{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:P7I3FJOPFLGLIXDJ3XCFGLVJG7","short_pith_number":"pith:P7I3FJOP","canonical_record":{"source":{"id":"2512.15133","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2025-12-17T06:46:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a3597a90bad5100fd4c4bdf6ba56f0d2f178116605dff4751682ea0eb71ec1f","abstract_canon_sha256":"16d7506b467a055e64b9fbb078337b6bc0c5e486bb43942d8ae439a34155b112"},"schema_version":"1.0"},"canonical_sha256":"7fd1b2a5cf2accb45c69ddc4532ea937cfcaa36b0a896302869b4c3c20acecd6","source":{"kind":"arxiv","id":"2512.15133","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.15133","created_at":"2026-05-29T02:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2512.15133v2","created_at":"2026-05-29T02:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.15133","created_at":"2026-05-29T02:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"P7I3FJOPFLGL","created_at":"2026-05-29T02:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"P7I3FJOPFLGLIXDJ","created_at":"2026-05-29T02:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"P7I3FJOP","created_at":"2026-05-29T02:05:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:P7I3FJOPFLGLIXDJ3XCFGLVJG7","target":"record","payload":{"canonical_record":{"source":{"id":"2512.15133","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2025-12-17T06:46:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a3597a90bad5100fd4c4bdf6ba56f0d2f178116605dff4751682ea0eb71ec1f","abstract_canon_sha256":"16d7506b467a055e64b9fbb078337b6bc0c5e486bb43942d8ae439a34155b112"},"schema_version":"1.0"},"canonical_sha256":"7fd1b2a5cf2accb45c69ddc4532ea937cfcaa36b0a896302869b4c3c20acecd6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:38.559611Z","signature_b64":"XS1I4k+AjdpvIEeKBQpxgsjk+WGd+VcTfeg1NPcl2WeIAVLMvmH239ry9LiK3R8Ajo4Z2Ci8QlmRgUAokpe7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fd1b2a5cf2accb45c69ddc4532ea937cfcaa36b0a896302869b4c3c20acecd6","last_reissued_at":"2026-05-29T02:05:38.558979Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:38.558979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.15133","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":"2026-05-29T02:05:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RV8zJYdOpoiuxQ5crektFcak6zyxrt3HsCkwiAXb5cMpG2Yiw+ozqNwXmka46LiHVOTUHVEBeh/Zd1iJ7r6BDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T09:12:45.866248Z"},"content_sha256":"874ab041f1fcd8cf0a7d343b5e61118cc54b5b245e24307681e96def7f92e497","schema_version":"1.0","event_id":"sha256:874ab041f1fcd8cf0a7d343b5e61118cc54b5b245e24307681e96def7f92e497"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:P7I3FJOPFLGLIXDJ3XCFGLVJG7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HD-Prot: A Protein Language Model for Joint Sequence-Structure Modeling with Continuous Structure Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CE","authors_text":"Haohao Qu, Le Song, Shanru Lin, Wenqi Fan, Yi Zhou, Yunqing Liu","submitted_at":"2025-12-17T06:46:27Z","abstract_excerpt":"Proteins inherently possess a consistent sequence-structure duality. The abundance of protein sequence data, which can be readily represented as discrete tokens, has driven fruitful developments in protein language models (pLMs). A key remaining challenge, however, is how to effectively integrate continuous structural knowledge into pLMs. Current methods often discretize protein structures to accommodate the language modeling framework, which inevitably results in the loss of fine-grained information and limits the performance potential of multimodal pLMs. In this paper, we argue that such con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.15133","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.15133/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":"2026-05-29T02:05:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SbouyZ3dx7J6vKOglMweLKXtUi+QRQ7YkRfSmdjL+sf0VtfHs7YrtFJe+3JKXi1cM/XxT7R1nKriMD8S9dUiAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T09:12:45.866688Z"},"content_sha256":"adccecfe0a54f41e23479e61ad5214e788e5450115c74d21ea044c67665baf26","schema_version":"1.0","event_id":"sha256:adccecfe0a54f41e23479e61ad5214e788e5450115c74d21ea044c67665baf26"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P7I3FJOPFLGLIXDJ3XCFGLVJG7/bundle.json","state_url":"https://