{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GP6374N4GDLDDTHDNCO26232JA","short_pith_number":"pith:GP6374N4","schema_version":"1.0","canonical_sha256":"33fdbff1bc30d631cce3689daf6b7a4806111ed85d7b0430f0fc532342bf01a3","source":{"kind":"arxiv","id":"2106.09373","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Path Representation Learning with Curriculum Negative Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Yang, Chenjuan Guo, Jian Tang, Jilin Hu, Sean Bin Yang","submitted_at":"2021-06-17T10:47:19Z","abstract_excerpt":"Path representations are critical in a variety of transportation applications, such as estimating path ranking in path recommendation systems and estimating path travel time in navigation systems. Existing studies often learn task-specific path representations in a supervised manner, which require a large amount of labeled training data and generalize poorly to other tasks. We propose an unsupervised learning framework Path InfoMax (PIM) to learn generic path representations that work for different downstream tasks. We first propose a curriculum negative sampling method, for each input path, t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2106.09373","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-17T10:47:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b1eb7d69da2a9a23d86716cefa3b8ff031f14a5d71e4c870a2a657c1e442eea9","abstract_canon_sha256":"102ea9e25629eaf35935c82b55935eb43a96a834bc2806e64ad871b982a00c39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:15.522993Z","signature_b64":"DbCrE1TYYZUvoMuxJ3TZai3QyXuNNjk4kDn8Fa5JFOXkC5DwHghdyZwH2PQeGmqlYC220wgC6SvfjvsBIKGPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33fdbff1bc30d631cce3689daf6b7a4806111ed85d7b0430f0fc532342bf01a3","last_reissued_at":"2026-07-05T02:50:15.522589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:15.522589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Path Representation Learning with Curriculum Negative Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Yang, Chenjuan Guo, Jian Tang, Jilin Hu, Sean Bin Yang","submitted_at":"2021-06-17T10:47:19Z","abstract_excerpt":"Path representations are critical in a variety of transportation applications, such as estimating path ranking in path recommendation systems and estimating path travel time in navigation systems. Existing studies often learn task-specific path representations in a supervised manner, which require a large amount of labeled training data and generalize poorly to other tasks. We propose an unsupervised learning framework Path InfoMax (PIM) to learn generic path representations that work for different downstream tasks. We first propose a curriculum negative sampling method, for each input path, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09373","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/2106.09373/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2106.09373","created_at":"2026-07-05T02:50:15.522647+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09373v1","created_at":"2026-07-05T02:50:15.522647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09373","created_at":"2026-07-05T02:50:15.522647+00:00"},{"alias_kind":"pith_short_12","alias_value":"GP6374N4GDLD","created_at":"2026-07-05T02:50:15.522647+00:00"},{"alias_kind":"pith_short_16","alias_value":"GP6374N4GDLDDTHD","created_at":"2026-07-05T02:50:15.522647+00:00"},{"alias_kind":"pith_short_8","alias_value":"GP6374N4","created_at":"2026-07-05T02:50:15.522647+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20134","citing_title":"TrajTok: Adaptive Spatial Tokenization for Trajectory Representation Learning","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GP6374N4GDLDDTHDNCO26232JA","json":"https://pith.science/pith/GP6374N4GDLDDTHDNCO26232JA.json","graph_json":"https://pith.science/api/pith-number/GP6374N4GDLDDTHDNCO26232JA/graph.json","events_json":"https://pith.science/api/pith-number/GP6374N4GDLDDTHDNCO26232JA/events.json","paper":"https://pith.science/paper/GP6374N4"},"agent_actions":{"view_html":"https://pith.science/pith/GP6374N4GDLDDTHDNCO26232JA","download_json":"https://pith.science/pith/GP6374N4GDLDDTHDNCO26232JA.json","view_paper":"https://pith.science/paper/GP6374N4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09373&json=true","fetch_graph":"https://pith.science/api/pith-number/GP6374N4GDLDDTHDNCO26232JA/graph.json","fetch_events":"https://pith.science/api/pith-number/GP6374N4GDLDDTHDNCO26232JA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GP6374N4GDLDDTHDNCO26232JA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GP6374N4GDLDDTHDNCO26232JA/action/storage_attestation","attest_author":"https://pith.science/pith/GP6374N4GDLDDTHDNCO26232JA/action/author_attestation","sign_citation":"https://pith.science/pith/GP6374N4GDLDDTHDNCO26232JA/action/citation_signature","submit_replication":"https://pith.science/pith/GP6374N4GDLDDTHDNCO26232JA/action/replication_record"}},"created_at":"2026-07-05T02:50:15.522647+00:00","updated_at":"2026-07-05T02:50:15.522647+00:00"}