{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4JDI53LCXYYN3M3O6NTY5GFTIM","short_pith_number":"pith:4JDI53LC","canonical_record":{"source":{"id":"2401.15569","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-28T05:12:09Z","cross_cats_sorted":[],"title_canon_sha256":"e0d6517bea716cd9a027ddf9532edf1ac56e8143c618679b0be9fdc56a6a6714","abstract_canon_sha256":"d5d30d6d1eef5d0aa57c1f18023b5c16c18672f5406f6f83dcb509ded903a542"},"schema_version":"1.0"},"canonical_sha256":"e2468eed62be30ddb36ef3678e98b343109af341322096b8073e79f487bd5c26","source":{"kind":"arxiv","id":"2401.15569","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.15569","created_at":"2026-07-05T08:47:49Z"},{"alias_kind":"arxiv_version","alias_value":"2401.15569v2","created_at":"2026-07-05T08:47:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15569","created_at":"2026-07-05T08:47:49Z"},{"alias_kind":"pith_short_12","alias_value":"4JDI53LCXYYN","created_at":"2026-07-05T08:47:49Z"},{"alias_kind":"pith_short_16","alias_value":"4JDI53LCXYYN3M3O","created_at":"2026-07-05T08:47:49Z"},{"alias_kind":"pith_short_8","alias_value":"4JDI53LC","created_at":"2026-07-05T08:47:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4JDI53LCXYYN3M3O6NTY5GFTIM","target":"record","payload":{"canonical_record":{"source":{"id":"2401.15569","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-28T05:12:09Z","cross_cats_sorted":[],"title_canon_sha256":"e0d6517bea716cd9a027ddf9532edf1ac56e8143c618679b0be9fdc56a6a6714","abstract_canon_sha256":"d5d30d6d1eef5d0aa57c1f18023b5c16c18672f5406f6f83dcb509ded903a542"},"schema_version":"1.0"},"canonical_sha256":"e2468eed62be30ddb36ef3678e98b343109af341322096b8073e79f487bd5c26","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:49.419039Z","signature_b64":"XqOdlfALELo8lhc3mp1cV/39y3aEN/GNGdTtVmI9I5Tb1GpmiMiTpWpUpgqHUj6gmmivsQBsQpdaurG6sd5gAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2468eed62be30ddb36ef3678e98b343109af341322096b8073e79f487bd5c26","last_reissued_at":"2026-07-05T08:47:49.418618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:49.418618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.15569","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":"2026-07-05T08:47:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZSVOvrrwULOoOzhiTOjomhReH6lcnd6jCfjT3EtBQo1EeK8CdfbsQ3KJmb9aLDdOwp2R2IbcZTOgG4RpwWiVDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:35:21.112036Z"},"content_sha256":"9bab71505ae72ba21119ad6bbd093f900f3906176485ca2f33ad7a1b8c8296a0","schema_version":"1.0","event_id":"sha256:9bab71505ae72ba21119ad6bbd093f900f3906176485ca2f33ad7a1b8c8296a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4JDI53LCXYYN3M3O6NTY5GFTIM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Tuning and Inference for Large Language Models on Textual Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haizhou Shi, Siliang Tang, Yaoke Wang, Yun Zhu","submitted_at":"2024-01-28T05:12:09Z","abstract_excerpt":"Rich textual and topological information of textual graphs need to be modeled in real-world applications such as webpages, e-commerce, and academic articles. Practitioners have been long following the path of adopting a shallow text encoder and a subsequent graph neural network (GNN) to solve this problem. In light of recent advancements in large language models (LLMs), it is apparent that integrating LLMs for enhanced textual encoding can substantially improve the performance of textual graphs. Nevertheless, the efficiency of these methods poses a significant challenge. In this paper, we prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15569","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/2401.15569/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":"2026-07-05T08:47:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E+bFz53Gf7sIPZAzSZ+ipeNoT7ZWKxW7I83rbdTc26a5/h36PvOdIrTw6yleBlKm/VPBtfC2sF9wUiVH2W73Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:35:21.112579Z"},"content_sha256":"bf04b1566421d37d063eebb987504854fbb60dd2e0cfe527cd758fd3d40c1e7b","schema_version":"1.0","event_id":"sha256:bf04b1566421d37d063eebb987504854fbb60dd2e0cfe527cd758fd3d40c1e7b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4JDI53LCXYYN3M3O6NTY5GFTIM/bundle.json","state_url":"https://pith.science