pith.science/pith/P7I3FJOPFLGLIXDJ3XCFGLVJG7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P7I3FJOPFLGLIXDJ3XCFGLVJG7/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":"2026-06-03T09:12:45Z","links":{"resolver":"https://pith.science/pith/P7I3FJOPFLGLIXDJ3XCFGLVJG7","bundle":"https://pith.science/pith/P7I3FJOPFLGLIXDJ3XCFGLVJG7/bundle.json","state":"https://pith.science/pith/P7I3FJOPFLGLIXDJ3XCFGLVJG7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P7I3FJOPFLGLIXDJ3XCFGLVJG7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P7I3FJOPFLGLIXDJ3XCFGLVJG7","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":"16d7506b467a055e64b9fbb078337b6bc0c5e486bb43942d8ae439a34155b112","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2025-12-17T06:46:27Z","title_canon_sha256":"5a3597a90bad5100fd4c4bdf6ba56f0d2f178116605dff4751682ea0eb71ec1f"},"schema_version":"1.0","source":{"id":"2512.15133","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.15133","created_at":"2026-05-29T02:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2512.15133v2","created_at":"2026-05-29T02:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.15133","created_at":"2026-05-29T02:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"P7I3FJOPFLGL","created_at":"2026-05-29T02:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"P7I3FJOPFLGLIXDJ","created_at":"2026-05-29T02:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"P7I3FJOP","created_at":"2026-05-29T02:05:38Z"}],"graph_snapshots":[{"event_id":"sha256:adccecfe0a54f41e23479e61ad5214e788e5450115c74d21ea044c67665baf26","target":"graph","created_at":"2026-05-29T02:05:38Z","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/2512.15133/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Proteins inherently possess a consistent sequence-structure duality. The abundance of protein sequence data, which can be readily represented as discrete tokens, has driven fruitful developments in protein language models (pLMs). A key remaining challenge, however, is how to effectively integrate continuous structural knowledge into pLMs. Current methods often discretize protein structures to accommodate the language modeling framework, which inevitably results in the loss of fine-grained information and limits the performance potential of multimodal pLMs. In this paper, we argue that such con","authors_text":"Haohao Qu, Le Song, Shanru Lin, Wenqi Fan, Yi Zhou, Yunqing Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2025-12-17T06:46:27Z","title":"HD-Prot: A Protein Language Model for Joint Sequence-Structure Modeling with Continuous Structure Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.15133","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":"sha256:874ab041f1fcd8cf0a7d343b5e61118cc54b5b245e24307681e96def7f92e497","target":"record","created_at":"2026-05-29T02:05:38Z","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":"16d7506b467a055e64b9fbb078337b6bc0c5e486bb43942d8ae439a34155b112","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2025-12-17T06:46:27Z","title_canon_sha256":"5a3597a90bad5100fd4c4bdf6ba56f0d2f178116605dff4751682ea0eb71ec1f"},"schema_version":"1.0","source":{"id":"2512.15133","kind":"arxiv","version":2}},"canonical_sha256":"7fd1b2a5cf2accb45c69ddc4532ea937cfcaa36b0a896302869b4c3c20acecd6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fd1b2a5cf2accb45c69ddc4532ea937cfcaa36b0a896302869b4c3c20acecd6","first_computed_at":"2026-05-29T02:05:38.558979Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:38.558979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XS1I4k+AjdpvIEeKBQpxgsjk+WGd+VcTfeg1NPcl2WeIAVLMvmH239ry9LiK3R8Ajo4Z2Ci8QlmRgUAokpe7Cg==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:38.559611Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.15133","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:874ab041f1fcd8cf0a7d343b5e61118cc54b5b245e24307681e96def7f92e497","sha256:adccecfe0a54f41e23479e61ad5214e788e5450115c74d21ea044c67665baf26"],"state_sha256":"d215ba62aa7daee76c69246b0dc56c87d365e18889529f00fc8a57bff252df4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z/elXeVH6EvBP1jEvDUeSmA52NE1oRtkk8w/owWlvn43LK+/yrGhHU0iUb4Im2kXOmH3jCLd31DO3zMrDEmhBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T09:12:45.868773Z","bundle_sha256":"830a7424a4059b663b1e4b46241d2a54cf27da69af66c174877d19b63b088c8d"}}