{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CSMMBWOC6ERODM7RHBDGPXFHX6","short_pith_number":"pith:CSMMBWOC","canonical_record":{"source":{"id":"2412.20014","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-28T04:23:47Z","cross_cats_sorted":["cs.AI","q-bio.BM"],"title_canon_sha256":"7646d42fd9cb492e876a73736f3cd33926423a9fef28b3be8bd45462272abd37","abstract_canon_sha256":"1de2e835201ca8a35da7f833a1315b94bc5b92da0fcb6fb971f9956ba36f3b67"},"schema_version":"1.0"},"canonical_sha256":"1498c0d9c2f122e1b3f1384667dca7bfa57fd908767790bb7d7fbd4def1c26aa","source":{"kind":"arxiv","id":"2412.20014","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20014","created_at":"2026-07-05T09:54:53Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20014v1","created_at":"2026-07-05T09:54:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20014","created_at":"2026-07-05T09:54:53Z"},{"alias_kind":"pith_short_12","alias_value":"CSMMBWOC6ERO","created_at":"2026-07-05T09:54:53Z"},{"alias_kind":"pith_short_16","alias_value":"CSMMBWOC6ERODM7R","created_at":"2026-07-05T09:54:53Z"},{"alias_kind":"pith_short_8","alias_value":"CSMMBWOC","created_at":"2026-07-05T09:54:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CSMMBWOC6ERODM7RHBDGPXFHX6","target":"record","payload":{"canonical_record":{"source":{"id":"2412.20014","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-28T04:23:47Z","cross_cats_sorted":["cs.AI","q-bio.BM"],"title_canon_sha256":"7646d42fd9cb492e876a73736f3cd33926423a9fef28b3be8bd45462272abd37","abstract_canon_sha256":"1de2e835201ca8a35da7f833a1315b94bc5b92da0fcb6fb971f9956ba36f3b67"},"schema_version":"1.0"},"canonical_sha256":"1498c0d9c2f122e1b3f1384667dca7bfa57fd908767790bb7d7fbd4def1c26aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:53.215465Z","signature_b64":"1m6wGoPlRq6aRyMJqpMNhtULUb8rxgRMOIt/nFaFR5GJuDVaQJeD1YJJZeYMYVY/gQOXPxrWEj3Bygjv9XE0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1498c0d9c2f122e1b3f1384667dca7bfa57fd908767790bb7d7fbd4def1c26aa","last_reissued_at":"2026-07-05T09:54:53.215010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:53.215010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.20014","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":"2026-07-05T09:54:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+K8OwYg9EWPKEisVOq6KPnEhmx5qccFUkLKTcPW5Dwlj4jnQgME7iwM0AYH+JSOHbF1scmdznHo7VO+emzAxBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T03:08:25.533547Z"},"content_sha256":"2024b8f3ca4557945eef2b11e9101d8152da2cc468052994e611c6c859f32bab","schema_version":"1.0","event_id":"sha256:2024b8f3ca4557945eef2b11e9101d8152da2cc468052994e611c6c859f32bab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CSMMBWOC6ERODM7RHBDGPXFHX6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ProtCLIP: Function-Informed Protein Multi-Modal Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Hanjing Zhou, Jian Wu, Jintai Chen, Kun Fu, Mingyang Li, Mingze Yin, Wei Wu, Zheng Wang","submitted_at":"2024-12-28T04:23:47Z","abstract_excerpt":"Multi-modality pre-training paradigm that aligns protein sequences and biological descriptions has learned general protein representations and achieved promising performance in various downstream applications. However, these works were still unable to replicate the extraordinary success of language-supervised visual foundation models due to the ineffective usage of aligned protein-text paired data and the lack of an effective function-informed pre-training paradigm. To address these issues, this paper curates a large-scale protein-text paired dataset called ProtAnno with a property-driven samp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20014","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.20014/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":"2026-07-05T09:54:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ayuASlxBnboMfgGsxXpvFPZqkYD210ZRhOrDXegS1Vcf71QLtQcWJiTT4lbYBdUAihxPMXmeM34cpvUcMNHnBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T03:08:25.534081Z"},"content_sha256":"fff5a06474ddf73ee426b6b7037354a604602d883ad0266e797c9caf3146bf18","schema_version":"1.0","event_id":"sha256:fff5a06474ddf73ee426b6b7037354a604602d883ad0266e797c9caf3146bf18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CSMMBWOC6ERODM7RHBDGPXFHX6/bundle.json","state_url":"https://pith.science/pith/CSMMBWOC6ERODM7RHBDGPXFHX6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CSMMBWOC6ERODM7RHBDGPXFHX6/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":"2026-07-11T03:08:25Z","links":{"resolver":"https://pith.science/pith/CSMMBWOC6ERODM7RHBDGPXFHX6","bundle":"https://pith.science/pith/CSMMBWOC6ERODM7RHBDGPXFHX6/bundle.json","state":"https://pith.science/pith/CSMMBWOC6ERODM7RHBDGPXFHX6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CSMMBWOC6ERODM7RHBDGPXFHX6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CSMMBWOC6ERODM7RHBDGPXFHX6","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":"1de2e835201ca8a35da7f833a1315b94bc5b92da0fcb6fb971f9956ba36f3b67","cross_cats_sorted":["cs.AI","q-bio.BM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-28T04:23:47Z","title_canon_sha256":"7646d42fd9cb492e876a73736f3cd33926423a9fef28b3be8bd45462272abd37"},"schema_version":"1.0","source":{"id":"2412.20014","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20014","created_at":"2026-07-05T09:54:53Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20014v1","created_at":"2026-07-05T09:54:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20014","created_at":"2026-07-05T09:54:53Z"},{"alias_kind":"pith_short_12","alias_value":"CSMMBWOC6ERO","created_at":"2026-07-05T09:54:53Z"},{"alias_kind":"pith_short_16","alias_value":"CSMMBWOC6ERODM7R","created_at":"2026-07-05T09:54:53Z"},{"alias_kind":"pith_short_8","alias_value":"CSMMBWOC","created_at":"2026-07-05T09:54:53Z"}],"graph_snapshots":[{"event_id":"sha256:fff5a06474ddf73ee426b6b7037354a604602d883ad0266e797c9caf3146bf18","target":"graph","created_at":"2026-07-05T09:54:53Z","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/2412.20014/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modality pre-training paradigm that aligns protein sequences and biological descriptions has learned general protein representations and achieved promising performance in various downstream applications. However, these works were still unable to replicate the extraordinary success of language-supervised visual foundation models due to the ineffective usage of aligned protein-text paired data and the lack of an effective function-informed pre-training paradigm. To address these issues, this paper curates a large-scale protein-text paired dataset called ProtAnno with a property-driven samp","authors_text":"Hanjing Zhou, Jian Wu, Jintai Chen, Kun Fu, Mingyang Li, Mingze Yin, Wei Wu, Zheng Wang","cross_cats":["cs.AI","q-bio.BM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-28T04:23:47Z","title":"ProtCLIP: Function-Informed Protein Multi-Modal Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20014","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":"sha256:2024b8f3ca4557945eef2b11e9101d8152da2cc468052994e611c6c859f32bab","target":"record","created_at":"2026-07-05T09:54:53Z","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":"1de2e835201ca8a35da7f833a1315b94bc5b92da0fcb6fb971f9956ba36f3b67","cross_cats_sorted":["cs.AI","q-bio.BM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-28T04:23:47Z","title_canon_sha256":"7646d42fd9cb492e876a73736f3cd33926423a9fef28b3be8bd45462272abd37"},"schema_version":"1.0","source":{"id":"2412.20014","kind":"arxiv","version":1}},"canonical_sha256":"1498c0d9c2f122e1b3f1384667dca7bfa57fd908767790bb7d7fbd4def1c26aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1498c0d9c2f122e1b3f1384667dca7bfa57fd908767790bb7d7fbd4def1c26aa","first_computed_at":"2026-07-05T09:54:53.215010Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:53.215010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1m6wGoPlRq6aRyMJqpMNhtULUb8rxgRMOIt/nFaFR5GJuDVaQJeD1YJJZeYMYVY/gQOXPxrWEj3Bygjv9XE0CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:53.215465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.20014","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2024b8f3ca4557945eef2b11e9101d8152da2cc468052994e611c6c859f32bab","sha256:fff5a06474ddf73ee426b6b7037354a604602d883ad0266e797c9caf3146bf18"],"state_sha256":"066687cf9b9ee16afa8b104091ab66efee289647e2475b0d4a25df1088480a0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GGpSp18ipruznyMA4eeHDZgtQrjq6d8WJmouAVh3crIFnYtN6kK9Xxo0nVtIqwlxFdUHSMClaO8SSjkvaXPLBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T03:08:25.538900Z","bundle_sha256":"50d3c7fd7270df69b76d785ff2ed3ab18bdd64028c77e0ca473c3565a912203c"}}