet in a lower dimensional vector space makes the data more amenable for use by current machine learning tools, provided the quality of embedding is high and it captures the most meaningful information of the original sequences."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.05949","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":""},"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":"2026-05-18T01:04:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+hAyzpVMPqIrDygY7zhtP+ZtTYmKUClxoJx/EB9uWcc/o7ExNRi5OlyJOP8YQhrJL8T5N9gbrLp0fFziNcUaBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T05:10:47.703017Z"},"content_sha256":"f7c8413641e2571c3bdecefe008761af0e7920956db8f2da1f01d179be74fefa","schema_version":"1.0","event_id":"sha256:f7c8413641e2571c3bdecefe008761af0e7920956db8f2da1f01d179be74fefa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5KJGTQYPVM5U2XFXLYPUNXDG3S/bundle.json","state_url":"https://pith.science/pith/5KJGTQYPVM5U2XFXLYPUNXDG3S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5KJGTQYPVM5U2XFXLYPUNXDG3S/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":"2026-06-02T05:10:47Z","links":{"resolver":"https://pith.science/pith/5KJGTQYPVM5U2XFXLYPUNXDG3S","bundle":"https://pith.science/pith/5KJGTQYPVM5U2XFXLYPUNXDG3S/bundle.json","state":"https://pith.science/pith/5KJGTQYPVM5U2XFXLYPUNXDG3S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5KJGTQYPVM5U2XFXLYPUNXDG3S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:5KJGTQYPVM5U2XFXLYPUNXDG3S","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":"5c47c9c28b498e544f3005ee0a81bb19e48d83187406980a5336c5b923d0eb5c","cross_cats_sorted":["q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-08-21T14:58:01Z","title_canon_sha256":"f1afdeef344a572dc5a770ca6035c30f152bad33cbe72965695191ca5f29a18b"},"schema_version":"1.0","source":{"id":"1608.05949","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.05949","created_at":"2026-05-18T01:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"1608.05949v2","created_at":"2026-05-18T01:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.05949","created_at":"2026-05-18T01:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"5KJGTQYPVM5U","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"5KJGTQYPVM5U2XFX","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"5KJGTQYP","created_at":"2026-05-18T12:30:01Z"}],"graph_snapshots":[{"event_id":"sha256:f7c8413641e2571c3bdecefe008761af0e7920956db8f2da1f01d179be74fefa","target":"graph","created_at":"2026-05-18T01:04:49Z","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":"Biological sequence comparison is a key step in inferring the relatedness of various organisms and the functional similarity of their components. Thanks to the Next Generation Sequencing efforts, an abundance of sequence data is now available to be processed for a range of bioinformatics applications. Embedding a biological sequence over a nucleotide or amino acid alphabet in a lower dimensional vector space makes the data more amenable for use by current machine learning tools, provided the quality of embedding is high and it captures the most meaningful information of the original sequences.","authors_text":"Akshay Soni, Dhananjay Kimothi, James M. Hogan, Pravesh Biyani","cross_cats":["q-bio.QM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-08-21T14:58:01Z","title":"Distributed Representations for Biological Sequence Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.05949","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":"sha256:47d858b10da15dddafda8cbe580cd3f505d27c5e234e8de46a49d75523dc8612","target":"record","created_at":"2026-05-18T01:04:49Z","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":"5c47c9c28b498e544f3005ee0a81bb19e48d83187406980a5336c5b923d0eb5c","cross_cats_sorted":["q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-08-21T14:58:01Z","title_canon_sha256":"f1afdeef344a572dc5a770ca6035c30f152bad33cbe72965695191ca5f29a18b"},"schema_version":"1.0","source":{"id":"1608.05949","kind":"arxiv","version":2}},"canonical_sha256":"ea9269c30fab3b4d5cb75e1f46dc66dc9deaced882c7893b0df7e877c1c932b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea9269c30fab3b4d5cb75e1f46dc66dc9deaced882c7893b0df7e877c1c932b4","first_computed_at":"2026-05-18T01:04:49.475849Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:04:49.475849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WsAyVbMLTE9qPuBQYE9relJWZy4plM6/j+cWwNh2mRNfpTejC2c3aiDM5cSVhM1wG3WWHAofYeHo6+CjpIlYCg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:04:49.476251Z","signed_message":"canonical_sha256_bytes"},"source_id":"1608.05949","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47d858b10da15dddafda8cbe580cd3f505d27c5e234e8de46a49d75523dc8612","sha256:f7c8413641e2571c3bdecefe008761af0e7920956db8f2da1f01d179be74fefa"],"state_sha256":"5b2c79afd794cb94ebb16ee2ae9a59c2973cd8d9fee34f464d16c8b702e185ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i16DvVA8TfA4Az0Z7LQqj4v/BYGd9EAYNDoI8ipEqr8/FvuHrRNn+RtIlQRv4PI3Wv4X5BuusJNcMzJMF4ctBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T05:10:47.705192Z","bundle_sha256":"336c68cdeb67a0e0db92ea13aff3811234a18a0a1e2dd951083fd2b895349875"}}