{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CWQSZ5GBSZ2AEMBDUY7CRGOVE4","short_pith_number":"pith:CWQSZ5GB","canonical_record":{"source":{"id":"2506.08293","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-06-09T23:50:11Z","cross_cats_sorted":[],"title_canon_sha256":"47ef41a85d9f6d6170b44dfae2cf8a3d7c7518f629be185d85b342db8511bd8d","abstract_canon_sha256":"4db8ce0a0279b74ebd72d5f3e6efc722c58cf99f6d7bb69bf80b614d26c38d2e"},"schema_version":"1.0"},"canonical_sha256":"15a12cf4c19674023023a63e2899d527023136dc2b3c94fd828d5681796ab8b6","source":{"kind":"arxiv","id":"2506.08293","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08293","created_at":"2026-07-05T11:18:47Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08293v1","created_at":"2026-07-05T11:18:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08293","created_at":"2026-07-05T11:18:47Z"},{"alias_kind":"pith_short_12","alias_value":"CWQSZ5GBSZ2A","created_at":"2026-07-05T11:18:47Z"},{"alias_kind":"pith_short_16","alias_value":"CWQSZ5GBSZ2AEMBD","created_at":"2026-07-05T11:18:47Z"},{"alias_kind":"pith_short_8","alias_value":"CWQSZ5GB","created_at":"2026-07-05T11:18:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CWQSZ5GBSZ2AEMBDUY7CRGOVE4","target":"record","payload":{"canonical_record":{"source":{"id":"2506.08293","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-06-09T23:50:11Z","cross_cats_sorted":[],"title_canon_sha256":"47ef41a85d9f6d6170b44dfae2cf8a3d7c7518f629be185d85b342db8511bd8d","abstract_canon_sha256":"4db8ce0a0279b74ebd72d5f3e6efc722c58cf99f6d7bb69bf80b614d26c38d2e"},"schema_version":"1.0"},"canonical_sha256":"15a12cf4c19674023023a63e2899d527023136dc2b3c94fd828d5681796ab8b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:47.642245Z","signature_b64":"fVeque0lGFxZGiap14yBGMjXGQ8RWO7FjXratk1uFIpgfeDSCEFqZxv12vl0q4L6P+0MFuW9b9pmXlH2h6n5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15a12cf4c19674023023a63e2899d527023136dc2b3c94fd828d5681796ab8b6","last_reissued_at":"2026-07-05T11:18:47.641759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:47.641759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.08293","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":"2026-07-05T11:18:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qm+BKzZdc9uvv5CurP2Cwf99NWmdgZMvde+/t8r/x5h43dpnBs/m0qYxsJ0uugRcQ7dPsex9kT51ocJ8933SBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:05:19.067184Z"},"content_sha256":"b8449127ceb3fdc9ba25e038874e46887481c1c1cf763428dcc83a83890b9a11","schema_version":"1.0","event_id":"sha256:b8449127ceb3fdc9ba25e038874e46887481c1c1cf763428dcc83a83890b9a11"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CWQSZ5GBSZ2AEMBDUY7CRGOVE4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diffusion Sequence Models for Enhanced Protein Representation and Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.BM","authors_text":"David B. Bichara, Jason P. Gleghorn, Logan Hallee, Nikolaos Rafailidis","submitted_at":"2025-06-09T23:50:11Z","abstract_excerpt":"Proteins are fundamental to biology, executing diverse functions through complex physicochemical interactions, and they hold transformative potential across medicine, materials science, and environmental applications. Protein Language Models (pLMs) aim to unlock insights from the vast space of unlabeled protein sequences by learning rich, semantic representations from primary sequences via masked language modeling. However, these models typically exhibit limited generative capacity. In this work, we introduce the Diffusion Sequence Model (DSM), a novel pLM trained with masked diffusion to enab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08293","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/2506.08293/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":"2026-07-05T11:18:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VVHCf4LLFmKf8Ok0x+ngj09zJMx9C6NR62eQYmH3IQuRptS5o+QecuLlg9O1ZMpKOus6Lvd66qS4rjBp4b4EAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:05:19.067706Z"},"content_sha256":"1b6a5099c58bc1ddd6d408791049f77f34f3a56284a18eeb40c303ca52e3a0e4","schema_version":"1.0","event_id":"sha256:1b6a5099c58bc1ddd6d408791049f77f34f3a56284a18eeb40c303ca52e3a0e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CWQSZ5GBSZ2AEMBDUY7CRGOVE4/bundle.json","state_url":"https