{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GS5TNC2JSW6EM7AHLDRQM73VOA","short_pith_number":"pith:GS5TNC2J","canonical_record":{"source":{"id":"2510.01632","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-10-02T03:25:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d8c7dc2e6466c5d5a1766d12c02087bb1383e51439526e84dc85e2bb9b09bf27","abstract_canon_sha256":"647115e6bea630afe1251e7166f0d9d32b2c5153d4061715fccc41d80ae2f24d"},"schema_version":"1.0"},"canonical_sha256":"34bb368b4995bc467c0758e3067f75703c8d637bc7f1ca2223e36679e8d45e0c","source":{"kind":"arxiv","id":"2510.01632","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.01632","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"arxiv_version","alias_value":"2510.01632v3","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.01632","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"pith_short_12","alias_value":"GS5TNC2JSW6E","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"pith_short_16","alias_value":"GS5TNC2JSW6EM7AH","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"pith_short_8","alias_value":"GS5TNC2J","created_at":"2026-05-20T00:01:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GS5TNC2JSW6EM7AHLDRQM73VOA","target":"record","payload":{"canonical_record":{"source":{"id":"2510.01632","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-10-02T03:25:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d8c7dc2e6466c5d5a1766d12c02087bb1383e51439526e84dc85e2bb9b09bf27","abstract_canon_sha256":"647115e6bea630afe1251e7166f0d9d32b2c5153d4061715fccc41d80ae2f24d"},"schema_version":"1.0"},"canonical_sha256":"34bb368b4995bc467c0758e3067f75703c8d637bc7f1ca2223e36679e8d45e0c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:35.722853Z","signature_b64":"Rcs7o5fn/GvEcYuBEyGmXnBTICSCqRI8R8gBHW0y6g4Wd+r+4a/i6r30v+Cyu6bNsDjec5mU64aNQTsAqXj5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34bb368b4995bc467c0758e3067f75703c8d637bc7f1ca2223e36679e8d45e0c","last_reissued_at":"2026-05-20T00:01:35.721974Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:35.721974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.01632","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:01:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g50ujjDH8aYbESt9SDO1tuYjq/Je4ptab3ar1a0c4WjeUHqTIriapTYuqH3hSWwd0iuExmr46JWk6GK/mnbfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T11:03:30.593537Z"},"content_sha256":"3c4b3becc4030a3982f17e8eeaaca2417e425f512d72ee093a142b34874c7e00","schema_version":"1.0","event_id":"sha256:3c4b3becc4030a3982f17e8eeaaca2417e425f512d72ee093a142b34874c7e00"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GS5TNC2JSW6EM7AHLDRQM73VOA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BioBlobs: Unsupervised Discovery of Functional Substructures for Protein Function Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"BioBlobs compresses proteins into a small set of cohesive residue groups and predicts function from those groups alone.","cross_cats":["cs.AI"],"primary_cat":"q-bio.BM","authors_text":"Carlos Oliver, Kaiwen Shi, Xin Wang","submitted_at":"2025-10-02T03:25:02Z","abstract_excerpt":"Protein function is driven by cohesive substructures, such as catalytic triads, binding pockets, and structural motifs, that occupy only a small fraction of a protein's residues. Yet existing pipelines built on protein encoders do not model proteins at the substructure level, leaving the central biological question unanswered: which substructure of a protein is responsible for its function? We introduce BioBlobs, an encoder-agnostic, end-to-end differentiable framework that compresses a protein into a small set of cohesive substructures (blobs) and predicts function from these blobs alone, so "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Trained only on protein-level labels, BioBlobs recovers experimentally annotated catalytic sites in the M-CSA database, demonstrating unsupervised functional substructure discovery.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The central premise that functional information can be isolated into a small number of spatially cohesive residue groups (blobs) whose collective representation is sufficient to predict the protein-level label, with the compression step itself being learned without explicit substructure supervision.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"BioBlobs discovers functional substructures unsupervised by learning to compress proteins into task-adaptive blobs from which function is predicted, recovering known catalytic sites from protein-level labels alone.