{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:F62P7YFE533KH5A3B66HV2MBWM","short_pith_number":"pith:F62P7YFE","canonical_record":{"source":{"id":"2505.07293","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T07:25:51Z","cross_cats_sorted":[],"title_canon_sha256":"f25ecf6175d2efdd89fe1b86c68b1075628c642132019d01c93db8bda20e56b6","abstract_canon_sha256":"96a30d920749f37c08d4d6076a80cb2a2672cd2211767837b4b6cf2c4d310007"},"schema_version":"1.0"},"canonical_sha256":"2fb4ffe0a4eef6a3f41b0fbc7ae981b32e7da08d44dd7e892e7e3ec936fedf4f","source":{"kind":"arxiv","id":"2505.07293","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07293","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07293v1","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07293","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"pith_short_12","alias_value":"F62P7YFE533K","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"pith_short_16","alias_value":"F62P7YFE533KH5A3","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"pith_short_8","alias_value":"F62P7YFE","created_at":"2026-07-05T11:01:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:F62P7YFE533KH5A3B66HV2MBWM","target":"record","payload":{"canonical_record":{"source":{"id":"2505.07293","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T07:25:51Z","cross_cats_sorted":[],"title_canon_sha256":"f25ecf6175d2efdd89fe1b86c68b1075628c642132019d01c93db8bda20e56b6","abstract_canon_sha256":"96a30d920749f37c08d4d6076a80cb2a2672cd2211767837b4b6cf2c4d310007"},"schema_version":"1.0"},"canonical_sha256":"2fb4ffe0a4eef6a3f41b0fbc7ae981b32e7da08d44dd7e892e7e3ec936fedf4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:45.665700Z","signature_b64":"Y1SedwdlD2EGO3QoNK4gwbKfv0MflTqCxqPWUX/IjTY+pujZLGoNIp//04XbJkoLao5KxTQcvW0+rQIwUgUvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fb4ffe0a4eef6a3f41b0fbc7ae981b32e7da08d44dd7e892e7e3ec936fedf4f","last_reissued_at":"2026-07-05T11:01:45.665172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:45.665172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.07293","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":"2026-07-05T11:01:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UaMWqwLboAq6ApJpXE+bx5J7J8J/xe7AqfOutaK2RFJe+/xjP0OfeywnnDhkuS3lHU70PRYGcdZtQf2goTZGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:12:17.099697Z"},"content_sha256":"ba00a6ca662d4d8c401c6f448439c508f0130983696c3cf6b819e85886cdbb79","schema_version":"1.0","event_id":"sha256:ba00a6ca662d4d8c401c6f448439c508f0130983696c3cf6b819e85886cdbb79"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:F62P7YFE533KH5A3B66HV2MBWM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ge Zhang, Kai Hua, Ke Shen, Steven Wu","submitted_at":"2025-05-12T07:25:51Z","abstract_excerpt":"Recently, there has been growing interest in collecting reasoning-intensive pretraining data to improve LLMs' complex reasoning ability. Prior approaches typically rely on supervised classifiers to identify such data, which requires labeling by humans or LLMs, often introducing domain-specific biases. Due to the attention heads being crucial to in-context reasoning, we propose AttentionInfluence, a simple yet effective, training-free method without supervision signal. Our approach enables a small pretrained language model to act as a strong data selector through a simple attention head masking"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07293","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/2505.07293/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":"2026-07-05T11:01:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t9GzzMoS71Lt8Qr95JyKxw8zdO47Pln6CFykKsEGeel1mc2GjwHJ5yKjjJ+kZwpmMVt7u32MWE+k+vkP3F/7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:12:17.100725Z"},"content_sha256":"a44b2658b2176fa21ff4dc4dd25cce6227f9b1d2ec7b98666898024a294c1f58","schema_version":"1.0","event_id":"sha256:a44b2658b2176fa21ff4dc4dd25cce6227f9b1d2ec7b98666898024a294c1f58"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F62P7YFE533KH5A3B66HV2MBWM/bundle.json","state_url":"https://pith.science/pith/F62P7