://pith.science/pith/CWQSZ5GBSZ2AEMBDUY7CRGOVE4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CWQSZ5GBSZ2AEMBDUY7CRGOVE4/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":"2026-08-14T07:05:19Z","links":{"resolver":"https://pith.science/pith/CWQSZ5GBSZ2AEMBDUY7CRGOVE4","bundle":"https://pith.science/pith/CWQSZ5GBSZ2AEMBDUY7CRGOVE4/bundle.json","state":"https://pith.science/pith/CWQSZ5GBSZ2AEMBDUY7CRGOVE4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CWQSZ5GBSZ2AEMBDUY7CRGOVE4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CWQSZ5GBSZ2AEMBDUY7CRGOVE4","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":"4db8ce0a0279b74ebd72d5f3e6efc722c58cf99f6d7bb69bf80b614d26c38d2e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-06-09T23:50:11Z","title_canon_sha256":"47ef41a85d9f6d6170b44dfae2cf8a3d7c7518f629be185d85b342db8511bd8d"},"schema_version":"1.0","source":{"id":"2506.08293","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08293","created_at":"2026-07-05T11:18:47Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08293v1","created_at":"2026-07-05T11:18:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08293","created_at":"2026-07-05T11:18:47Z"},{"alias_kind":"pith_short_12","alias_value":"CWQSZ5GBSZ2A","created_at":"2026-07-05T11:18:47Z"},{"alias_kind":"pith_short_16","alias_value":"CWQSZ5GBSZ2AEMBD","created_at":"2026-07-05T11:18:47Z"},{"alias_kind":"pith_short_8","alias_value":"CWQSZ5GB","created_at":"2026-07-05T11:18:47Z"}],"graph_snapshots":[{"event_id":"sha256:1b6a5099c58bc1ddd6d408791049f77f34f3a56284a18eeb40c303ca52e3a0e4","target":"graph","created_at":"2026-07-05T11:18:47Z","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/2506.08293/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Proteins are fundamental to biology, executing diverse functions through complex physicochemical interactions, and they hold transformative potential across medicine, materials science, and environmental applications. Protein Language Models (pLMs) aim to unlock insights from the vast space of unlabeled protein sequences by learning rich, semantic representations from primary sequences via masked language modeling. However, these models typically exhibit limited generative capacity. In this work, we introduce the Diffusion Sequence Model (DSM), a novel pLM trained with masked diffusion to enab","authors_text":"David B. Bichara, Jason P. Gleghorn, Logan Hallee, Nikolaos Rafailidis","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-06-09T23:50:11Z","title":"Diffusion Sequence Models for Enhanced Protein Representation and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08293","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:b8449127ceb3fdc9ba25e038874e46887481c1c1cf763428dcc83a83890b9a11","target":"record","created_at":"2026-07-05T11:18:47Z","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":"4db8ce0a0279b74ebd72d5f3e6efc722c58cf99f6d7bb69bf80b614d26c38d2e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-06-09T23:50:11Z","title_canon_sha256":"47ef41a85d9f6d6170b44dfae2cf8a3d7c7518f629be185d85b342db8511bd8d"},"schema_version":"1.0","source":{"id":"2506.08293","kind":"arxiv","version":1}},"canonical_sha256":"15a12cf4c19674023023a63e2899d527023136dc2b3c94fd828d5681796ab8b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15a12cf4c19674023023a63e2899d527023136dc2b3c94fd828d5681796ab8b6","first_computed_at":"2026-07-05T11:18:47.641759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:47.641759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fVeque0lGFxZGiap14yBGMjXGQ8RWO7FjXratk1uFIpgfeDSCEFqZxv12vl0q4L6P+0MFuW9b9pmXlH2h6n5Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:47.642245Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08293","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8449127ceb3fdc9ba25e038874e46887481c1c1cf763428dcc83a83890b9a11","sha256:1b6a5099c58bc1ddd6d408791049f77f34f3a56284a18eeb40c303ca52e3a0e4"],"state_sha256":"876431870ab828177dcd9c1b834c4fe5cfb1b311a531b8b4ee88542ff3967875"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cgvUIfTD0nTqMwlY7nAY/Hwcimb6MNY34WKkN05BtqrlX4KcYl3l3ySa807827hVwhxS2tujaj7tNzKB0DrDDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T07:05:19.073552Z","bundle_sha256":"5f604bcd184a75f44c22bca114afbd320bbb38fa533491ca3468696ca9caf18a"}}