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"BioBlobs compresses proteins into a small set of cohesive residue groups and predicts function from those groups alone.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"48f38c7ebe44f44fd69a79959342141a78ad4576bf8d582fb38f8419d2595135"},"source":{"id":"2510.01632","kind":"arxiv","version":3},"verdict":{"id":"953608e1-876b-4b24-bc8f-c4cb1acc0fb7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-18T11:10:08.595291Z","strongest_claim":"Trained only on protein-level labels, BioBlobs recovers experimentally annotated catalytic sites in the M-CSA database, demonstrating unsupervised functional substructure discovery.","one_line_summary":"BioBlobs discovers functional substructures unsupervised by learning to compress proteins into task-adaptive blobs from which function is predicted, recovering known catalytic sites from protein-level labels alone.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The central premise that functional information can be isolated into a small number of spatially cohesive residue groups (blobs) whose collective representation is sufficient to predict the protein-level label, with the compression step itself being learned without explicit substructure supervision.","pith_extraction_headline":"BioBlobs compresses proteins into a small set of cohesive residue groups and predicts function from those groups alone."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.01632/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":2,"snapshot_sha256":"3f60ddf2912ada7bbcb66dc3b84e9b80c0084065ec863873983a8e09ca084868"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"953608e1-876b-4b24-bc8f-c4cb1acc0fb7"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:01:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GVmmB/pcD+DATKki5EoJNPgEV4sGdy6mcYx1I3YL400Flqs4eGkdYQ1WTuDcJ19eLwbtxIQSZUiHUzm0cGEtBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T11:03:30.593997Z"},"content_sha256":"3357964c9c61b8daaeda48abc98872b1d9f7697012a084a80e7e2e02e9b27b9b","schema_version":"1.0","event_id":"sha256:3357964c9c61b8daaeda48abc98872b1d9f7697012a084a80e7e2e02e9b27b9b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GS5TNC2JSW6EM7AHLDRQM73VOA/bundle.json","state_url":"https://pith.science/pith/GS5TNC2JSW6EM7AHLDRQM73VOA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GS5TNC2JSW6EM7AHLDRQM73VOA/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":"2026-07-17T11:03:30Z","links":{"resolver":"https://pith.science/pith/GS5TNC2JSW6EM7AHLDRQM73VOA","bundle":"https://pith.science/pith/GS5TNC2JSW6EM7AHLDRQM73VOA/bundle.json","state":"https://pith.science/pith/GS5TNC2JSW6EM7AHLDRQM73VOA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GS5TNC2JSW6EM7AHLDRQM73VOA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GS5TNC2JSW6EM7AHLDRQM73VOA","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":"647115e6bea630afe1251e7166f0d9d32b2c5153d4061715fccc41d80ae2f24d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-10-02T03:25:02Z","title_canon_sha256":"d8c7dc2e6466c5d5a1766d12c02087bb1383e51439526e84dc85e2bb9b09bf27"},"schema_version":"1.0","source":{"id":"2510.01632","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.01632","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"arxiv_version","alias_value":"2510.01632v3","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.01632","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"pith_short_12","alias_value":"GS5TNC2JSW6E","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"pith_short_16","alias_value":"GS5TNC2JSW6EM7AH","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"pith_short_8","alias_value":"GS5TNC2J","created_at":"2026-05-20T00:01:35Z"}],"graph_snapshots":[{"event_id":"sha256:3357964c9c61b8daaeda48abc98872b1d9f7697012a084a80e7e2e02e9b27b9b","target":"graph","created_at":"2026-05-20T00:01:35Z","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":"Trained only on protein-level labels, BioBlobs recovers experimentally annotated catalytic sites in the M-CSA database, demonstrating unsupervised functional substructure discovery."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The central premise that functional information can be isolated into a small number of spatially cohesive residue groups (blobs) whose collective representation is sufficient to predict the protein-level label, with the compression step itself being learned without explicit substructure supervision."