YFE533KH5A3B66HV2MBWM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F62P7YFE533KH5A3B66HV2MBWM/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":"2026-08-03T19:12:17Z","links":{"resolver":"https://pith.science/pith/F62P7YFE533KH5A3B66HV2MBWM","bundle":"https://pith.science/pith/F62P7YFE533KH5A3B66HV2MBWM/bundle.json","state":"https://pith.science/pith/F62P7YFE533KH5A3B66HV2MBWM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F62P7YFE533KH5A3B66HV2MBWM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F62P7YFE533KH5A3B66HV2MBWM","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":"96a30d920749f37c08d4d6076a80cb2a2672cd2211767837b4b6cf2c4d310007","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T07:25:51Z","title_canon_sha256":"f25ecf6175d2efdd89fe1b86c68b1075628c642132019d01c93db8bda20e56b6"},"schema_version":"1.0","source":{"id":"2505.07293","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07293","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07293v1","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07293","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"pith_short_12","alias_value":"F62P7YFE533K","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"pith_short_16","alias_value":"F62P7YFE533KH5A3","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"pith_short_8","alias_value":"F62P7YFE","created_at":"2026-07-05T11:01:45Z"}],"graph_snapshots":[{"event_id":"sha256:a44b2658b2176fa21ff4dc4dd25cce6227f9b1d2ec7b98666898024a294c1f58","target":"graph","created_at":"2026-07-05T11:01:45Z","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/2505.07293/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, there has been growing interest in collecting reasoning-intensive pretraining data to improve LLMs' complex reasoning ability. Prior approaches typically rely on supervised classifiers to identify such data, which requires labeling by humans or LLMs, often introducing domain-specific biases. Due to the attention heads being crucial to in-context reasoning, we propose AttentionInfluence, a simple yet effective, training-free method without supervision signal. Our approach enables a small pretrained language model to act as a strong data selector through a simple attention head masking","authors_text":"Ge Zhang, Kai Hua, Ke Shen, Steven Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T07:25:51Z","title":"AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07293","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:ba00a6ca662d4d8c401c6f448439c508f0130983696c3cf6b819e85886cdbb79","target":"record","created_at":"2026-07-05T11:01:45Z","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":"96a30d920749f37c08d4d6076a80cb2a2672cd2211767837b4b6cf2c4d310007","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T07:25:51Z","title_canon_sha256":"f25ecf6175d2efdd89fe1b86c68b1075628c642132019d01c93db8bda20e56b6"},"schema_version":"1.0","source":{"id":"2505.07293","kind":"arxiv","version":1}},"canonical_sha256":"2fb4ffe0a4eef6a3f41b0fbc7ae981b32e7da08d44dd7e892e7e3ec936fedf4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fb4ffe0a4eef6a3f41b0fbc7ae981b32e7da08d44dd7e892e7e3ec936fedf4f","first_computed_at":"2026-07-05T11:01:45.665172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:45.665172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y1SedwdlD2EGO3QoNK4gwbKfv0MflTqCxqPWUX/IjTY+pujZLGoNIp//04XbJkoLao5KxTQcvW0+rQIwUgUvBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:45.665700Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07293","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba00a6ca662d4d8c401c6f448439c508f0130983696c3cf6b819e85886cdbb79","sha256:a44b2658b2176fa21ff4dc4dd25cce6227f9b1d2ec7b98666898024a294c1f58"],"state_sha256":"f8a21dca5e6975dc040c48db009cfa84a0fcaa7cbbbc9c24989dac2dae2eeb09"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OSZea2cRv7veb5Y7sUVD5lINvIE3qB+UXYb4U2D6BxX3mS2xgssS7G8TjanAsPKuRrt+YJQr3yjxYGM1IRBHDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:12:17.108412Z","bundle_sha256":"f371b652343b9b6389777169704c76d99b22508c43d744b4f450bfcc76e1f50f"}}