{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CUIM6RFKZTKUGR42MQJVR5G2GG","short_pith_number":"pith:CUIM6RFK","canonical_record":{"source":{"id":"2404.13571","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-21T08:20:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"231c04d7a3f7532c2c2eb9f779044235ec40b0c12ceae8b25aa29f3b693e19ca","abstract_canon_sha256":"97f8a88c3ebfbe9eeec75be0a1f542157d75bc46848043ec1e19c606c2cfb602"},"schema_version":"1.0"},"canonical_sha256":"1510cf44aaccd543479a641358f4da31b0f944de6689726cc2d16acc4258de29","source":{"kind":"arxiv","id":"2404.13571","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.13571","created_at":"2026-07-05T08:10:34Z"},{"alias_kind":"arxiv_version","alias_value":"2404.13571v1","created_at":"2026-07-05T08:10:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13571","created_at":"2026-07-05T08:10:34Z"},{"alias_kind":"pith_short_12","alias_value":"CUIM6RFKZTKU","created_at":"2026-07-05T08:10:34Z"},{"alias_kind":"pith_short_16","alias_value":"CUIM6RFKZTKUGR42","created_at":"2026-07-05T08:10:34Z"},{"alias_kind":"pith_short_8","alias_value":"CUIM6RFK","created_at":"2026-07-05T08:10:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CUIM6RFKZTKUGR42MQJVR5G2GG","target":"record","payload":{"canonical_record":{"source":{"id":"2404.13571","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-21T08:20:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"231c04d7a3f7532c2c2eb9f779044235ec40b0c12ceae8b25aa29f3b693e19ca","abstract_canon_sha256":"97f8a88c3ebfbe9eeec75be0a1f542157d75bc46848043ec1e19c606c2cfb602"},"schema_version":"1.0"},"canonical_sha256":"1510cf44aaccd543479a641358f4da31b0f944de6689726cc2d16acc4258de29","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:34.316138Z","signature_b64":"4Va//pRrwrTudsS2pha6kmChpFcVoa7bY1koDnAdTULGE8Q8WAoq/Xh+FAEPzrfcsub/dIA0KZ592moq0xTHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1510cf44aaccd543479a641358f4da31b0f944de6689726cc2d16acc4258de29","last_reissued_at":"2026-07-05T08:10:34.315722Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:34.315722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.13571","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":"2026-07-05T08:10:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sZn1aLWLq2NMvklHl5GO/8+F/Jh+Ny1NcwA4EfpsS8WaMVp/tOKWDxADFOHLNquIKIRgnGjsZWaFQN5rWVmcDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:04:48.273992Z"},"content_sha256":"887f40bd15fd1d8ee4ea71688c268d9ae8161a72c653ca26c3242515ab7be07b","schema_version":"1.0","event_id":"sha256:887f40bd15fd1d8ee4ea71688c268d9ae8161a72c653ca26c3242515ab7be07b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CUIM6RFKZTKUGR42MQJVR5G2GG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Test-Time Training on Graphs with Large Language Models (LLMs)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"En Zhu, Jiaxin Zhang, Ruicaho Ren, Siwei Wang, Xihong Yang, Xinwang Liu, Yiqi Wang, Yu Feng, Yu Shi","submitted_at":"2024-04-21T08:20:02Z","abstract_excerpt":"Graph Neural Networks have demonstrated great success in various fields of multimedia. However, the distribution shift between the training and test data challenges the effectiveness of GNNs. To mitigate this challenge, Test-Time Training (TTT) has been proposed as a promising approach. Traditional TTT methods require a demanding unsupervised training strategy to capture the information from test to benefit the main task. Inspired by the great annotation ability of Large Language Models (LLMs) on Text-Attributed Graphs (TAGs), we propose to enhance the test-time training on graphs with LLMs as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13571","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/2404.13571/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":"2026-07-05T08:10:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lOqMPWFFEyhPzr6Shw5ActCCxosww/B21iazAJL788X+/QFLBxC8Ts4rzUlOQlgrgD5hFUzgXzDhLEFUbnmSCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:04:48.274374Z"},"content_sha256":"692539517e9b9e87c132865f96b095df62dcb748cb123782d508c806b8e35981","schema_version":"1.0","event_id":"sha256:692539517e9b9e87c132865f96b095df62dcb748cb123782d508c806b8e35981"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CUIM6RFKZTKUGR42MQJVR5G2GG/bundle.json","state_url":"https://pith.