{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IQA5J27E2AXQTNGPQ5AB5GD5XD","short_pith_number":"pith:IQA5J27E","canonical_record":{"source":{"id":"2502.12953","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T15:36:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"df9fb0de01687abd37459d98a3dd8818a8cb558c48328afd4ea426aee62172ab","abstract_canon_sha256":"4da858c7fcc1c97ddeb6e125077b8eedce2e777264b37430fc0b4d7af431ae68"},"schema_version":"1.0"},"canonical_sha256":"4401d4ebe4d02f09b4cf87401e987db8d96129c4baa6f5ecc6588af6abe4a91a","source":{"kind":"arxiv","id":"2502.12953","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12953","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12953v2","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12953","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"pith_short_12","alias_value":"IQA5J27E2AXQ","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"pith_short_16","alias_value":"IQA5J27E2AXQTNGP","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"pith_short_8","alias_value":"IQA5J27E","created_at":"2026-07-05T11:10:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IQA5J27E2AXQTNGPQ5AB5GD5XD","target":"record","payload":{"canonical_record":{"source":{"id":"2502.12953","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T15:36:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"df9fb0de01687abd37459d98a3dd8818a8cb558c48328afd4ea426aee62172ab","abstract_canon_sha256":"4da858c7fcc1c97ddeb6e125077b8eedce2e777264b37430fc0b4d7af431ae68"},"schema_version":"1.0"},"canonical_sha256":"4401d4ebe4d02f09b4cf87401e987db8d96129c4baa6f5ecc6588af6abe4a91a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:05.139206Z","signature_b64":"0aujZ0obDO9ESGBMzwD1WE59UArH6ovh+0mZSnbp0RAYcqGNiIW0i0yajFgz8rgvnu2m6DS1aiaeKrvcHiwhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4401d4ebe4d02f09b4cf87401e987db8d96129c4baa6f5ecc6588af6abe4a91a","last_reissued_at":"2026-07-05T11:10:05.138692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:05.138692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.12953","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":"2026-07-05T11:10:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qJbFuRj1DnfC5wS7d+8r/Tz/n05VVb2L+xvasz0+r1QJL6MZFUnPbwSI+ZyFp/7CjhNNW8XqHLkqiKkCw5/RDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:51:29.619009Z"},"content_sha256":"4f097daef99688a6e0b26d5d5bc900728a894cd755dfa721befc35ad8d1a331e","schema_version":"1.0","event_id":"sha256:4f097daef99688a6e0b26d5d5bc900728a894cd755dfa721befc35ad8d1a331e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IQA5J27E2AXQTNGPQ5AB5GD5XD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Task-Informed Anti-Curriculum by Masking Improves Downstream Performance on Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrei Jarca, Florinel Alin Croitoru, Radu Tudor Ionescu","submitted_at":"2025-02-18T15:36:16Z","abstract_excerpt":"Masked language modeling has become a widely adopted unsupervised technique to pre-train large language models (LLMs). However, the process of selecting tokens for masking is random, and the percentage of masked tokens is typically fixed for the entire training process. In this paper, we propose to adjust the masking ratio and to decide which tokens to mask based on a novel task-informed anti-curriculum learning scheme. First, we harness task-specific knowledge about useful and harmful tokens in order to determine which tokens to mask. Second, we propose a cyclic decaying masking ratio, which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12953","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/2502.12953/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":"2026-07-05T11:10:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"degRKJW8Flu1FrVSB7+YsOnXMx30mDl7/HfSEXMTIO9fiFJ8LhRWtKHll5tWWqmq2M6DkFEDr1OvLjnAtqIVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:51:29.619516Z"},"content_sha256":"cf9a04518910412ce0355465a5a2775ce9e7e540bc35060ea3f8ed4ec49dd2e8","schema_version":"1.0","event_id":"sha256:cf9a04518910412ce0355465a5a2775ce9e7e540bc35060ea3f8ed4ec49dd2e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IQA5J27E2AXQTNGPQ5AB5GD5XD/bundle.json","state_url":"https://pith.science