{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TBBYYBPVDHNTVEA4X3YYGDVUAT","short_pith_number":"pith:TBBYYBPV","canonical_record":{"source":{"id":"2410.16710","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-22T05:32:40Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"ad6fad52491d66196aa30d398be238c2aad326045c6c8acdd551431bdd6f1da6","abstract_canon_sha256":"a9f6a3e861d3875b065f5a7abdf074476ec11dc2f8cecc6ebc67a0fdbd51e4d9"},"schema_version":"1.0"},"canonical_sha256":"98438c05f519db3a901cbef1830eb404caf32f995d833464ebbdf6b4c4b9e789","source":{"kind":"arxiv","id":"2410.16710","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16710","created_at":"2026-07-05T09:24:05Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16710v1","created_at":"2026-07-05T09:24:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16710","created_at":"2026-07-05T09:24:05Z"},{"alias_kind":"pith_short_12","alias_value":"TBBYYBPVDHNT","created_at":"2026-07-05T09:24:05Z"},{"alias_kind":"pith_short_16","alias_value":"TBBYYBPVDHNTVEA4","created_at":"2026-07-05T09:24:05Z"},{"alias_kind":"pith_short_8","alias_value":"TBBYYBPV","created_at":"2026-07-05T09:24:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TBBYYBPVDHNTVEA4X3YYGDVUAT","target":"record","payload":{"canonical_record":{"source":{"id":"2410.16710","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-22T05:32:40Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"ad6fad52491d66196aa30d398be238c2aad326045c6c8acdd551431bdd6f1da6","abstract_canon_sha256":"a9f6a3e861d3875b065f5a7abdf074476ec11dc2f8cecc6ebc67a0fdbd51e4d9"},"schema_version":"1.0"},"canonical_sha256":"98438c05f519db3a901cbef1830eb404caf32f995d833464ebbdf6b4c4b9e789","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:05.463645Z","signature_b64":"qHTa5Xd9eJYIaMHOS7kRFpFB4dNzTXzaA+MCqWfbz8WbK00AwnQjR/Kacwmkk2l8yvx9GySxwfOszug6ghVrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98438c05f519db3a901cbef1830eb404caf32f995d833464ebbdf6b4c4b9e789","last_reissued_at":"2026-07-05T09:24:05.463213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:05.463213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.16710","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":"2026-07-05T09:24:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G72Sw4fZbnfAD8gzQ7VtdePys7FAl1SX/bIwkzFfJnPocWGQxZUgdyO19t6Q+ZM/YspTg5DT/de5RoVBUOvzDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:32:36.723665Z"},"content_sha256":"7db14706968491bc89757148958cdeb94aa4ff5b45b73fd4a11e59d955c039d1","schema_version":"1.0","event_id":"sha256:7db14706968491bc89757148958cdeb94aa4ff5b45b73fd4a11e59d955c039d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TBBYYBPVDHNTVEA4X3YYGDVUAT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Influential Language Data Selection via Gradient Trajectory Pursuit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Tao Li, Yang Li, Zhiwei Deng","submitted_at":"2024-10-22T05:32:40Z","abstract_excerpt":"Curating a desirable dataset for training has been the core of building highly capable large language models (Touvron et al., 2023; Achiam et al., 2023; Team et al.,2024). Gradient influence scores (Pruthi et al., 2020; Xia et al., 2024) are shown to be correlated with model performance and are commonly used as the criterion for data selection. However, existing methods are built upon either individual sample rankings or inefficient matching process, leading to suboptimal performance or scaling up issues.In this paper, we propose Gradient Trajectory Pursuit (GTP), an algorithm that performs pu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16710","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/2410.16710/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":"2026-07-05T09:24:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9CumuWI0Q0SDot7QcNHo3XjkWPSrzYO8QvLXMAh2sG2AdLCM2+UYos5B3OHu2SqDMrqmkA6uc89qSU4BQsS2Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:32:36.724164Z"},"content_sha256":"7e8a1cdc8bf412ea2d114ab6754af08af5b23abba0b82c68456a89e82b4fdc0c","schema_version":"1.0","event_id":"sha256:7e8a1cdc8bf412ea2d114ab6754af08af5b23abba0b82c68456a89e82b4fdc0c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TBBYYBPVDHNTVEA4X3YYGDVUAT/bundle.json","state_url":"https://pith.science