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"BioBlobs discovers functional substructures unsupervised by learning to compress proteins into task-adaptive blobs from which function is predicted, recovering known catalytic sites from protein-level labels alone."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"BioBlobs compresses proteins into a small set of cohesive residue groups and predicts function from those groups alone."}],"snapshot_sha256":"48f38c7ebe44f44fd69a79959342141a78ad4576bf8d582fb38f8419d2595135"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3f60ddf2912ada7bbcb66dc3b84e9b80c0084065ec863873983a8e09ca084868"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2510.01632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Protein function is driven by cohesive substructures, such as catalytic triads, binding pockets, and structural motifs, that occupy only a small fraction of a protein's residues. Yet existing pipelines built on protein encoders do not model proteins at the substructure level, leaving the central biological question unanswered: which substructure of a protein is responsible for its function? We introduce BioBlobs, an encoder-agnostic, end-to-end differentiable framework that compresses a protein into a small set of cohesive substructures (blobs) and predicts function from these blobs alone, so ","authors_text":"Carlos Oliver, Kaiwen Shi, Xin Wang","cross_cats":["cs.AI"],"headline":"BioBlobs compresses proteins into a small set of cohesive residue groups and predicts function from those groups alone.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-10-02T03:25:02Z","title":"BioBlobs: Unsupervised Discovery of Functional Substructures for Protein Function Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.01632","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-18T11:10:08.595291Z","id":"953608e1-876b-4b24-bc8f-c4cb1acc0fb7","model_set":{"reader":"grok-4.3"},"one_line_summary":"BioBlobs discovers functional substructures unsupervised by learning to compress proteins into task-adaptive blobs from which function is predicted, recovering known catalytic sites from protein-level labels alone.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"BioBlobs compresses proteins into a small set of cohesive residue groups and predicts function from those groups alone.","strongest_claim":"Trained only on protein-level labels, BioBlobs recovers experimentally annotated catalytic sites in the M-CSA database, demonstrating unsupervised functional substructure discovery.","weakest_assumption":"The central premise that functional information can be isolated into a small number of spatially cohesive residue groups (blobs) whose collective representation is sufficient to predict the protein-level label, with the compression step itself being learned without explicit substructure supervision."}},"verdict_id":"953608e1-876b-4b24-bc8f-c4cb1acc0fb7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3c4b3becc4030a3982f17e8eeaaca2417e425f512d72ee093a142b34874c7e00","target":"record","created_at":"2026-05-20T00:01:35Z","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":"647115e6bea630afe1251e7166f0d9d32b2c5153d4061715fccc41d80ae2f24d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-10-02T03:25:02Z","title_canon_sha256":"d8c7dc2e6466c5d5a1766d12c02087bb1383e51439526e84dc85e2bb9b09bf27"},"schema_version":"1.0","source":{"id":"2510.01632","kind":"arxiv","version":3}},"canonical_sha256":"34bb368b4995bc467c0758e3067f75703c8d637bc7f1ca2223e36679e8d45e0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34bb368b4995bc467c0758e3067f75703c8d637bc7f1ca2223e36679e8d45e0c","first_computed_at":"2026-05-20T00:01:35.721974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:35.721974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rcs7o5fn/GvEcYuBEyGmXnBTICSCqRI8R8gBHW0y6g4Wd+r+4a/i6r30v+Cyu6bNsDjec5mU64aNQTsAqXj5DA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:35.722853Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.01632","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c4b3becc4030a3982f17e8eeaaca2417e425f512d72ee093a142b34874c7e00","sha256:3357964c9c61b8daaeda48abc98872b1d9f7697012a084a80e7e2e02e9b27b9b"],"state_sha256":"cb4ad63cb94725948c66c493de6a471671ddc88f4abd00dabb436f9ad2468fca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lrxlKjkL4asvliEaTxu5fObmQaolVZqg9po7XCRoNibGtqOm+fJT/6/epdcRaSBWsbkDZXyPUTSYi30P6ugvCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T11:03:30.596707Z","bundle_sha256":"f66c5fa4c7d2979b91e2b0088d4c5a01b84d09494982cc6e03feb3ecf1b6ba12"}}