/pith/IQA5J27E2AXQTNGPQ5AB5GD5XD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IQA5J27E2AXQTNGPQ5AB5GD5XD/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":"2026-08-01T07:51:29Z","links":{"resolver":"https://pith.science/pith/IQA5J27E2AXQTNGPQ5AB5GD5XD","bundle":"https://pith.science/pith/IQA5J27E2AXQTNGPQ5AB5GD5XD/bundle.json","state":"https://pith.science/pith/IQA5J27E2AXQTNGPQ5AB5GD5XD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IQA5J27E2AXQTNGPQ5AB5GD5XD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IQA5J27E2AXQTNGPQ5AB5GD5XD","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":"4da858c7fcc1c97ddeb6e125077b8eedce2e777264b37430fc0b4d7af431ae68","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T15:36:16Z","title_canon_sha256":"df9fb0de01687abd37459d98a3dd8818a8cb558c48328afd4ea426aee62172ab"},"schema_version":"1.0","source":{"id":"2502.12953","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12953","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12953v2","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12953","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"pith_short_12","alias_value":"IQA5J27E2AXQ","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"pith_short_16","alias_value":"IQA5J27E2AXQTNGP","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"pith_short_8","alias_value":"IQA5J27E","created_at":"2026-07-05T11:10:05Z"}],"graph_snapshots":[{"event_id":"sha256:cf9a04518910412ce0355465a5a2775ce9e7e540bc35060ea3f8ed4ec49dd2e8","target":"graph","created_at":"2026-07-05T11:10:05Z","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/2502.12953/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Masked language modeling has become a widely adopted unsupervised technique to pre-train large language models (LLMs). However, the process of selecting tokens for masking is random, and the percentage of masked tokens is typically fixed for the entire training process. In this paper, we propose to adjust the masking ratio and to decide which tokens to mask based on a novel task-informed anti-curriculum learning scheme. First, we harness task-specific knowledge about useful and harmful tokens in order to determine which tokens to mask. Second, we propose a cyclic decaying masking ratio, which ","authors_text":"Andrei Jarca, Florinel Alin Croitoru, Radu Tudor Ionescu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T15:36:16Z","title":"Task-Informed Anti-Curriculum by Masking Improves Downstream Performance on Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12953","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":"sha256:4f097daef99688a6e0b26d5d5bc900728a894cd755dfa721befc35ad8d1a331e","target":"record","created_at":"2026-07-05T11:10:05Z","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":"4da858c7fcc1c97ddeb6e125077b8eedce2e777264b37430fc0b4d7af431ae68","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T15:36:16Z","title_canon_sha256":"df9fb0de01687abd37459d98a3dd8818a8cb558c48328afd4ea426aee62172ab"},"schema_version":"1.0","source":{"id":"2502.12953","kind":"arxiv","version":2}},"canonical_sha256":"4401d4ebe4d02f09b4cf87401e987db8d96129c4baa6f5ecc6588af6abe4a91a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4401d4ebe4d02f09b4cf87401e987db8d96129c4baa6f5ecc6588af6abe4a91a","first_computed_at":"2026-07-05T11:10:05.138692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:05.138692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0aujZ0obDO9ESGBMzwD1WE59UArH6ovh+0mZSnbp0RAYcqGNiIW0i0yajFgz8rgvnu2m6DS1aiaeKrvcHiwhDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:05.139206Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12953","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f097daef99688a6e0b26d5d5bc900728a894cd755dfa721befc35ad8d1a331e","sha256:cf9a04518910412ce0355465a5a2775ce9e7e540bc35060ea3f8ed4ec49dd2e8"],"state_sha256":"650a78676b43e8b2065b245b4f76e5eb2160c108b433ecf4b72a4cd42b178e95"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xanuIHTRM6WsaeQHmfwV2MyYbTr7C3ITkohpoQPgqI4kNFkhTTbAGupn8H0bW6UdhB532XJB2YvbD5F6iz9vDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T07:51:29.622985Z","bundle_sha256":"3ccc67c4c5febc9a77541f6ba83dd8cef6a72d8bb9c77ae504d18139e137fb54"}}