/pith/4JDI53LCXYYN3M3O6NTY5GFTIM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4JDI53LCXYYN3M3O6NTY5GFTIM/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":"2026-08-07T22:35:21Z","links":{"resolver":"https://pith.science/pith/4JDI53LCXYYN3M3O6NTY5GFTIM","bundle":"https://pith.science/pith/4JDI53LCXYYN3M3O6NTY5GFTIM/bundle.json","state":"https://pith.science/pith/4JDI53LCXYYN3M3O6NTY5GFTIM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4JDI53LCXYYN3M3O6NTY5GFTIM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4JDI53LCXYYN3M3O6NTY5GFTIM","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":"d5d30d6d1eef5d0aa57c1f18023b5c16c18672f5406f6f83dcb509ded903a542","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-28T05:12:09Z","title_canon_sha256":"e0d6517bea716cd9a027ddf9532edf1ac56e8143c618679b0be9fdc56a6a6714"},"schema_version":"1.0","source":{"id":"2401.15569","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.15569","created_at":"2026-07-05T08:47:49Z"},{"alias_kind":"arxiv_version","alias_value":"2401.15569v2","created_at":"2026-07-05T08:47:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15569","created_at":"2026-07-05T08:47:49Z"},{"alias_kind":"pith_short_12","alias_value":"4JDI53LCXYYN","created_at":"2026-07-05T08:47:49Z"},{"alias_kind":"pith_short_16","alias_value":"4JDI53LCXYYN3M3O","created_at":"2026-07-05T08:47:49Z"},{"alias_kind":"pith_short_8","alias_value":"4JDI53LC","created_at":"2026-07-05T08:47:49Z"}],"graph_snapshots":[{"event_id":"sha256:bf04b1566421d37d063eebb987504854fbb60dd2e0cfe527cd758fd3d40c1e7b","target":"graph","created_at":"2026-07-05T08:47:49Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.15569/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Rich textual and topological information of textual graphs need to be modeled in real-world applications such as webpages, e-commerce, and academic articles. Practitioners have been long following the path of adopting a shallow text encoder and a subsequent graph neural network (GNN) to solve this problem. In light of recent advancements in large language models (LLMs), it is apparent that integrating LLMs for enhanced textual encoding can substantially improve the performance of textual graphs. Nevertheless, the efficiency of these methods poses a significant challenge. In this paper, we prop","authors_text":"Haizhou Shi, Siliang Tang, Yaoke Wang, Yun Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-28T05:12:09Z","title":"Efficient Tuning and Inference for Large Language Models on Textual Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15569","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":"sha256:9bab71505ae72ba21119ad6bbd093f900f3906176485ca2f33ad7a1b8c8296a0","target":"record","created_at":"2026-07-05T08:47:49Z","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":"d5d30d6d1eef5d0aa57c1f18023b5c16c18672f5406f6f83dcb509ded903a542","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-28T05:12:09Z","title_canon_sha256":"e0d6517bea716cd9a027ddf9532edf1ac56e8143c618679b0be9fdc56a6a6714"},"schema_version":"1.0","source":{"id":"2401.15569","kind":"arxiv","version":2}},"canonical_sha256":"e2468eed62be30ddb36ef3678e98b343109af341322096b8073e79f487bd5c26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2468eed62be30ddb36ef3678e98b343109af341322096b8073e79f487bd5c26","first_computed_at":"2026-07-05T08:47:49.418618Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:47:49.418618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XqOdlfALELo8lhc3mp1cV/39y3aEN/GNGdTtVmI9I5Tb1GpmiMiTpWpUpgqHUj6gmmivsQBsQpdaurG6sd5gAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:47:49.419039Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.15569","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9bab71505ae72ba21119ad6bbd093f900f3906176485ca2f33ad7a1b8c8296a0","sha256:bf04b1566421d37d063eebb987504854fbb60dd2e0cfe527cd758fd3d40c1e7b"],"state_sha256":"8084749343602b277861975a5e88f87af919b6a643a2a54c08bdef1a03781c63"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G+IRcdM4wVNT9niQcl73y3eZ6h4YjfoOYWCLehaoUv9LHFyCSqc2Ikaf+2Ov8G8BM6Mwgwh5biAgwFIX7g/nDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:35:21.116286Z","bundle_sha256":"be209515a4ead9bf6ed95e29fe265860e4590d2319a64347bd320c6ac5e39c42"}}