science/pith/CUIM6RFKZTKUGR42MQJVR5G2GG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CUIM6RFKZTKUGR42MQJVR5G2GG/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":"2026-07-06T19:04:48Z","links":{"resolver":"https://pith.science/pith/CUIM6RFKZTKUGR42MQJVR5G2GG","bundle":"https://pith.science/pith/CUIM6RFKZTKUGR42MQJVR5G2GG/bundle.json","state":"https://pith.science/pith/CUIM6RFKZTKUGR42MQJVR5G2GG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CUIM6RFKZTKUGR42MQJVR5G2GG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CUIM6RFKZTKUGR42MQJVR5G2GG","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":"97f8a88c3ebfbe9eeec75be0a1f542157d75bc46848043ec1e19c606c2cfb602","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-21T08:20:02Z","title_canon_sha256":"231c04d7a3f7532c2c2eb9f779044235ec40b0c12ceae8b25aa29f3b693e19ca"},"schema_version":"1.0","source":{"id":"2404.13571","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.13571","created_at":"2026-07-05T08:10:34Z"},{"alias_kind":"arxiv_version","alias_value":"2404.13571v1","created_at":"2026-07-05T08:10:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13571","created_at":"2026-07-05T08:10:34Z"},{"alias_kind":"pith_short_12","alias_value":"CUIM6RFKZTKU","created_at":"2026-07-05T08:10:34Z"},{"alias_kind":"pith_short_16","alias_value":"CUIM6RFKZTKUGR42","created_at":"2026-07-05T08:10:34Z"},{"alias_kind":"pith_short_8","alias_value":"CUIM6RFK","created_at":"2026-07-05T08:10:34Z"}],"graph_snapshots":[{"event_id":"sha256:692539517e9b9e87c132865f96b095df62dcb748cb123782d508c806b8e35981","target":"graph","created_at":"2026-07-05T08:10:34Z","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/2404.13571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph Neural Networks have demonstrated great success in various fields of multimedia. However, the distribution shift between the training and test data challenges the effectiveness of GNNs. To mitigate this challenge, Test-Time Training (TTT) has been proposed as a promising approach. Traditional TTT methods require a demanding unsupervised training strategy to capture the information from test to benefit the main task. Inspired by the great annotation ability of Large Language Models (LLMs) on Text-Attributed Graphs (TAGs), we propose to enhance the test-time training on graphs with LLMs as","authors_text":"En Zhu, Jiaxin Zhang, Ruicaho Ren, Siwei Wang, Xihong Yang, Xinwang Liu, Yiqi Wang, Yu Feng, Yu Shi","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-21T08:20:02Z","title":"Test-Time Training on Graphs with Large Language Models (LLMs)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13571","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":"sha256:887f40bd15fd1d8ee4ea71688c268d9ae8161a72c653ca26c3242515ab7be07b","target":"record","created_at":"2026-07-05T08:10:34Z","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":"97f8a88c3ebfbe9eeec75be0a1f542157d75bc46848043ec1e19c606c2cfb602","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-21T08:20:02Z","title_canon_sha256":"231c04d7a3f7532c2c2eb9f779044235ec40b0c12ceae8b25aa29f3b693e19ca"},"schema_version":"1.0","source":{"id":"2404.13571","kind":"arxiv","version":1}},"canonical_sha256":"1510cf44aaccd543479a641358f4da31b0f944de6689726cc2d16acc4258de29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1510cf44aaccd543479a641358f4da31b0f944de6689726cc2d16acc4258de29","first_computed_at":"2026-07-05T08:10:34.315722Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:10:34.315722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4Va//pRrwrTudsS2pha6kmChpFcVoa7bY1koDnAdTULGE8Q8WAoq/Xh+FAEPzrfcsub/dIA0KZ592moq0xTHAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:10:34.316138Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.13571","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:887f40bd15fd1d8ee4ea71688c268d9ae8161a72c653ca26c3242515ab7be07b","sha256:692539517e9b9e87c132865f96b095df62dcb748cb123782d508c806b8e35981"],"state_sha256":"5a9f0909df58924bec421b8256eda644fa72c214f8a5f2d660b3b4b2f30f49a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BfZSbu7GzgvfYzAwEZy0kFYCjBapp1Z5eAv/RVnMiDhcOkPTFgvPQhHHZHFINSBBVQQHL6oqHUq34lAvlgoEAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:04:48.276713Z","bundle_sha256":"18f4c4fd3a786c3079c1c851a088f8195efcb97205df99b148158dbe851bc316"}}