{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3OI5JPPTY4CGXT2XNEUBYTW2EI","short_pith_number":"pith:3OI5JPPT","schema_version":"1.0","canonical_sha256":"db91d4bdf3c7046bcf5769281c4eda221ec7f6c081f025f0ac5e49ac6d02670d","source":{"kind":"arxiv","id":"2605.24680","version":1},"attestation_state":"computed","paper":{"title":"Trajectory-Based Difficulty Scoring for Reliable Learning on Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bracha Shapira, Nadav Rappoport, Tomer Lavi","submitted_at":"2026-05-23T17:30:08Z","abstract_excerpt":"Gradient-boosted trees achieve strong performance on tabular data, yet often leave a long tail of poorly predicted instances. We introduce a Trajectory-based Difficulty Score (TDS), an instance-level difficulty estimator for boosted ensembles derived from per-tree cumulative prediction trajectories. For each instance, we compute interpretable trajectory descriptors (e.g., variance, oscillation peaks, sign switches, and tail stability) and train a lightweight regression model to predict held-out loss. An empirical CDF calibrates the resulting signal into a score in $[0,1]$ that supports ranking"},"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":"2605.24680","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T17:30:08Z","cross_cats_sorted":[],"title_canon_sha256":"f0657a3fab1508516350b2f0cf63d0419798778fb9cb8cc8809c63f1fafd13e8","abstract_canon_sha256":"09c0da06e9d4d42a930b4c0f7528f9b810d92255a99d816f6b84297a840d4bf1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:52.926209Z","signature_b64":"jL9LBlxglxF87Hrmvo6IyGKfGNQQ8RKlbj2u/hlMLsgVs6sfLGbrRmg59cH6SvpGaLIVrBx5vpFS26kYp+KKDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db91d4bdf3c7046bcf5769281c4eda221ec7f6c081f025f0ac5e49ac6d02670d","last_reissued_at":"2026-05-26T01:03:52.925457Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:52.925457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trajectory-Based Difficulty Scoring for Reliable Learning on Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bracha Shapira, Nadav Rappoport, Tomer Lavi","submitted_at":"2026-05-23T17:30:08Z","abstract_excerpt":"Gradient-boosted trees achieve strong performance on tabular data, yet often leave a long tail of poorly predicted instances. We introduce a Trajectory-based Difficulty Score (TDS), an instance-level difficulty estimator for boosted ensembles derived from per-tree cumulative prediction trajectories. For each instance, we compute interpretable trajectory descriptors (e.g., variance, oscillation peaks, sign switches, and tail stability) and train a lightweight regression model to predict held-out loss. An empirical CDF calibrates the resulting signal into a score in $[0,1]$ that supports ranking"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24680","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/2605.24680/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":"2605.24680","created_at":"2026-05-26T01:03:52.925607+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24680v1","created_at":"2026-05-26T01:03:52.925607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24680","created_at":"2026-05-26T01:03:52.925607+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OI5JPPTY4CG","created_at":"2026-05-26T01:03:52.925607+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OI5JPPTY4CGXT2X","created_at":"2026-05-26T01:03:52.925607+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OI5JPPT","created_at":"2026-05-26T01:03:52.925607+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3OI5JPPTY4CGXT2XNEUBYTW2EI","json":"https://pith.science/pith/3OI5JPPTY4CGXT2XNEUBYTW2EI.json","graph_json":"https://pith.science/api/pith-number/3OI5JPPTY4CGXT2XNEUBYTW2EI/graph.json","events_json":"https://pith.science/api/pith-number/3OI5JPPTY4CGXT2XNEUBYTW2EI/events.json","paper":"https://pith.science/paper/3OI5JPPT"},"agent_actions":{"view_html":"https://pith.science/pith/3OI5JPPTY4CGXT2XNEUBYTW2EI","download_json":"https://pith.science/pith/3OI5JPPTY4CGXT2XNEUBYTW2EI.json","view_paper":"https://pith.science/paper/3OI5JPPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24680&json=true","fetch_graph":"https://pith.science/api/pith-number/3OI5JPPTY4CGXT2XNEUBYTW2EI/graph.json","fetch_events":"https://pith.science/api/pith-number/3OI5JPPTY4CGXT2XNEUBYTW2EI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OI5JPPTY4CGXT2XNEUBYTW2EI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OI5JPPTY4CGXT2XNEUBYTW2EI/action/storage_attestation","attest_author":"https://pith.science/pith/3OI5JPPTY4CGXT2XNEUBYTW2EI/action/author_attestation","sign_citation":"https://pith.science/pith/3OI5JPPTY4CGXT2XNEUBYTW2EI/action/citation_signature","submit_replication":"https://pith.science/pith/3OI5JPPTY4CGXT2XNEUBYTW2EI/action/replication_record"}},"created_at":"2026-05-26T01:03:52.925607+00:00","updated_at":"2026-05-26T01:03:52.925607+00:00"}