/pith/TBBYYBPVDHNTVEA4X3YYGDVUAT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TBBYYBPVDHNTVEA4X3YYGDVUAT/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":"2026-08-07T23:32:36Z","links":{"resolver":"https://pith.science/pith/TBBYYBPVDHNTVEA4X3YYGDVUAT","bundle":"https://pith.science/pith/TBBYYBPVDHNTVEA4X3YYGDVUAT/bundle.json","state":"https://pith.science/pith/TBBYYBPVDHNTVEA4X3YYGDVUAT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TBBYYBPVDHNTVEA4X3YYGDVUAT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TBBYYBPVDHNTVEA4X3YYGDVUAT","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":"a9f6a3e861d3875b065f5a7abdf074476ec11dc2f8cecc6ebc67a0fdbd51e4d9","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-22T05:32:40Z","title_canon_sha256":"ad6fad52491d66196aa30d398be238c2aad326045c6c8acdd551431bdd6f1da6"},"schema_version":"1.0","source":{"id":"2410.16710","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16710","created_at":"2026-07-05T09:24:05Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16710v1","created_at":"2026-07-05T09:24:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16710","created_at":"2026-07-05T09:24:05Z"},{"alias_kind":"pith_short_12","alias_value":"TBBYYBPVDHNT","created_at":"2026-07-05T09:24:05Z"},{"alias_kind":"pith_short_16","alias_value":"TBBYYBPVDHNTVEA4","created_at":"2026-07-05T09:24:05Z"},{"alias_kind":"pith_short_8","alias_value":"TBBYYBPV","created_at":"2026-07-05T09:24:05Z"}],"graph_snapshots":[{"event_id":"sha256:7e8a1cdc8bf412ea2d114ab6754af08af5b23abba0b82c68456a89e82b4fdc0c","target":"graph","created_at":"2026-07-05T09:24:05Z","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/2410.16710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Curating a desirable dataset for training has been the core of building highly capable large language models (Touvron et al., 2023; Achiam et al., 2023; Team et al.,2024). Gradient influence scores (Pruthi et al., 2020; Xia et al., 2024) are shown to be correlated with model performance and are commonly used as the criterion for data selection. However, existing methods are built upon either individual sample rankings or inefficient matching process, leading to suboptimal performance or scaling up issues.In this paper, we propose Gradient Trajectory Pursuit (GTP), an algorithm that performs pu","authors_text":"Tao Li, Yang Li, Zhiwei Deng","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-22T05:32:40Z","title":"Influential Language Data Selection via Gradient Trajectory Pursuit"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16710","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":"sha256:7db14706968491bc89757148958cdeb94aa4ff5b45b73fd4a11e59d955c039d1","target":"record","created_at":"2026-07-05T09:24:05Z","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":"a9f6a3e861d3875b065f5a7abdf074476ec11dc2f8cecc6ebc67a0fdbd51e4d9","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-22T05:32:40Z","title_canon_sha256":"ad6fad52491d66196aa30d398be238c2aad326045c6c8acdd551431bdd6f1da6"},"schema_version":"1.0","source":{"id":"2410.16710","kind":"arxiv","version":1}},"canonical_sha256":"98438c05f519db3a901cbef1830eb404caf32f995d833464ebbdf6b4c4b9e789","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98438c05f519db3a901cbef1830eb404caf32f995d833464ebbdf6b4c4b9e789","first_computed_at":"2026-07-05T09:24:05.463213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:24:05.463213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qHTa5Xd9eJYIaMHOS7kRFpFB4dNzTXzaA+MCqWfbz8WbK00AwnQjR/Kacwmkk2l8yvx9GySxwfOszug6ghVrDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:24:05.463645Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16710","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7db14706968491bc89757148958cdeb94aa4ff5b45b73fd4a11e59d955c039d1","sha256:7e8a1cdc8bf412ea2d114ab6754af08af5b23abba0b82c68456a89e82b4fdc0c"],"state_sha256":"44257d2377580c8f28279522098093e012227153df667f98b3c5b079f83339a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KPLb4cAZUz+QhfOMoIqi34Cdbwt8rIc1ULkz1NLt7G0XcAJw7gUVSOAmIlmjheXuwTbYONcrr5pEP5WQhLR3Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:32:36.728816Z","bundle_sha256":"9bf7bcb019f5046c7cc9a6073acf87a431dfef23bd953c7c62802e1ee8003f12"}}